Search

Presurgical discrimination of 1p/19q codeletion status may have prognostic and diagnostic value for glioma patients for immediate personalized treatment. Artificial intelligence-based models have been proved as effective method to demonstrate computer aided diagnostic system for glioma cancer. An objective of study is to present an advanced biomedical texture descriptor to perform machine learning-assisted identification of 1p/19q codeletion status of low-grade glioma (LGG) cancer. An aim is to verify efficacy of textures, extracted using local binary pattern and derived from gray level co-occurrence matrix (GLCM). Proposed study used random forest-assisted radiomics model to analyse MRI images of 159 subjects. Four different advanced biomedical texture descriptors are proposed by experimenting different extensions of LBP method. These variants-(as variant I to IV) with 8-bit or 16-bit or 24-bit LBP codes are applied with different orientations in 5 × 5, 7 × 7 square-sized neighbourhood, which are recorded in LBP histograms. These histogram features are concatenated by GLCM-based textures including energy, correlation, contrast and homogeneity. Texture descriptors performed best with classification accuracy of 87.50% (AUC: 0.917, sensitivity: 95%, specificity: 75%, f1-score: 90.48%) using 8-bit LBP variant-I. 10-fold cross-validated accuracy of all four sets range from 65.62% to 87.50% using random forest classifier and mean-AUC range from 0.646 to 0.917.

The geometrically invariant image descriptors are very important for recognizing objects of arbitrary shapes and orientations. We propose a framework for the fusion of the geometrically invariant descriptors representing color, shape, and texture for the recognition of color objects using multiple kernel learning (MKL) approach. To describe texture of color images, we propose an effective rotation invariant texture descriptor which is based on the Zernike moments (ZMs) of the gradient of the color images, referred to as the GZMs. For the shape features, we use the ZMs of the intensity component of a color image and also use multi-channel ZMs (MZMs) which have proven to be superior in performance than the quaternion ZMs (QZMs). For comparative performance analysis, rotation invariants of the QZMs (RQZMs) are also considered. Since the color histograms (CH) are known to be very effective color descriptors, we consider them for representing color. The five sets of features – CH, ZMs, GZMs, MZMs, and RQZMs are invariant to translation, rotation, and scale. The fusion of color, shape and texture features in different combinations using the MKL approach is shown to provide very high recognition rates on PASCAL VOC 2005, Soccer, SIMPLIcity, Flower, and Caltech-101 datasets.

Texture can be defined as the change of image intensity that forms repetitive patterns resulting from the physical properties of an object’s roughness or differences in a reflection on the surface. Considering that texture forms a system of patterns in a non-deterministic way, biodiversity concepts can help its characterization from an image. This paper proposes a novel approach to quantify such a complex system of diverse patterns through species diversity, richness, and taxonomic distinctiveness. The proposed approach considers each image channel as a species ecosystem and computes species diversity and richness as well as taxonomic measures to describe the texture. Furthermore, the proposed approach takes advantage of ecological patterns’ invariance characteristics to build a permutation, rotation, and translation invariant descriptor. Experimental results on three datasets of natural texture images and two datasets of histopathological images have shown that the proposed texture descriptor has advantages over several texture descriptors and deep methods.

In this work we propose a new online, low cost and fast approach based on computer vision and machine learning to determine whether cutting tools used in edge profile milling processes are serviceable or disposable based on their wear level. We created a new dataset of 254 images of edge profile cutting heads which is, to the best of our knowledge, the first publicly available dataset with enough quality for this purpose. All the inserts were segmented and their cutting edges were cropped, obtaining 577 images of cutting edges: 301 functional and 276 disposable. The proposed method is based on (1) dividing the cutting edge image in different regions, called Wear Patches (WP), (2) characterising each one as worn or serviceable using texture descriptors based on different variants of Local Binary Patterns (LBP) and (3) determine, based on the state of these WP, if the cutting edge (and, therefore, the tool) is serviceable or disposable. We proposed and assessed five different patch division configurations. The individual WP were classified by a Support Vector Machine (SVM) with an intersection kernel. The best patch division configuration and texture descriptor for the WP achieves an accuracy of 90.26% in the detection of the disposable cutting edges. These results show a very promising opportunity for automatic wear monitoring in edge profile milling processes.

Glaucoma is an asymptomatic disease caused by damage to the optic nerve due to elevated intraocular pressure. With early diagnosis, the chances of controlling progression are greater. Glaucoma is a major global health problem as a cause of blindness, second only to cataracts. This paper presents the development of a method for the automatic detection of glaucoma in retinal images using a deep learning approach together with the exploration of texture attributes through phylogenetic diversity indexes. The methodology employed is as follows: First, image acquisition is done from the RIM-ONE, DRIONS-DB, and DRISHTI-GS databases, followed by training the convolutional neural network for optical disk segmentation. After this segmentation, it is necessary to perform removal of the blood vessels after which feature extraction is applied to the images generated from the RGB channels and the gray levels. The extracted attributes are based only on the features of texture using phylogenetic diversity indexes. Classification was performed using an approach based on the convolutional neural network. The method proved to be promising, achieving accuracy, sensitivity, and specificity of 100%. The medical expertise developed by the proposed method proved to be robust and efficient for the automatic detection task of glaucoma through retinal image analysis, using image processing and computational intelligence techniques. We thus propose a specialist system through the construction of a complete CAD tool to integrate into real clinical environments, providing a second opinion on the diagnosis of glaucoma quickly, efficiently, and at low cost.

In this work we describe a fast and stable algorithm for the computation of the orthogonal moments of an image. Indeed, orthogonal moments are characterized by a high discriminative power, but some of their possible formulations are characterized by a large computational complexity, which limits their real-time application. This paper describes in detail an approach based on recurrence relations, and proposes an optimized Matlab implementation of the corresponding computational procedure, aiming to solve the above limitations and put at the community's disposal an efficient and easy to use software. In our experiments we evaluate the effectiveness of the recurrence formulation, as well as its performance for the reconstruction task, in comparison to the closed form representation, often used in the literature. The results show a sensible reduction in the computational complexity, together with a greater accuracy in reconstruction. In order to assess and compare the accuracy of the computed moments in texture analysis, we perform classification experiments on six well-known databases of texture images. Again, the recurrence formulation performs better in classification than the closed form representation. More importantly, if computed from the GLCM of the image using the proposed stable procedure, the orthogonal moments outperform in some situations some of the most diffused state-of-the-art descriptors for texture classification., Comment: 29 pages, 9 figures

Detecting immature fruit in groves provides a promising benefit for growers to plan application of nutrients and estimate their yield and profit prior to harvesting. The goal of this study was to develop a robust algorithm to detect and count immature citrus fruit in images of the tree canopy. Images were all taken in low natural light conditions with a flashlight, and the green component of the colour images was used for further analysis. Local intensity maxima were detected and local binary pattern (LBP) features around them were extracted as an input of an ensemble classifier-RUSBoost. The positive predictions were considered as candidates and the hierarchical contour maps around them were extracted and fitted with Circular Hough Transform. The fitted circles were predicted as fruit targets if its radius were in a predetermined range. The algorithm was evaluated with a test set of 25 images, achieved 80.4% true positive rate and 82.3% precision rate, and F-measure was 81.3%. The good performance of occlusion tolerance of the proposed method was mainly coming from the robust LBP texture descriptor and hierarchical contour analysis (HCA) which used the pattern of light intensity distribution on fruit surface. This study proposed an innovative method to detect green fruit in images of trees only by using texture and intensity distribution.

The separation of malignant from benign lung nodules on chest computed tomography (CT) is important for the early detection of lung cancer, since early detection and management offer the best chance for cure. Although deep learning methods have recently produced a marked improvement in image classification there are still challenges as these methods contain myriad parameters and require large-scale training sets that are not usually available for most routine medical imaging studies. In this paper, we propose an algorithm for lung nodule classification that fuses the texture, shape and deep model-learned information (Fuse-TSD) at the decision level. This algorithm employs a gray level co-occurrence matrix (GLCM)-based texture descriptor, a Fourier shape descriptor to characterize the heterogeneity of nodules and a deep convolutional neural network (DCNN) to automatically learn the feature representation of nodules on a slice-by-slice basis. It trains an AdaBoosted back propagation neural network (BPNN) using each feature type and fuses the decisions made by three classifiers to differentiate nodules. We evaluated this algorithm against three approaches on the LIDC-IDRI dataset. When the nodules with a composite malignancy rate 3 were discarded, regarded as benign or regarded as malignant, our Fuse-TSD algorithm achieved an AUC of 96.65%, 94.45% and 81.24%, respectively, which was substantially higher than the AUC obtained by other approaches.

Regions in the visual field can be characterized by differences in texture, brightness, colour, or other attributes. Bilateral filter is an efficient way to smooth any digital image while preserving the fine information. In bilateral filter, it has been observed that by selecting carefully, the bilateral filter range parameter and bilateral filter domain parameter the ability to smooth any arbitrary digital image while preserving the edges can be improved. This trait of bilateral filter helps to adapt it to application specific requirements. In this study, a new feature extraction method is recommended by integrating the conventional Laws’ mask method with bilateral filter, which results in the improvement of classification accuracy. The texture features are extracted by using different values of range parameter and domain parameter and are fed as input to k-Nearest Neighbor (k-NN) classifier for classification. The new fusion model is tested with Brodatz, VisTex, STex and ALOT databases. The results of the proposed method are also compared with the conventional Laws’ mask descriptor for all the aforementioned four datasets. The experimental results show that bilateral filter based Laws’ mask feature extraction technique provides better classification accuracy for all the four databases for various combinations of bilateral filter range and domain parameters. Keywords: Bilateral filter, Laws mask descriptor, Feature extraction, Texture classification

In this paper, the three level descriptions from LTP and the directional features from LDP are combined to form a new local feature descriptor, referred to as local directional ternary pattern (LDTP) for texture classification. LDTP is a framework, which consists in encoding both contrast information and directional pattern features in a compact way based on local derivative variations. To achieve robustness, the proposed operator first computes for each pixel within its 3 × 3 overlapping grayscale image patch, on the one hand, eight directional edge responses using the eight Frei–Chen masks, and on the other hand, central edge response through the 2nd derivative of Gaussian filter to capture more detailed information. This allows producing a more discriminative encoding than several state-of-the art methods based only on intensity information. Then, spatial relationships among the neighboring pixels through the edge responses are exploited independently with the help of both LDP’s and LTP’s concepts to enhance the discrimination capability. Indeed, the implicit utilization of both concepts of LTP and LDP encodes more information in comparison to the existing directional and derivative methods in less space, and simultaneously allows discriminating more textures. Finally, the resultant LDTP pattern is divided into two distinct parts: local directional ternary pattern upper (LDTPU) and local directional ternary pattern lower (LDTPL), and the final feature descriptor vector is obtained by linear concatenation of both LDTPU and LDTPL histograms. The experiments carried out on nine publicly available texture datasets demonstrated that the proposed LDTP descriptor achieves classification performance, which is competitive or better than several recent and old state-of-the-art LBP variants. Statistical significance of the achieved accuracy improvement by the proposed descriptor has been also demonstrated through the Wilcoxon signed rank test applied on all the tested datasets.

We propose a novel local color texture descriptor called local binary pattern for color images (LBPC). The proposed descriptor uses a plane to threshold color pixels in the neighborhood of a local window into two categories. To boost the discriminative power of the proposed LBPC operator, local binary patterns of the hue component in the HSI color space, called the local binary pattern of the hue (LBPH) is derived. Further, LBPC, LBPH are fused to derive LBPC+LBPH which when combined with the color histogram (CH) of the hue component results in an effective image retrieval method LBPC+LBPH+CH. The uniform patterns of the two proposed descriptors ULBPC and ULBPH are combined to yield another low dimension local color descriptor ULBPC+ULBPH+CH which provides a good tradeoff between retrieval accuracy and speed. Detailed experiments conducted on Wang, Holidays, Corel-5K and Corel-10K datasets demonstrate that the proposed low dimension descriptors LBPC+LBPH+CH, and ULBPC+ULBPH+CH outperform the state-of-the-art color texture descriptors in terms of retrieval accuracy and speed.

Searching for similar images in large databases is a time-consuming work and an efficient image retrieval system is valuable in this situation. Texture is a prominent feature of image which can extract contents of image, hence a good texture feature extractor is necessary for content based image retrieval process. In this paper, a new texture descriptor is developed which is a combination of Local Ternary Pattern (LTP) and gray level co-occurrence matrix (GLCM). This feature descriptor which is named as CoALTP, inherits the attributes of both LTP and GLCM. First LTPs of pixels are obtained and then using GLCM in four directions, co-relations between pixel pairs are calculated as features. Two texture databases and a face images dataset are used for evaluation of proposed descriptor and results are compared with other local feature descriptors.

Nowadays, human-based video analysis becomes increasingly exhausting due to the ubiquitous use of surveillance cameras and explosive growth of video data. This paper proposes a novel approach to detect and localize video anomalies automatically. For video feature extraction, video volumes are jointly represented by two novel local motion based video descriptors, SL-HOF and ULGP-OF. SL-HOF descriptor captures the spatial distribution information of 3D local regions motion in the spatio-temporal cuboid extracted from video, which can implicitly reflect the structural information of foreground and depict foreground motion more precisely than the normal HOF descriptor. To locate the video foreground more accurately, we propose a new Robust PCA based foreground localization scheme. ULGP-OF descriptor, which seamlessly combines the classic 2D texture descriptor LGP and optical flow, is proposed to describe the motion statistics of local region texture in the areas located by the foreground localization scheme. Both SL-HOF and ULGP-OF are shown to be more discriminative than existing video descriptors in anomaly detection. To model features of normal video events, we introduce the newly-emergent one-class Extreme Learning Machine (OCELM) as the data description algorithm. With a tremendous reduction in training time, OCELM can yield comparable or better performance than existing algorithms like the classic OCSVM, which makes our approach easier for model updating and more applicable to fast learning from the rapidly generated surveillance data. The proposed approach is tested on UCSD ped1, ped2 and UMN datasets, and experimental results show that our approach can achieve state-of-the-art results in both video anomaly detection and localization task.

The paper presents a novel texture descriptor based on Local Binary Pattern.We address the problems of rotation invariance and illumination invariance.The proposed texture descriptor FbLBP is low-dimension.The results of FbLBP are compared with the state-of-the-art LBP-like variants. The local binary pattern (LBP) descriptor is widely used in texture analysis because of its computational simplicity and robustness to illumination changes. However, LBP has limitations to fully capture discriminative information since only the sign information of the difference vector in a local region is used. To enhance the performance of LBP, we propose a new descriptor for texture classificationfeature based local binary pattern (FbLBP). In the proposed FbLBP, difference vector is decomposed into sign part and magnitude part, the sign part is described by conventional LBP, while the magnitude part is described by two features of the mean and the variance of the magnitude vector. The way we extract magnitude information in difference vector shows high complementarity to the sign part and less sensitive to illumination changes with a low dimensionality. Furthermore, an adaptive local threshold is used to convert these two features into binary codes. The proposed low dimensional FbLBP is very fast to construct and no parameters are required to tune for different kinds of databases. Experimental results on four representative texture databases of Outex, CUReT, UIUC, and XU_HR show that the proposed FbLBP achieves more than 10% improvement compared with conventional LBP and 1%3% improvement compared with the best classification accuracy among other benchmarked state-of-the-art LBP variants.

In this work, the incorporation of content-based image retrieval (CBIR) into computer aided diagnosis (CADx) is investigated, in order to contribute to the decision-making process of radiologists in the characterization of mammographic masses. The proposed scheme comprises two stages: A margin-specific supervised CBIR stage that retrieves images from reference cases along with a decision stage that is based on the retrieved items. The feature set utilized exploits state-of-the-art features along with a newly proposed texture descriptor, namely mHOG, targeted to capturing margin and core specific mass properties. Performance evaluation considers the CBIR and diagnosis stages separately and is addressed by using standard measures on an enhanced version of the widely adopted digital database for screening mammography (DDSM). The proposed scheme achieved improved performance of CADx of masses in X-ray mammography experimentally compared to the state-of-the-art.

Textures widely exist in the natural scenes while traditional level set models generally use only intensity information to construct energy and ignore the inherent texture features. Thus these models have difficulty in segmenting texture images especially when the texture objects have similar intensity to the background. To solve this problem, we propose a new level set model for texture segmentation that considers the impact of local Gaussian distribution fitting (LGDF), local self-similarity (LSS) and a new numerical scheme on the evolving contour. The proposed method first introduces a texture energy term based on the local self-similarity texture descriptor to the LGDF model, and then the evolving contour could effectively snap to the textures boundary. Secondly, a lattice Boltzmann method (LBM) is deployed as a new numerical scheme to solve the level set equation, which can break the restriction of the Courant–Friedrichs–Lewy (CFL) condition that limits the time step of iterations in former numerical schemes. Moreover, GPU acceleration further improves the efficiency of the contour evolution. Experimental results show that our model can effectively handle the segmentation of synthetic and natural texture images with heavy noises, intensity inhomogeneity and messy background. At the same time, the proposed model has a relatively low complexity.

improved version of the Gaussians of Local Descriptorswe describe the covariance matrix using a set of visual featuresthe original approach and the new one are combined by sum rule This paper presents an improved version of a recent state-of-the-art texture descriptor called Gaussians of Local Descriptors (GOLD), which is based on a multivariate Gaussian that models the local feature distribution that describes the original image. The full rank covariance matrix, which lies on a Riemannian manifold, is projected on the tangent Euclidean space and concatenated to the mean vector for representing a given image. In this paper, we test the following features for describing the original image: scale-invariant feature transform (SIFT), histogram of gradients (HOG), and weber's law descriptor (WLD). To improve the baseline version of GOLD, we describe the covariance matrix using a set of visual features that are fed into a set of Support Vector Machines (SVMs). The SVMs are combined by sum rule. The scores obtained by an SVM trained using the original GOLD approach and the SVMs trained with visual features are then combined by sum rule. Experiments show that our proposed variant outperforms the original GOLD approach. The superior performance of the proposed system is validated across a large set of datasets. Particularly interesting is the performance obtained in two widely used person re-identification datasets, CAVIAR4REID and IAS, where the proposed GOLD variant is coupled with a state-of-the-art ensemble to obtain an improvement of performance on these two datasets. Moreover, we performed further tests that combine GOLD with non-binary features (local ternary/quinary patterns) and deep transfer learning. The fusion among SVMs trained with deep features and the SVMs trained using the ternary/quinary coding ensemble is demonstrated to obtain a very high performance across datasets. The MATLAB code for the ensemble of classifiers and for the extraction of the features will be publicly available11https://www.dei.unipd.it/node/2357 (+Pattern Recognition and Ensemble Classifiers) to other researchers for future comparisons.

Dynamic texture has been found as a powerful cue for modeling natural scenes such as fire, waves and smoke, etc. It combines appearance with motion to characterize the moving scene that exhibits certain spatially repetitive and time-varying visual patterns. This paper proposes a new method of recognizing dynamic texture using the well-known texture descriptor, local binary pattern. The new variant differentiates different structural patterns more efficiently using the additional information from the local patch. This pattern information is further combined with shape information to improve the discriminative power of texture descriptor. The proposed method is extended to multiscale using classifier fusion scheme to capture the spatio-temporal content of a moving scene at multiple scales, thus improves representation capability of the new descriptor. Proposed descriptor is tested on three dynamic texture databases: UCLA, Dyntex and Dyntex++. Results demonstrate that the proposed feature descriptor outperforms various state-of-the-art approaches on all representative databases in terms of classification accuracy.

A novel local pattern referred as Local Derivative Radial Pattern (LDRP) is proposed.Proposed LDRP is based on gray-level difference of pixels along a line.Instead of binary coding, multi-level coding in different directions is used as well.A new similarity measure is presented which is more robust against image rotation. In this paper, we propose a novel local pattern descriptor called Local Derivative Radial Pattern (LDRP) for texture representation in content-based image retrieval. All prior local patterns are based on gray-level difference of pixels located in a square or circle. Since many of the actual textures can be represented by intensity relationship of pixels along a line, these methods do not have a suitable ability to represent texture information. In prior methods, difference between referenced pixel and its adjacent pixel is encoded with two, three or four values which leads to information loss of the image. The proposed LDRP is based on gray-level difference of pixels along a line and their weighted combinations. In addition, multi-level coding in different directions is used instead of binary coding. The performance of the proposed method is compared with prior methods including local binary pattern (LBP), local ternary pattern (LTP), local derivative pattern (LDP), local tetra pattern (LTrP) and local vector pattern (LVP). The proposed LDRP outperforms all mentioned prior methods by at least 3.82% and 5.17% in terms of average precision on Brodatz and VisTex databases, respectively.

Texture descriptors such as local binary patterns (LBP) have been successfully employed for feature extraction in image retrieval algorithms because of their high discriminating ability and computational efficiency. In this paper, we propose histogram feature refinement methods for enhancing performance of texture descriptor based content-based image retrieval (CBIR) systems. In the proposed approach for histogram refinement, each pixel in the query and database images is classified into one of the two categories based on the analysis of pixel values in its neighborhood. Local patterns corresponding to two sets of pixels are used to generate two histogram features for each image, effectively resulting in splitting of the original global histogram of texture descriptors into two based on the category of each pixel. Resulting histograms are then concatenated to form a single histogram feature. This study also explores three hybrid frameworks for histogram refinement in CBIR systems. Comparison of histogram features corresponding to query and database images are performed using the relative l1 distance metric. Performance evaluation on three publicly available benchmark image databases namely, GHIM 10000, COREL 1000 database, and Brodatz texture database shows that performances of existing texture descriptor based approaches improve considerably when the proposed histogram feature refinement is incorporated. Specifically, the average precision rate is improved by 6.02%, 5.69%, 4.79%, and 4.21% for LBP, local derivative pattern (LDP), local ternary pattern (LTP), and local tetra pattern (LTrP) descriptors, respectively on GHIM 10000 database. The proposed histogram refinement approaches also provide performance improvement for other texture descriptors considered in this study. A general framework for histogram refinement of texture descriptors.Improves retrieval performance of texture descriptor based CBIR systems.Performance improvement in CBIR validated using 9 texture descriptors.Marginal increase in average image retrieval time with 1.2s in the worst case.

This paper proposes a new local texture descriptor, called quad binary pattern (QBP). Compared with local binary pattern (LBP), the QBP is with stronger robustness for feature extraction under complex scene (e.g., luminance change, similar target and background color) and with lower computational complexity. To demonstrate its effectiveness, the proposed QBP is further applied on the mean-shift tracking, in which a joint color-QBP model is developed to effectively represent the color and texture characteristics of the target region. Extensive simulation results have demonstrated that the proposed algorithm is able to improve the tracking speed and accuracy, compared with the standard mean-shift tracking and joint color-LBP model based mean-shift tracking.

Current advances in driver drowsiness detection consist of a variety of innovative technologies generally based on driver state monitoring systems. Extracting effective and relevant features to characterize drowsy symptoms in images and videos is still an open topic. In this work, we introduce a face monitoring system based on a compact face texture descriptor able to cover the most discriminant drowsy features. The compactness has been achieved by both a multi-scale pyramidal face representation that capture the main characteristics of local and global information, and the feature selection process applied on the raw extracted features. The proposed framework is rolled out in four phases: (i) face detection and alignment; (ii) Pyramid-Multi Level (PML) face representation; (iii) face description using a multi-level multi scale feature extraction; and (vi) feature subset selection and classification. Experiments conducted on the public dataset NTH Drowsy Driver Detection (NTHUDDD) show the effectiveness of the proposed face descriptor and the associated selection schemes. The results show that the proposed method compares favorably with several approaches including those based on deep Convolutional Neural Networks.

Describing texture is a very challenging problem for many image-based expert and intelligent systems (e.g. defective product detection, people re-identification, abnormality investigation in medical imaging and remote sensing applications … ) since the process of texture classification relies on the quality of the extracted features. Indeed, detecting and extracting features is a hard and time-consuming task that requires the intervention of an expert, notably when dealing with challenging textures. Thus, machine learning-based descriptors have emerged as another alternative to deal with the difficulty of feature extracting. In this work, we propose a new operator, which we named Local Edge Signature (LES) descriptor, to locally represent texture. The proposed texture descriptor is based on statistical information on edge pixels’ arrangement and orientation in a specific local region, and it is insensitive to rotation and scale changes. A genetic programming-based approach is then fitted to automatically learn a global texture descriptor that we called Genetic Texture Signature (GTS). In fact, a tree representation of individuals is used to generate global texture features by applying elementary operations on LES elements at a set of keypoints, and a fitness function evaluates the descriptors considering intra-class homogeneity and inter-class discrimination properties of their generated features. The obtained results, on six challenging texture datasets (Brodatz, Outex_TC_00000, Outex_TC_00013, KTH-TIPS, KTH-TIPS2b and UIUCTex), show that the proposed classification method, which is fully automated, achieves state-of-the-art performance, especially when the number of available training samples is limited.

Efficient feature description and classification of dynamic texture (DT) is an important problem in computer vision and pattern recognition. Recently, the local binary pattern (LBP) based dynamic texture descriptor has been proposed to classify DTs by extending the LBP operator used in static texture analysis to the temporal domain. However, the extended LBP operator cannot characterize the intrinsic motion of dynamic texture well. In this paper, we propose a novel video set based collaborative representation dynamic texture classification method. First, we divide the dynamic texture sequence into subsequences along the temporal axis to form the video set. For each DT, we extract the video set based LBP histogram to describe it. We then propose a regularized collaborative representation model to code the LBP histograms of the query video sets over the LBP histograms of the training video sets. Finally, with the coding coefficients, the distance between the query video set and the training video sets can be calculated for classification. Experimental results on the benchmark dynamic texture datasets demonstrate that the proposed method can yield good performance in terms of both classification accuracy and efficiency. The weighted volume local binary pattern descriptor is formed to represent dynamic texture.The weights are learned with a regularized collaborative representation model.The representation residual is used for dynamic texture classification.

A texture recognition method is proposed.The image is modeled into networks.The texture is characterized by the diffusion over the networks.It is demonstrated that directed networks are better to texture recognition.The proposed method outperform the state-of-the-art. Much work has been done in the field of texture analysis and classification. While promising classification methods have been proposed, most of them rely on classical image analysis approaches. This paper presents a texture classification method based on diffusion in directed networks. First, an image is modeled as a directed network by mapping each pixel as a node and connecting two nodes up to a maximum distance r. To reveal texture properties, links between two nodes are removed based on the pixel intensity difference. Once such a network is obtained, the activity of each node is estimated by random walks and combined into a histogram to describe the image. The main contribution of this paper is the use of directed networks, which tends to provide better performance than in undirected cases. Also, we have shown that the activity induced on these networks can be effectively used as texture descriptor. Experimental results show that the proposed method is favorably compared to traditional texture methods on widely used texture datasets. The proposed method is also found to be promising for plant species classification using samples of leaf texture.

International audience; An efficient texture modelling framework based on Topological Attribute Patterns (TAP) is presented considering topology related attributes calculated from Local Binary Patterns (LBP). Our main contribution is to introduce new efficient mapping mechanisms that improve some typical mappings for LBP-based operators in texture classification such as rotation invariant patterns (ri), rotation invariant uniform patterns (riu2), and Local Binary Count (LBC). Like them, the proposed approach allows contrast and rotation invariant image description using more compact descriptors by projecting binary patterns to a reduced feature space. However, its expressiveness, and then its discrimination capability, is higher, since it includes additional information, related to the connected components of the binary patterns. The proposed mapping, evaluated and compared with different popular mappings, validates the interest of our approach. We then develop Complemented Patterns of Topological Attributes (CTAP) that generalise TAP model and exploit complemented information to further enhance its discrimination capability, and evaluate it on different texture datasets.

Dynamic texture recognition method based on LBP and Michelson contrast is proposed.An adaptive threshold is proposed to compute the texture pattern in DT frames.Michelson contrast is used to compute the contrast of local image patch.A new formulation is devised to extend local binary pattern to spatiotemporal domain.Center pixel is combined with feature vector to boost its descriptive power. Dynamic textures (DTs) are moving sequences of natural scenes with some form of temporal regularity such as boiling water, a flag fluttering in the wind. The motion causes continuous changes in the geometry of dynamic textures thus it is difficult to apply traditional vision algorithms to recognize this class of textures. This paper proposes a scheme for modeling and classification of dynamic textures using a local image descriptor which efficiently encodes texture information in a space-time domain. The proposed descriptor extends the well-known spatial texture descriptor, local binary pattern (LBP), to spatio-temporal domain in order to represent the DT by combining appearance feature with the motion. Although, local binary patterns are used extensively in visual recognition applications due to their excellent performance and computational simplicity, but sometimes unable to differentiate different structures properly due to their dependency on center pixel as a threshold. In this paper, a new descriptor based on a global adaptive threshold is employed to compute the structure pattern of local image patch which differentiates various local image structures more efficiently. However, the LBP pattern defines the spatial structure of a local image patch but it does not give information about the contrast of local image patch. We have used Michelson contrast to compute the difference in luminance in the local texture and clubbed with local structure pattern computed using the proposed descriptor. Extensive experiments on dynamic texture databases (Dyntex, Dyntex++ and UCLA) prove the efficiency of the proposed method.

In this paper, we propose a new method for improving the performance of 2D descriptors by building an n-layer image using different preprocessing approaches from which multilayer descriptors are extracted and used as feature vectors for training a Support Vector Machine. The different preprocessing approaches are used to build different n-layer images (n=3, n=5, etc.). We test both color and gray-level images, two well-known texture descriptors (Local Phase Quantization and Local Binary Pattern), and three of their variants suited for n-layer images (Volume Local Phase Quantization, Local Phase Quantization Three-Orthogonal-Planes, and Volume Local Binary Patterns). Our results show that multilayers and texture descriptors can be combined to outperform the standard single-layer approaches. Experiments on 10 datasets demonstrate the generalizability of the proposed descriptors. Most of these datasets are medical, but in each case the images are very different. Two datasets are completely unrelated to medicine and are included to demonstrate the discriminative power of the proposed descriptors across very different image recognition tasks. A MATLAB version of the complete system developed in this paper will be made available at https://www.dei.unipd.it/node/2357.

The paper presents a novel texture descriptor based on Local Binary Patterns.We address the problem of rotation invariance and feature selections.The experiments are performed on standard datasets and the results are compared with the state-of-the-art.The source code to reproduce the results is made publicly available. In this paper, we present a novel rotation-invariant and computationally efficient texture descriptor called Dominant Rotated Local Binary Pattern (DRLBP). A rotation invariance is achieved by computing the descriptor with respect to a reference in a local neighborhood. A reference is fast to compute maintaining the computational simplicity of the Local Binary Patterns (LBP). The proposed approach not only retains the complete structural information extracted by LBP, but it also captures the complimentary information by utilizing the magnitude information, thereby achieving more discriminative power. For feature selection, we learn a dictionary of the most frequently occurring patterns from the training images, and discard redundant and non-informative features. To evaluate the performance we conduct experiments on three standard texture datasets: Outex12, Outex 10 and KTH-TIPS. The performance is compared with the state-of-the-art rotation invariant texture descriptors and results show that the proposed method is superior to other approaches.

A good image representation is critical to face recognition task. Recently, eight-direction Kirsch masks based image descriptors, e.g. local directional pattern (LDP), local sign directional pattern (LSDP), have been devised and shown competitive results than conventional LBP descriptor. However, these methods may lose or do not fully explore valuable texture information of the image. To remedy this drawback, a novel discriminative image descriptor, namely local edge direction and texture descriptor (LEDTD) is proposed in this paper. LEDTD differs from the existing Kirsch based methods in a manner that it not only considers image edge direction information but also extracts image texture feature by encoding the edge response directions of center and its neighborhood pixels by employing local XOR binary coding strategy. Finally, edge direction and texture features are integrated to form the image feature vector. Extensive performance evaluations on four benchmark face databases show that the proposed approach yields a better performance in terms of the recognition rate as well as robustness to the noise compared with the state of the art methods.

HighlightsAn automated GI hemorrhage detection scheme from WCE images is proposed..Features from the NGLCM of the spectrum of the frames and SVM are employed.We introduce difference average- a new feature that operates on NGLCM.Validity of the method is confirmed by statistical and graphical analyses.The performance of the proposed scheme, compared to the existing ones is promising. Background and objectiveWireless Capsule Endoscopy (WCE) can image the portions of the human gastrointestinal tract that were previously unreachable for conventional endoscopy examinations. A major drawback of this technology is that a large volume of data are to be analyzed in order to detect a disease which can be time-consuming and burdensome for the clinicians. Consequently, there is a dire need of computer-aided disease detection schemes to assist the clinicians. In this paper, we propose a real-time, computationally efficient and effective computerized bleeding detection technique applicable for WCE technology. MethodsThe development of our proposed technique is based on the observation that characteristic patterns appear in the frequency spectrum of the WCE frames due to the presence of bleeding region. Discovering these discriminating patterns, we develop a texture-feature-descriptor-based-algorithm that operates on the Normalized Gray Level Co-occurrence Matrix (NGLCM) of the magnitude spectrum of the images. A new local texture descriptor called difference average that operates on NGLCM is also proposed. We also perform statistical validation of the proposed scheme. ResultsThe proposed algorithm was evaluated using a publicly available WCE database. The training set consisted of 600 bleeding and 600 non-bleeding frames. This set was used to train the SVM classifier. On the other hand, 860 bleeding and 860 non-bleeding images were selected from the rest of the extracted images to form the test set. The accuracy, sensitivity and specificity obtained from our method are 99.19%, 99.41% and 98.95% respectively which are significantly higher than state-of-the-art methods. In addition, the low computational cost of our method makes it suitable for real-time implementation. ConclusionThis work proposes a bleeding detection algorithm that employs textural features from the magnitude spectrum of the WCE images. Experimental outcomes backed by statistical validations prove that the proposed algorithm is superior to the existing ones in terms of accuracy, sensitivity, specificity and computational cost.

International audience; The proposal of this study is to analyze the texture pattern recognition over the local jet space looking forward to improve the texture characterization. Local jets decompose the image based on partial derivatives allowing the texture feature extraction be exploited in different levels of geometrical structures. Each local jet component evidences a different local pattern, such as, flat regions, directional variations and concavity or convexity. Subsequently , a texture descriptor is used to extract features from 0th, 1st and 2nd-derivative components. Four well-known databases (Brodatz, Vistex, Usptex and Outex) and four texture descriptors (Fourier descriptors, Gabor filters, Local Binary Pattern and Local Binary Pattern Variance) were used to validate the idea, showing in most cases an increase of the success rates.

In the coal-fire industry, recognition of burning condition is vital for combustion control and optimization as it can provide early warning of abnormal conditions in the combustion system. We propose an effective model based on spatiotemporal features extracted from flame video for burning condition recognition especially for unsteady state condition. This model extracts features from both the spatial and temporal dimensions based on multiple adjacent frames to capture the appearance and motion information of the flame. Two new three-dimensional (3D) descriptors are developed to characterize the dynamic characteristics of the flame video stream. A computationally simple and fast dynamic texture descriptor, 3DBLBP, is designed to extract flame dynamic texture and motion from three adjacent frames of a video block, and a dynamic structure descriptor, HOPC-TOP is developed by extracting 3D phase congruency information of video clip from three orthogonal planes to capture structure and motion characterizes of flame. The two descriptors are combined to extract spatiotemporal features from flame clip for burning condition recognition. Experiment results show the proposed framework can achieve a high recognition accuracy in the real-world data, thus verifying the effectiveness of our proposed framework for the recognition of burning conditions in a rotary kiln.

In this paper, we propose a novel descriptor called spatially weighted order binary pattern (SWOBP) for color texture classification. The SWOBP descriptor not only encodes color order information in different channels but also encodes color order relationships in the spatial domain. To achieve these goals, we introduce a color gradient channel to complement the traditional color channels and explore a multi-channel color order pattern to jointly encode inter-channel features. Furthermore, we decompose local color differences into spatially weighted binary templates and use them to encode color order information in a local neighborhood. Finally, we aggregate all the encoded features into image histograms as texture descriptor. Experiments on five benchmark databases demonstrate that the proposed SWOBP descriptor achieves the state-of-the-art performance for color texture classification.

In this paper, we propose a texture descriptor, called Wavelet Domain Directional Binary Pattern using Majority Principle (WDDBP θ ) which integrates the discrete wavelet transform and Local Binary Pattern (LBP). The discrete wavelet transform provides the directional information, while LBP describes the texture features predominately. The proposed approach consists of four phases. In the first phase, the image is subjected to single level decomposition; resulting in discrete wavelet coefficients. The wavelet coefficients present at various distances; one, two and three are compared among themselves which results in sign pattern. In the second phase, the difference of wavelet coefficients located at different distances are compared with global difference of wavelet coefficient and results in magnitude pattern. In the third phase, the majority principle is applied for both sign and magnitude pattern resulting in WDDBP_S and WDDBP_M pattern. Finally, the histogram of both WDDBP_S and WDDBP_M is concatenated. The proposed method is also evaluated by involving the wavelet coefficients present at twelve different directions. The K-NN algorithm is applied to classify the input and database images. The experimental results demonstrate that the proposed method outperforms the other existing methods on Brodatz and Outex database with improved classification accuracy.

In this paper, we present an efficient and distinctive local descriptor, namely block intensity and gradient difference ( BIGD ). In an image patch, we randomly sample multi-scale block pairs and utilize the intensity and gradient differences of pairwise blocks to construct the local BIGD descriptor. The random sampling strategy and the multi-scale framework help BIGD descriptors capture the distinctive patterns of patches at different orientations and spatial granularity levels. We use vectors of locally aggregated descriptors (VLAD) or improved Fisher vector (IFV) to encode local BIGD descriptors into a full image descriptor, which is then fed into a linear support vector machine (SVM) classifier for texture classification. We compare the proposed descriptor with typical and state-of-the-art ones by evaluating their classification performance on five public texture data sets including Brodatz, CUReT, KTH-TIPS, and KTH-TIPS-2a and -2b. Experimental results show that the proposed BIGD descriptor with stronger discriminative power yields 0 . 12 % ∼ 6 . 43 % higher classification accuracy than the state-of-the-art texture descriptor, dense microblock difference (DMD).

An adjacent evaluation window is constructed to modify threshold scheme of LBP.The adjacent evaluation derives two new descriptors: AECLBP and AELTP.The adjacent evaluation plays an important role in solving sensitivity to noise.The proposed approaches are experimented on five texture databases. This paper presents a novel, simple, yet robust texture descriptor against noise named the adjacent evaluation local binary patterns (AELBP) for texture classification. In the proposed approach, an adjacent evaluation window is constructed to modify the threshold scheme of LBP. The neighbors of the neighborhood center gc are set as the evaluation center ap. Surrounding the evaluation center, we set up an evaluation window and calculate the value of ap, and then extract the local binary codes by comparing the value of ap with the value of the neighborhood center gc. Moreover, this adjacent evaluation method is generalized and can be integrated with the existing LBP variants such as completed local binary pattern (CLBP) and local ternary pattern (LTP) to derive new image features against noise for texture classification. The proposed approaches are compared with the state-of-the-art approaches on Outex and CUReT databases, and evaluated on three challenging databases (i.e. UIUC, UMD and ALOT databases) for texture classification. Experimental results demonstrate that the proposed approaches present a solid power of texture classification under illumination and rotation variations, significant viewpoint changes, and significant large-scale challenging conditions. Furthermore, the proposed approaches are more robust against noise and consistently outperform all the basic approaches in comparison.

For tea processing production lines, different fresh tea leaves require different processing parameters for the control systems of tea machines. Hence, an effective algorithm for classification of tea leaves will be important for automatic tea processing. However, most of tea classification researches were focused on gross tea, instead of fresh tea leaves. In this paper, a texture extraction method combing a non-overlap window local binary pattern (LBP) and Gray Level Co-Occurrence Matrix (GLCM) has been proposed for green tea leaves classification. By taking advantages of both LBP and GLCM for texture extraction, this method is able to effectively extract texture of tea leaves for classification at low computational cost to meet automatic tea production line requirements. The experiments have been conducted to prove the effectiveness of the proposed method. An effective method of tea leaves classification is crucial for the real-time control of tea production lines.The proposed method for tea leaves classification combines a Non-Overlap Window LBP and GLCM, which has better discrimination ability and classification accuracy, compared with other traditional approaches.The proposed texture descriptor requires much lower computation load than that of classic LBP and GLCM, thanks to the power of the Non-Overlap Window LBP.

Local binary pattern is introduced to highlight the local texture artifacts from seam carving.Six new half-seam features are defined to unveil the energy bias in the upper and lower half-images.All the features are extracted in LBP domain, instead of conventional pixel domain. Seam carving is the most popular content-aware image retargeting technique. However, it can also be deliberately used for object removal tampering. In this paper, a blind image forensics approach is proposed for seam-carved forgery detection. Since seam carving changes the local texture in an image, a local texture descriptor, i.e., local binary pattern (LBP), is exploited as pre-processing to highlight the local texture artifacts. Moreover, six new half-seam features are defined to unveil the energy changes in half images. They are combined with the existing eighteen energy bias and noise-based features to form twenty-four features. These features are extracted in LBP domain, instead of the conventional pixel-domain to highlight the local texture changes. Finally, support vector machine (SVM) classifier is exploited to determine whether an image is original or suffered from seam carving. Experimental results show that compared with the state-of-the-art methods, the proposed approach improves the detection accuracy by 3.5-19.1% for resized images with different scaling ratios.

Transient Binary Patterns of gait sequence.Inherently combines both appearance information and temporal information.Less sensitive to silhouette noise in individual frames. In this work, we present a combination of spatiotemporal approach and texture descriptors to extract the temporal patterns in gait cycles. Unlike most conventional methods that focus on spatial information while limiting temporal information captured, spatiotemporal methods preserve both spatial and temporal information. Inspired by the success of texture descriptors in face recognition, the proposed method likewise constructs texture descriptors of gait motion over time. For each gait cycle, the pixel-wise binary patterns along the temporal axis, referred to as the Transient Binary Patterns (TBP), is analyzed. These pixel-wise TBPs are then grouped into regional blocks from which we construct regional TBP histograms. These regional TBP histograms collectively form the global TBP histogram that represents both the distribution of temporal patterns and spatial location. Experimental results clearly show the superiority of the proposed approach over other considered methods.

In this letter, we present a rotation-invariant texture descriptor in a multi-resolution framework.The proposed method is robust to Gaussian noise, and it can be used for both noise-free and noisy texture classification.Experimental results on three well-known texture datasets indicate that the proposed method achieves high texture classification accuracy, especially in the presence of various levels of Gaussian noise. In this letter an effective multi-resolution and rotation-invariant texture description approach is presented, which can be utilized in various computer vision and image processing tasks such as texture classification and texture segmentation. In the proposed method, a given gray-scale texture image is first processed by a bank of Gabor wavelets (filters) at different scales and orientations. The obtained filters' responses are then further processed, and a set of local binary patterns called "Local Gabor Wavelets Binary Patterns" (LGWBPs) are computed by comparing the local filters' outputs at different orientations with the global mean of filters' outputs at the same orientations. The obtained patterns are then converted to a number of decimal rotation-invariant codes, and a histogram of the resultant codes at different scales is finally used as a texture feature vector. Experimental results on three popular texture datasets (Outex TC10, CUReT, and Brodatz) indicate that the proposed method achieves high texture classification accuracy, especially in the presence of various levels of Gaussian noise.

In this study, two novel local binary patterns were proposed.First one is based on spatial relations between neighbors with a distance parameter.The second is based on relations between a reference pixel and its neighbor on the same orientation.Two approaches are improved to detect special patterns in images.The results show that the proposed approaches can be used in image processing areas. The recent developments in the image quality, storage and data transmission capabilities increase the importance of texture analysis, which plays an important role in computer vision and image processing. Local binary pattern (LBP) is an effective statistical texture descriptor, which has successful applications in texture classification. In this paper, two novel descriptors were proposed to search different patterns in images built on LBP. One of them is based on the relations between the sequential neighbors with a specified distance and the other one is based on determining the neighbors in the same orientation through central pixel parameter. These descriptors are tested with the Brodatz-1, Brodatz-2, Butterfly and Kylberg datasets to show the applicability of the proposed nLBPd and dLBPα descriptors. The proposed methods are also compared with classical LBP. The average accuracies obtained by ANN with 10 fold cross validation, which are 99.26% (LBPu2 and nLBPd), 94.44% (dLBPα), 95.71% ( n L B P d u 2 ) and %99.64 (nLBPd), for Brodatz-1, Brodatz-2, Butterfly and Kylberg datasets, respectively, show that the proposed methods outperform significant accuracies.

This paper addresses the challenging problem of the recognition and classification of textured surfaces given a single instance acquired under unknown pose, scale and illumination conditions. We propose a novel texture descriptor, the Adaptive Median Binary Pattern (AMBP) based on an adaptive analysis window of local patterns. The principal idea of the AMBP is to convert a small local image patch to a binary pattern using adaptive threshold selection that switches between the central pixel value as used in the Local Binary Pattern (LBP) and the median as in Median Binary Pattern (MBP), but within a variable sized analysis window depending on the local microstructure of the texture. The variability of the local adaptive window is included as joint information to increase the discriminative properties. A new multiscale scheme is also proposed in this paper to handle the texture resolution problem. AMBP is evaluated in relation to other recent binary pattern techniques and many other texture analysis methods on three large texture corpora with and without noise added, CUReT, Outex_TC00012 and KTH_TIPS2. Generally, the proposed method performs better than the best state-of-the-art techniques in the noiseless case and significantly outperforms all of them in the presence of impulse noise. HighlightsNew method for texture analysis and classification.Adaptive approach to extract the local patterns is proposed.Combining different information with the joint histogram.New multiscale scheme of the texture cue is proposed.The classification accuracy reach high rates and robustness for impulse noise.

To detect smoke regions from video clips, a novel dynamic texture descriptor is proposed with Surfacelet transform and hidden Markov tree (HTM) model. The image sequence is multi-scale decomposed by a pyramid model, and the signals are decomposed to different directions using 3D directional filter banks. Then a 3D HMT model is built for obtained coefficients from Surfacelet transform with both Gaussian mixture model and scale continuity model. Parameters of the HMT model are estimated through expectation maximization algorithm, and the joint probability density is determined as the dynamic texture feature value. Support vector machine (SVM) classifier is trained with samples including smoke and non-smoke videos. For input image sequence, the joint probability density of each divided unit 3D block is taken as the input of SVM to decide whether there is smoke. The new dynamic texture descriptor takes image sequence as a multidimensional volumetric data, i.e., considering both spatial and temporal information of coefficients into one model. In experiments, existing texture descriptors of gray level co-occurrence matrix (GLCM), local binary pattern (LBP) and Wavelet are implemented and used for comparison. Results from many real smoke videos have proved that the new dynamic texture descriptor can obtain higher detection accuracy.

A simple and efficient discrete wavelet transform (DWT) based first-order statistical (FOS) texture descriptor is proposed in this paper to accurately classify the microscopic images of hardwood species. Primarily, DWT decomposes each image up to 8 levels using selected Daubechies (db1- db10) wavelet as a decomposition filter. Subsequently, four FOS features, namely, mean, standard deviation, skewness and kurtosis are employed to obtain substantial signatures of these images at different levels. The db3 based FOS texture features has achieved 96.80% classification accuracy compared to 93.20% classification accuracy obtained by local binary pattern features using linear support vector machine (SVM) classifier.

We show that combining multiple texture description methods significantly improves the performance compared to using the single best texture method alone.We further propose to use information theoretic compression approach to compress high-dimensional multi-texture features into a compact heterogeneous texture representation.We perform a comprehensive evaluation of color features, popular in object recognition, for the task of texture classification.We show that late fusion of our compact texture descriptor with discriminative color feature outperforms state-of-the-art results on challenging texture recognition datasets. Describing textures is a challenging problem in computer vision and pattern recognition. The classification problem involves assigning a category label to the texture class it belongs to. Several factors such as variations in scale, illumination and viewpoint make the problem of texture description extremely challenging. A variety of histogram based texture representations exists in literature. However, combining multiple texture descriptors and assessing their complementarity is still an open research problem. In this paper, we first show that combining multiple local texture descriptors significantly improves the recognition performance compared to using a single best method alone. This gain in performance is achieved at the cost of high-dimensional final image representation. To counter this problem, we propose to use an information-theoretic compression technique to obtain a compact texture description without any significant loss in accuracy. In addition, we perform a comprehensive evaluation of pure color descriptors, popular in object recognition, for the problem of texture classification. Experiments are performed on four challenging texture datasets namely, KTH-TIPS-2a, KTH-TIPS-2b, FMD and Texture-10. The experiments clearly demonstrate that our proposed compact multi-texture approach outperforms the single best texture method alone. In all cases, discriminative color names outperforms other color features for texture classification. Finally, we show that combining discriminative color names with compact texture representation outperforms state-of-the-art methods by 7.8%, 4.3% and 5.0% on KTH-TIPS-2a, KTH-TIPS-2b and Texture-10 datasets respectively.

Local binary pattern (LBP) is a texture descriptor that has been proven to be quite effective for various image analysis tasks in image processing. In this paper one-dimensional local binary pattern (1D-LBP) based features are used for classification of seizure and seizure-free electroencephalogram (EEG) signals. The proposed method employs a bank of Gabor filters for processing the EEG signals. The processed EEG signal is divided into smaller segments and histograms of 1D-LBPs of these segments are computed. Nearest neighbor classifier utilizes the histogram matching scores to determine whether the acquired EEG signal belongs to seizure or seizure-free category. Experimental results on publicly available database suggest that the proposed features effectively characterize local variations and are useful for classification of seizure and seizure-free EEG signals with a classification accuracy of 98.33%. This result demonstrates the superiority of our approach for classification of seizure and seizure-free EEG signals over recently proposed approaches in the literature.

In this paper, we proposed a system of automatically classifying different types of dates from their images. Different dates have various distinguished features that can be useful to recognize a particular date. These features include color, texture, and shape. In the proposed system, a color image of a date is decomposed into its color components. Then, local texture descriptor in the form of local binary pattern (LBP) or Weber local descriptor (WLD) histogram is applied to each of the components to encode the texture pattern of the date. The texture patterns from all the components are fused to describe the image. Fisher discrimination ratio (FDR) based feature selection is utilized to reduce the dimensionality of the feature set. Size and shape features are appended to the texture descriptors to fully describe the date. As a classifier, we use support vector machines. The proposed system achieves more than 98% accuracy to classify the dates.

Feature extraction plays a great important role in image processing and pattern recognition. As a power tool, multifractal theory is recently employed for this job. However, traditional multifractal methods are proposed to analyze the objects with stationary measure and cannot for non-stationary measure. The works of this paper is twofold. First, the definition of stationary image and 2D image feature detection methods are proposed. Second, a novel feature extraction scheme for non-stationary image is proposed by local multifractal detrended fluctuation analysis (Local MF-DFA), which is based on 2D MF-DFA. A set of new multifractal descriptors, called local generalized Hurst exponent ( Lh q ) is defined to characterize the local scaling properties of textures. To test the proposed method, both the novel texture descriptor and other two multifractal indicators, namely, local Holder coefficients based on capacity measure and multifractal dimension D q based on multifractal differential box-counting (MDBC) method, are compared in segmentation experiments. The first experiment indicates that the segmentation results obtained by the proposed Lh q are better than the MDBC-based D q slightly and superior to the local Holder coefficients significantly. The results in the second experiment demonstrate that the Lh q can distinguish the texture images more effectively and provide more robust segmentations than the MDBC-based D q significantly.

This paper proposes a novel robust texture descriptor based on Gaussian Markov random fields (GMRFs). A spatially localized parameter estimation technique using local linear regression is performed and the distributions of local parameter estimates are constructed to formulate the texture features. The inconsistencies arising in localized parameter estimation are addressed by applying generalized inverse, regularization and an estimation window size selection criterion. The texture descriptors are named as local parameter histograms (LPHs) and are used in texture segmentation with the k-means clustering algorithm. The segmentation results on general texture datasets demonstrate that LPH descriptors significantly improve the performance of classical GMRF features and achieve better results compared to the state-of-the-art texture descriptors based on local feature distributions. Impressive natural image segmentation results are also achieved and comparisons to the other standard natural image segmentation algorithms are also presented. LPH descriptors produce promising texture features that integrate both statistical and structural information about a texture. The region boundary localization can be further improved by integrating colour information and using advanced segmentation algorithms. Display Omitted Distributions of GMRF local parameter estimates as improved texture descriptors.Spatially localized parameter estimation using local linear regression.Approaches to overcome inconsistencies in localized parameter estimation.Proposed descriptors capture both spatial dependencies and distributions of texture.