Search

Face recognition is used in many applications such as access control, automobile security, criminal identification, immigration, healthcare, cyber security, and so on. Each person has his/her own unique face, so the face can help distinguish people from each other. Feature extraction process plays a fundamental role in accuracy of face recognition, and many algorithms have been presented to extract more informative features from the face image. In this paper, an efficient texture descriptor is proposed based on local information of the face image. In the proposed method, at first, face image is split into several sub-images in such a way that each sub-image includes one of the facial parts such as eyes, nose, and lips. Second, texture features are extracted from each sub-image using a new local pattern descriptor, and then features of sub-images are concatenated to construct feature vector. Finally, the face image is compared to images in a dataset based on a similarity measure. In addition, particle swarm optimization algorithm is used to assign weight to the features of different parts of the face image. To evaluate the proposed algorithm, four face datasets, Yale, ORL, GT and KDEF, are used. Implementation results show that the proposed method outperforms recent methods in terms of accuracy, receiver operating characteristic (ROC) curve, and area under ROC curve. [ABSTRACT FROM AUTHOR]

Facial recognition technology has emerged as the most important element in many interactive AI systems due to its ease and accuracy on par with that of humans. Nevertheless, its dependable deployment is constrained by vulnerability to presentation attacks. Therefore, for facial recognition technology to be used safely in unsupervised situations, automatic detection of presentation attacks is crucial. In this context, we propose a novel deep face spoof detection framework, which employs multi-level Elliptical Local Binary Pattern (ELBP) and stacked LSTMs. The ELBP, a variant of Local Binary Patterns (LBPs), is utilized in three levels for three color spaces—RGB, HSV, and RGB + HSV—to acquire discriminating features. We evaluate our framework through extensive experiments on two publicly available and challenging datasets—CASIA-FASD, CASIA-SURF, and OULU-NPU. The experimental results demonstrate that our framework achieves better performance in terms of APCER, NPCER, ACER, EER, ROCs, and confusion matrix. [ABSTRACT FROM AUTHOR]

Abstract At present, facial recognition entertains great importance in performing authentication processes, because it prevents unauthorized access to devices and places. Additionally, it allows for the identification of persons. Henceforth, this paper proposes a novel texture descriptor called Cyclical Chroma and a new classification technique, which takes in consideration the sub‐pixel values of 0–255 for each RGB (Red, Green, Blue) channel that conforms the image. To verify the effectiveness of the proposed techniques, tests were performed with a database of images in a controlled environment and in one under uncontrolled conditions; additionally, Cyclical Chroma was tested with a different classifier, denominated the Multiclass Classifier, and the results were compared against other descriptors, including GLCM, SHDH, LQP, and CCR, demonstrating the effectiveness of the proposed techniques with 100% efficiency with controlled images and 78% effectiveness under uncontrolled conditions prior to the application of an equalization technique, increasing the efficiency to 100%.

The tensile strength of the ECAP processed composite of AA6063/(Si3N4)x/(Cu(NO3)2)y (x=12%, y=2-6%) at various strain rates from 0.0001 to 1s-1 with an increment of 10 was examined in relation to the seven-fracture image texture descriptor through void features such as void size and distribution. In order to measure the matrices of voids on the fracture surface created through the coalescence of void results to enhance the material hardening as strain rate increases, the second order statistical texture analysis has been used. With respect to the rising strain rate, it was observed that the composite fracture image feature parameter correlation, homogeneity improved by 6 %, and 20.74% for AA6063/12%Si3N4/6%Cu(NO3)2 after I passes as compared to AA6063/12% Si3N4 after III pass. The contrast was reduced by around 58.643% when reinforcement went from a single reinforcement of 12% Si3N4 with I Pass to a composite of two reinforcements (Si3N4, Cu(NO3)2) that had 6% Cu(NO3)2 with I Pass. After three passes on AA6063/12%Si3N4/2%Cu(NO3)2, the maximum entropy was seen due to the material's increased plastic deformation, which led to an uneven particle distribution. As strain rate and copper nitrate percentage grew from 0 to 6 percent, the tensile strength of the composite improved by 34.69%. To assess the importance of fracture image features in relation to tensile strength with respect to strain rate, a regression model was developed. In order to get information about the fracture studies from fractography, the contrast with varying strain rate was nevertheless the aspect, which had the greatest influence.

At present, facial recognition entertains great importance in performing authentication processes, because it prevents unauthorized access to devices and places. Additionally, it allows for the identification of persons. Henceforth, this paper proposes a novel texture descriptor called Cyclical Chroma and a new classification technique, which takes in consideration the sub‐pixel values of 0–255 for each RGB (Red, Green, Blue) channel that conforms the image. To verify the effectiveness of the proposed techniques, tests were performed with a database of images in a controlled environment and in one under uncontrolled conditions; additionally, Cyclical Chroma was tested with a different classifier, denominated the Multiclass Classifier, and the results were compared against other descriptors, including GLCM, SHDH, LQP, and CCR, demonstrating the effectiveness of the proposed techniques with 100% efficiency with controlled images and 78% effectiveness under uncontrolled conditions prior to the application of an equalization technique, increasing the efficiency to 100%. [ABSTRACT FROM AUTHOR]

Background: Convolutional Neural Network (CNN) has exciting advantages in the processing of medical images. It produces the denoised and segmented results of images. When an image has orientation and scaling issues over the bundle that is not correctly recognized by the classifier. Methods: To overcome these issues, we propose Extreme Deep Learning on Feature Fusion Convolutional Neural Network (EDL‐FFCNN) for classification. Feature fusion workflow enhances the ability to learn the feature from the inconsistent behaviour. And, to learn the texture, colour, and intensities of an image. The initial step of the FFCNN framework is to reconstruct the images using filtered back projection. It reduces the noise in edges and cross‐sectional areas. Contrast Limited Adaptive Histogram Equalization and Local Binary Pattern is applied to an image to adjust and extract the intensity and textural features of an image. The proposed FFCNN is a decision‐based approach that consists of two persistent classifiers. One, the convolutional features are combined with manually extracted multi‐scaled features. Subsequently, the normalization techniques are built‐in every layer to adjust the input dimensions. It also helps to reduce the training time. As an outcome of Image abnormalities is considered as knowledge transfer to the CNN. Results: The fused features on the CNN classifier produce the abnormality prediction results. Second, the Inception V2 CNN classifier framework classifies the bone images with extracted features. With these two comparative‐classification results, the major counting has been taken as the decision for final abnormality prediction. The proposed model gives improved accuracy of 95% for the elbow, 93% for the forearm, 92% for the shoulder, 92% for the wrist, 93% for the finger, 92% for humerus images. [ABSTRACT FROM AUTHOR]

Autism Spectrum Disorders (ASD) assessment relies on clinical rating scales to measure related social and behavioral changes, a subjective process which is prone to misdiagnosis. ASD heterogeneity of social and cognitive functioning has been associated with underlying neuro-anatomical alterations. Automatic medical imaging analyses have made possible quantification of these anatomical changes, yet these complex morphological patterns have been partially characterized by simple absolute scalar values. This paper presents a much more complete exploration of the global–local differences between ASD and control subjects using a multiscale descriptor that captures sub-visual spatial patterns. This analysis consists in three main steps: a pre-processing for segmenting the brain into a particular anatomical parcellation, a region-based characterization for capturing global–local folding/shape patterns, and a statistical analysis for quantifying differences between ASD and control individuals. A large data cohort (n = 1245) consisting in three different age groups, was used to perform this exploration. The analysis was carried out in the entire set of cortical and subcortical brain regions: (i) using two different brain parcellations, and (ii) separately for each age group. This characterization revealed statistically significant differences (p ¡ 0.05) in the ASD group compared to control individuals using two brain parcellations. These results demonstrate the representation is able to identify folding and shape differences for a particular age range in both parcellations, supporting the generalizability of these findings. • Quantification of brain folding/shape differences at different orientation, depths and circumvolution patterns in every cortical and subcortical brain region. • A statistical analysis for establishing brain differences between ASD and control individuals. • A more complete evaluation by assessing the representation with a larger population (n = 1245, three groups of age), and two different brain parcellations. • An anatomical–functional correlation, crucial for developing an unbiased quantification of the disease and a more accurate categorization. [ABSTRACT FROM AUTHOR]

Since texture is prominent low level feature of an image, most of the image processing and computer vision applications rely on this feature for efficient extraction, retrieval, visualization and classification of the images. Hence, the texture analysis method mainly concentrates on efficient feature extraction and representation of the image. The images captured and analyzed in many of the applications are not in same (or) similar scale, orientation and illumination and also texture has regular, stochastic, periodic, homogeneous (or) inhomogeneous and directional in nature. To address these issues, recent texture analysis method focused on efficient and invariant feature extraction and representation with reduced dimension. Hence this paper proposes a invariant texture descriptor, Locality preserving Rotation Invariant Modified Directional Local Binary Pattern (LRIMDLBP) based on LBP. The classical LBP descriptor is widely used in most of the texture analysis applications due to its simplicity and robustness to illumination changes. However, it does not efficiently capture the discriminative texture information because it uses sign information and ignores the magnitude value of the neighborhood and also suffers from high dimensionality. Hence to improve the performance of LBP, many variants are proposed. Though most of these LBP variants are either geometrical or direction invariant, fails to address the spatial locality and contrast invariance. To address these issues, the proposed LRIMDLBP incorporates spatial locality, contrast and direction information for rotation invariant texture descriptor with reduced dimension. The proposed LRIMDLBP consists of 5 phases: (i) Reference point identification, (ii) Magnitude calculation, (iii) Binary Label computation based on threshold, (iv) Pattern identification in dominant direction and (v) LRIMDLBP code computation. The locality and rotation invariance is achieved by identifying and using reference point in a local neighborhood. The reference point is a dominant pixel whose magnitude is large in the neighborhood excluding center pixel. The spatial locality and rotation invariance is achieved by preserving the weights of LBP dynamically based on the reference point. The proposed method also preserves the direction information of the texture by comparing the magnitude of the pixel in the four dominant directions such as horizontal, vertical, diagonal and anti-diagonal directions. Finally the proposed invariant LRIMDLBP descriptor computes histogram based on decimal pattern value. The proposed LRIMDLBP descriptor results in texture feature with reduced dimension when compared to other LBP variants. The performance of the proposed descriptor is evaluated with large and well known four bench mark texture datasets namely (i) CUReT, (ii) Outex, (iii) KTS-TIPS and (iv) UIUC against three classifiers such as (i). K-Nearest Neighbor (K-NN), (ii). Support Vector Machine (SVM) with Radial Basis Function (RBF) and (iii). Gradient Boosting Classifier (GBC). The intensive experimental result shows that the ensemble based GBC yields superior classification accuracy of 99.38%, 99.43%, 98.67% and 98.82% for the datasets CUReT, Outex, KTH-TIPS and UIUC respectively when compared with other two classifiers and also improves the generalization ability. The proposed LRIMDLBP descriptor achieves approximately 15% more classification accuracy when compared with traditional LBP and also produces 1% to 2.5% more classification accuracy compared with other state of the art LBP variants. [ABSTRACT FROM AUTHOR]

Digital images can be manipulated using the latest tools and techniques without leaving any visible traces. Image tampering detection is required to authenticate image validation. It is concluded from previous research that image tampering modifies the texture micropattern in a digital image. Therefore, texture descriptors can be applied to highlight these changes. A texture descriptor–based technique is proposed for detecting both copy-move and splicing forgery. In the proposed method, an RGB image is converted into a YCbCr image and Cb and Cr image components are extracted, as these components are more sensitive to tampering artifacts. Further, a standard deviation (STD) filter and higher-order texture descriptors are applied on Cb and Cr components. The STD filter is used to highlight important details of objects in the image. A support vector machine classifier is used to classify forged and tampered images. Support vector machine (SVM) classifier gives good results on both large- and small-image data sets. The performance is appraised in three online-available, widely used data sets: CASIA v1.0, CASIA v2.0, and Columbia. The proposed method outperforms most of the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Face recognition is one of the most interesting areas of research areas because of its importance in authentication and security. Differentiating between different facial images is not easy because of the similarities in facial features. Human faces can also be covered obscured by eyeglasses, facial expressions and hairstyles can also be changed causing difficulty in finding similar faces. Thus, the need for powerful image features has become a critical issue in the face recognition systems. Many texture features have been used in these systems, including Local Binary Pattern (LBP), Local Ternary Pattern (LTP), Completed Local Binary Pattern (CLBP), Completed Local Binary Count (CLBC) and Completed Local Ternary Pattern (CLTP). In this paper, a new texture descriptor, namely, Completed Local Ternary Count (CLTC), is proposed by adding a threshold value for the CLBC to overcome its sensitivity to noise drawback. The CLTC is also enhanced by adding the Fast-Local Laplacian filter during the pre-processing stage to increase the discriminative property of the proposed descriptor. The proposed Fast-Local Laplacian CLTC (FLL-CLTC) texture descriptor is evaluated for face recognition task using five different face image datasets. The experimental results of the FLL-CLTC showed that the proposed FLL-CLTC outperformed the CLBP and CLTP texture descriptors in term of recognition accuracy. The FLL-CLTC achieved 99.1%, 86.93%, 93.21%, 84.92% and 99.15% with JAFFE, YALE, Georgia Tech, Caltech and ORL face image datasets, respectively.

Due to the rapid spread of the new coronavirus variant during the most recent pandemic, it became difficult to distinguish common cold symptoms from those of other respiratory illnesses and coronavirus infections. X-rays of the thorax and Polymerase Chain Reaction with Reverse Transcription (RT-PCR) are common and efficient methods for preventing the spread of infectious diseases. In recent years, Machine Learning (ML) algorithms have been widely used to aid in the diagnosis of medical images, yielding simpler, more accurate, and quicker results. This study intends to apply texture descriptors to X-rays of COVID-19 patients' lungs and utilize the extracted features in frameworks designed to accurately evaluate COVID-19 patients. Multiple experiments employing individual texture descriptors and their integration were conducted in order to incorporate these new characteristics into the proposed models. In addition, these frameworks will be compared to the conventional ML models used to aid in the diagnosis of COVID-19. When texture descriptors are used in conjunction with other standard features, the predictive power of the algorithms increases, according to the results. In addition, the accuracy increases when different types of texture descriptors are combined, resulting in enhanced metrics for detecting and diagnosing COVID-19. • We present new predictive frameworks to assist with medical image diagonals. • We evaluate texture extraction methods for aiding COVID-19 diagnosis. • We show that combining texture extraction methods enhances ML classifier accuracy. [ABSTRACT FROM AUTHOR]

Image brightness in color representation has caught active research interests, while its influence to texture features is relatively rarely studied. In this paper, we address the issue of illuminance, or brightness, interference to texture descriptors, especially to the Gabor filter based approaches. Firstly, we reveal the fact that the Gabor filter response linearly drifts with the illuminance. Secondly, the Hodge decomposition is introduced, and a linear regression model is presented to interpret the linear drift phenomenon. An interesting connection with the intrinsic image decomposition is established. Finally, a partial differential equation based method is proposed to compensate the drift issue. Consequently, the texture of the compensated image is enhanced. Extensive experiments are conducted to verify the proposed statements. The proposed linear regression model is verified empirically, and the compensation performances are demonstrated. Classification results on various databases indicate that the compensation can effectively improve the capacity of many existing texture description methods. Especially, the results show that the boosting effect on some deep learning based methods is also valid. [ABSTRACT FROM AUTHOR]

Structure-texture image decomposition is a fundamental but challenging topic in computational graphics and image processing. In this paper, we introduce a structure-aware and a texture-aware measures to facilitate the structure-texture decomposition (STD) of images. Edge strengths and spatial scales that have been widely-used in previous STD researches cannot describe the structures and textures of images well. The proposed two measures differentiate image textures from image structures based on their distinctive characteristics. Specifically, the first one aims to measure the anisotropy of local gradients, and the second one is designed to measure the repeatability degree of signal patterns in a neighboring region. Since these two measures describe different properties of image structures and textures, they are complementary to each other. The STD is achieved by optimizing an objective function based on the two new measures. As using traditional optimization methods to solve the optimization problem will require designing different optimizers for different functional spaces, we employ an architecture of deep neural network to optimize the STD cost function in a unified manner. The experimental results demonstrate that, as compared with some state-of-the-art methods, our method can better separate image structure and texture and result in shaper edges in the structural component. Furthermore, to demonstrate the usefulness of the proposed STD method, we have successfully applied it to several applications including detail enhancement, edge detection, and visual quality assessment of super-resolved images. [ABSTRACT FROM AUTHOR]

Texture is a dominant tool for feature extraction. Incorporation of inter-channel chromatic information along with the texture feature will improve the accuracy of feature extraction. This paper provides deep learned Inter-Channel Colored Texture Pattern which gives the inter-channel chromatic texture information of an image. The information is extracted individually from the co-occurrent pixel values of various channels. It affords the unique channel-wise information and its relation with neighboring pixel information of opponent space. Deep learning with convolutional neural network is applied for learning the feature based on color and texture. The experiments for content-based image retrieval are carried out on three different databases which vary in nature: CIFAR-10 dataset (DB1) (Krizhevsky in Learning multiple layers of features from tiny images, University of Toronto, 2009), Corel database (DB2) (Corel 1000 and Corel 10000 image database, http://wang.ist.psu.edu/docs/related.shtml) and Facescrub dataset (DB3) (Ng and Winkler in 2014 IEEE international conference on image processing (ICIP), pp 343–347, 2014). Facescrub dataset is used for face recognition. The experimental analysis by applying this descriptor provides considerable improvement from the previous works for content-based image retrieval and face recognition. [ABSTRACT FROM AUTHOR]

Pattern recognition and computer vision fields experienced the proposal of several architectures and approaches to deal with the demands of real world applications including face recognition. They have almost the same structure, based generally on a series of steps where the main ones are feature extraction and classification. The literature works interessted in face recognition problems, insist on the role of texture description as one of the key elements in face analysis, since it greatly affects recognition accuracy. Therefore, texture feature extraction has gained much attention and became a long-standing research topic thanks to its abilities to efficiently understand the face recognition process, especially in terms of face description. Recently, several literature researches in face application proposed new architectures based on pattern description proved by their discriminative power when extracting the feature information from facial images. These advantages combined with an outstanding performance in many classification applications, allowed the LBP-like descriptors to be one of the most prominent texture description method. Given this period of remarkable evolution, this research work includes a comprehensive analytical study of the face recognition performance of 64 LBP-like and 3 non-LBP texture descriptors recently proposed in the literature. To this end, we adopted a face recognition framework composed of four stages: 1) image pre-processing using gamma correction; 2) feature extraction using texture descriptors; 3) histogram calculation and 4) face recognition and classification based on the simple parameter-free Nearest Neighbors classifier (NN). The conducted comprehensive evaluations and experiments on the challenging and widely used benchmarks ORL, YALE, Extended YALE B and FERET databases presenting different challenges, indicate that a number of evaluated texture descriptors, which are tested for the first time on face recognition task, achieve better or competitive compared to several recent systems reported in face recognition literature. [ABSTRACT FROM AUTHOR]

Content‐based image retrieval (CBIR) is an image retrieval technique that can retrieve images by matching its feature set values. This research focuses on a novel CBIR method namely hybrid CBIR method using statistical, Discrete Wavelet Transform (DWT)‐Entropy and Peak‐oriented Octal Pattern‐derived Majority Voting (POPMV)‐based feature sets (CBIR_SWPOPMV) to efficiently extract the relevant colour images from the colour image dataset. The doctrine of the proposed method is influenced by a novel texture descriptor namely POPMV which is an octal pattern based on the histogram peak information, to bring about a majority voting‐based feature set and three histogram‐based feature sets. Furthermore, to improve the retrieval accuracy, the DWT‐based Entropy feature set and the statistical feature set are also included. Finally, the Euclidean distance‐based matching process brings more favourable relevant images with respect to the query image. The proposed methodology is experimentally compared with the existing recent CBIR versions by using seven standard databases such as Corel‐1k, USPTex, MIT‐VisTex, KTH‐TIPS, KTH‐TIPS2a, KTH‐TIPS2a, Colored Brodatz and a user‐contributed database named DB_VEG. [ABSTRACT FROM AUTHOR]

Lung cancer is one of the leading causes of death in the world. Although early detection of lung tumours (nodules) can remarkably diminish the mortal rate, precise detection of them is not always possible by visual inspection of the computerised tomography images. Since nodules with different sizes have non‐uniform shape and brightness, texture attributes and also the gradient of orientation can be good candidate features, which have been used for this purpose. They determined the co‐occurrence matrix of the extended local binary pattern (ELBP) along with weighted orientation difference (WOD) for each sub‐region of the lung area. Local binary pattern is a texture descriptor that can extract the discriminative features efficiently. The proposed ELBP is rotation invariant and suitable to describe non‐uniform patterns. Moreover, WOD as a structural feature uses the magnitude of each edge as the weight of its orientation difference. After constructing the co‐occurrence matrix, discriminative features were extracted from this matrix and fed into a support vector machine in order to classify each sub‐region as a cancerous (nodule) or normal tissue. The proposed method was compared to some of state‐of‐the‐art nodule detection methods and was assessed over several real datasets in terms of specificity, sensitivity and accuracy. [ABSTRACT FROM AUTHOR]

Abstract The performance of graph cut based interactive object segmentation approach depends highly on the size of the image. For high-resolution images, it requires an unacceptable amount of storage and time and becomes even more complex when the image has textural contents. In this work, we present an efficient approach to graph cut based texture segmentation by extracting texture features and reducing the overall size of the graph. To extract texture features, Non-decimated Complex Wavelet Transform (NDCWT) is employed whose sub-bands present the texture attributes at different scales and orientations. Moreover, to deal with the huge computational burdens caused by large images, we consider partitioning of the image area where the image is divided into equal-sized non-overlapping blocks and each such block is mapped to a node in the graph. This will not only reduce the size of the graph but also expedite the optimization process significantly. To achieve pixel level accuracy without using any boundary editing, the blocks lying on the boundary are identified and the final segmentation is obtained by applying the standard graph cut on the pixels of such blocks. Thus our approach is able to retain full resolution accuracy with minimal user interaction as opposed to the pre-segmentation or super-pixel based graph cut approaches. Experiments have been conducted on various gray scale as well as color texture images from Brodatz, Berkeley and MSRC datasets which reveal that the proposed approach not only reduces the segmentation time and memory consumption but also improves segmentation accuracy significantly. Highlights • A block based graph reduction framework for texture aware image segmentation is proposed. • Texture features are extracted using non-decimated complex wavelet transform. • Pixel level accuracy is preserved at the boundary by specially treating the pixels in boundary blocks. • Superiority of the approach in segmenting both gray and color texture images is demonstrated. • Significant reduction in computational time and storage is achieved. [ABSTRACT FROM AUTHOR]

Pattern based texture descriptors are widely used in Content Based Image Retrieval (CBIR) for efficient retrieval of matching images. Local Derivative Pattern (LDP), a higher order local pattern operator, originally proposed for face recognition, encodes the distinctive spatial relationships contained in a local region of an image as the feature vector. LDP efficiently extracts finer details and provides efficient retrieval however, it was proposed for images of limited resolution. Over the period of time the development in the digital image sensors had paid way for capturing images at a very high resolution. LDP algorithm though very efficient in content-based image retrieval did not scale well when capturing features from such high-resolution images as it becomes computationally very expensive. This paper proposes how to efficiently extract parallelism from the LDP algorithm and strategies for optimally implementing it by exploiting some inherent General-Purpose Graphics Processing Unit (GPGPU) characteristics. By optimally configuring the GPGPU kernels, image retrieval was performed at a much faster rate. The LDP algorithm was ported on to Compute Unified Device Architecture (CUDA) supported GPGPU and a maximum speed up of around 240x was achieved as compared to its sequential counterpart. [ABSTRACT FROM AUTHOR]

This article proposes the "RGB Pixel N-grams" descriptor, which uses a sequence of n pixels to represent RGB color texture images. We conducted classification experiments with three different classifiers and five color texture image databases to evaluate the descriptor's performance, using accuracy as the evaluation metric. These databases include various textures from different surfaces, sometimes under different lighting, scale, or rotation conditions. The proposed descriptor proved to be robust and competitive compared to other state-of-the-art descriptors, as it has better accuracy in classification results in most databases and classifiers. [Display omitted] • A novel RGB texture image descriptor is proposed using the pixel n-grams approach. • Two different implementations emerged from the proposed descriptor. • The descriptor derives feature vectors with high discriminatory power. • The descriptor is compared with others showing statistically significant differences. [ABSTRACT FROM AUTHOR]

The installation of solar plants everywhere in the world increases year by year. Automated diagnostic methods are needed to inspect the solar plants and to identify anomalies within these photovoltaic panels. The inspection is usually carried out by unmanned aerial vehicles (UAVs) using thermal imaging sensors. The first step in the whole process is to detect the solar panels in those images. However, standard image processing techniques fail in case of low-contrast images or images with complex backgrounds. Moreover, the shades of power lines or structures similar to solar panels impede the automated detection process. In this research, two self-developed methods are compared for the detection of panels in this context, one based on classical techniques and another one based on deep learning, both with a common post-processing step. The first method is based on edge detection and classification, in contrast to the second method is based on training a region based convolutional neural networks to identify a panel. The first method corrects for the low contrast of the thermal image using several preprocessing techniques. Subsequently, edge detection, segmentation and segment classification are applied. The latter is done using a support vector machine trained with an optimized texture descriptor vector. The second method is based on deep learning trained with images that have been subjected to three different pre-processing operations. The postprocessing use the detected panels to infer the location of panels that were not detected. This step selects contours from detected panels based on the panel area and the angle of rotation. Then new panels are determined by the extrapolation of these contours. The panels in 100 random images taken from eleven UAV flights over three solar plants are labeled and used to evaluate the detection methods. The metrics for the new method based on classical techniques reaches a precision of 0.997, a recall of 0.970 and a F1 score of 0.983. The metrics for the method of deep learning reaches a precision of 0.996, a recall of 0.981 and a F1 score of 0.989. The two panel detection methods are highly effective in the presence of complex backgrounds.

Currently, intelligent devices with fingerprint identification are widely deployed in our daily life. However, they are vulnerable to attack by fake fingerprints made of special materials. To elevate the security of these intelligent devices, many fingerprint liveness detection (FLD) algorithms have been explored. In this paper, we propose a novel detection structure to discriminate genuine or fake fingerprints. First, to describe the subtle differences between them and take advantage of texture descriptors, three types of different fine-grained texture feature extraction algorithms are used. Next, we develop a feature fusion rule, including five operations, to better integrate the above features. Finally, those fused features are fed into a support vector machine (SVM) classifier for subsequent classification. Data analysis on three standard fingerprint datasets indicates that the performance of our method outperforms other FLD methods proposed in recent literature. Moreover, data analysis results of blind materials are also reported.