Search

Pulmonary emphysema is one of the lung disorders that are caused owing to the uncharacteristic enhancement of alveoli. Some early emphysema detection medical analyses are CT scanning and spirometry to minimize mortality. Thus, to resolve the drawbacks presented in the existing approach, a new pulmonary emphysema detection model will be developed in this paper. Initially, the required images related to pulmonary emphysema were collected from standard resources and fed to pre-processing stage. Further, the pre-processing is done with Gabor filtering, adaptive contrast and histogram equalization. The parameters of adaptive contrast and histogram equalization are tuned by utilizing a developed hybrid approach named Hybrid Mud Ring Tunicate Swarm Algorithm (H-MRTSA). Additionally, the pre-processed images are offered to the phase of segmentation, where it is performed using the Deep U-net model. Further, the input segmented images are given to the pulmonary emphysema disease detection region. In this phase, pulmonary emphysema is detected using an Attention-based Residual Network (A-ResNet), in which the parameters in the network are tuned using MR-TSA. The performance of the developed H-MRTSA-A-ResNet model achieves superior performance like 97% and 98% concerning accuracy and precision. Thus, the developed pulmonary emphysema disease detection approach achieves an improved disease identification rate than the conventional approaches through experimental analysis. [ABSTRACT FROM AUTHOR]

Parkinson's is a dreadful neurodegenerative disorder disease which affects people over the age of 40 around the world. To reduce the risk factors of Parkinson's, early diagnosis is highly required; therefore, the existing studies have developed different methods for an effective detection process. However, the existing methods failed to produce improved classification accuracy because of several limitations, such as higher computational complexity, excess irrelevant features, noisy samples, etc. Therefore, the proposed study introduces a new deep-learning mechanism to mitigate such issues. The most important steps involved in the proposed work are pre-processing, feature extraction, optimal feature selection and classification. Initially, the given raw input images are pre-processed to eliminate unwanted noises through the Gabor filtering process. The significant features are extracted from the pre-processed images using image decomposition methods like Empirical Wavelet Transform (EWT) and Dual-Tree Complex Wavelet Transform (DT-CWT). In order to reduce the higher feature dimensionality issue, optimal features are selected by the Tunicate Swarm Optimization (TSO) algorithm. Finally, the multiple classes of Parkinson's are classified by proposing a new Fired Bilateral Long-short-term Memory Network (FBLstmNet) model. For simulation, Python is employed, and the performance of the proposed model is analyzed by comparing the results with other existing methods. The experimental results exhibit that the proposed method gains superior classification performance in terms of accuracy (99.5%), precision (99.54%), recall (99.52%), specificity (99.57%) and F-measure (99.56%). [ABSTRACT FROM AUTHOR]

Purpose: Screening programs use mammography as a diagnostic tool for the early detection of breast cancer. Mammogram enhancement is used to increase the local contrast of the mammogram so that the lesions are more visible in the advanced image. For accurate diagnosis in the early stage of breast cancer, the appearance of masses and microcalcification on the mammographic image are two important indicators. The objective of this study was to evaluate the feasibility of the automatic separation of images of breast tissue microcalcifications and also to evaluate its accuracy. Methods: The research was carried out by using two techniques of image enhancement and highlighting of breast tissue microcalcifications for the desired areas by regional ROI based on fuzzy system and also Gabor filtering method. After determining the clusters of breast tissue microcalcifications, the clusters are classified using the decision tree classification algorithm. Then, for segmentation, samples suspected of microcalcification are highlighted and masked, and in the last stage, tissue characteristics are extracted. Subsequently, with the help of an artificial neural network (ANN), determining the benign and malignant types of segmented ROI clusters was accomplished. The proposed system is trained with a Digital Database for Screening Mammography (DDSM) developed by the University of South Florida, USA, and the simulations are performed under MATLAB software and the results are compared with previous work. Results: The results of this training performed under this work show an accuracy of 93% and an improvement of sensitivity above 95%. Conclusion: The result indicates that the proposed approach can be applied to ensure breast cancer diagnosis. [ABSTRACT FROM AUTHOR]

Red palm weevil (RPW) is a pest that can cause severe damage to plantations and affects palm trees. Classical approaches to detection depend on visual analysis, which is inaccurate and time-consuming. Hence, deep learning techniques emerge as a potential solution used for automating the process of detection and presenting efficient and precise results. The initial detection of the RPW remains a difficult task for good production as the identification will protect palm trees infected from the RPW. So advanced technologies like artificial intelligence (AI) and computer vision (CV) can be used in preventing the spread of the RPW on palm trees. Various scholars still working on identifying a precise method for the classification, identification, and localization of the RPW pest. This article develops an automated Red Palm Weevil Detection using Gorilla Troops Optimizer with Deep Learning (RPWD-GTODL) method. The goal of the presented RPWD-GTODL approach lies in the accurate detection and localization of the RPW effectually. To accomplish this, the presented RPWD-GTODL technique initially uses the Gabor filtering (GF) technique to pre-process the images. For RPW detection, the RPWD-GTODL technique uses a Mask RCNN object detector with MobileNetv2 as a backbone network. Moreover, the detection performance of the RPWD-GTODL technique can be boosted by the design of the GTO algorithm for the hyperparameter selection of the MobileNetv2 model. The performance validation of the RPWD-GTODL technique is tested using the RPW dataset and the results demonstrate the enhanced performance on RPW detection process with maximum accuracy of 99.27%.

Video capsule endoscope (VCE) is a developing methodology, which permits analysis of the full gastrointestinal (GI) tract with minimum intrusion. Although VCE permits for profound analysis, evaluating and analyzing for long hours of images is tiresome and cost-inefficient. To achieve automatic VCE-dependent GI disease detection, identifying the anatomical region shall permit for a more concentrated examination and abnormality identification in each area of the GI tract. Hence we proposed a hybrid (Long-short term memory-Visual Geometry Group network) LSTM-VGGNET based classification for the identification of the anatomical area inside the gastrointestinal tract caught by VCE images. The video input data is converted to frames such that the converted frame images are taken and are processed. The processing and classification of health condition data are done by the use of Artificial intelligence (AI) techniques. In this paper, we proposed a prediction of medical abnormality from medical video data that includes the following stages as given: Pre-processing stage performs using Gabor filtering, histogram-based enhancement technique is employed for the enhancement of the image. Multi-linear component analysis-based feature selection is employed, and the classification stage performs using Hybrid LSTMVGGNET with the performance of accurate prediction rate. [ABSTRACT FROM AUTHOR]

The significant defects in the artistic paints are rupture, scratches, and twisting, which are caused by variations in temperature, exposure to moisture, and erosion. Industrial radiography can detect the defect locations, which is a non-destructive test, can be carried out. In radiography testing (RT), the produced radiographs may suffer from some degree of blurriness and low contrast due to the inherent scattering of X-ray, geometric factors such as the size of the beam source, the thickness of the part, and the source to film distance (SFD). The diagnosis of the shapes and sizes of the damages is difficult in some cases. Image processing methods can be used as additional tools for enhancing image quality and more accessible interpretation. In the present study, a Gabor filter technique, based on wavelet analysis with an automatic threshold level, was used to reduce the fogginess of radiographs. The reconstructed images of the proposed algorithm have better contrast, and the defects and signs are more precise than the original image. This algorithm can help the restoration experts for repairing the artistic paintings.

The dynamic variation in the water surfaces of the river networks within the Qinghai-Tibet Plateau affects the water resource availability for downstream ecosystems and human activities. Small rivers (with a river width less than 30 m) are an important component of this network, but are difficult to map in the Qinghai-Tibet Plateau. Firstly, the width of most rivers is very narrow, at around 20 m, which appears as only one or two pixels in Sentinel-2 images and thus is susceptible to salt-and-pepper noise. Secondly, local mountain shadows, cloud shadows, and snow pixels have spectral characteristics similar to those of rivers, leading to misclassification. Therefore, we propose an automated small river mapping (ASRM) method based on Sentinel-2 imagery to address these two difficulties. A preprocessing procedure was designed to remove the salt-and-pepper noise and enhance the linear characteristic of rivers with specific widths. A flexible digital elevation model (DEM)-based post-processing was then imposed to remove the misclassifications caused by mountain shadows, cloud shadows, and snow pixels. The ASRM results achieved an overall accuracy of 87.5%, outperforming five preexisting remote sensing-derived river network products. The proposed ASRM method has shown great potential for small river mapping in the entire Qinghai-Tibet Plateau. [ABSTRACT FROM AUTHOR]

Complexity is one of the major attributes of the visual perception of texture. However, very little is known about how humans visually interpret texture complexity. A psychophysical experiment was conducted to visually quantify the seven texture attributes of a series of textile fabrics: complexity, color variation, randomness, strongness, regularity, repetitiveness, and homogeneity. It was found that the observers could discriminate between the textures with low and high complexity using some high-level visual cues such as randomness, color variation, strongness, etc. The results of principal component analysis (PCA) on the visual scores of the above attributes suggest that complexity and homogeneity could be essentially the underlying attributes of the same visual texture dimension, with complexity at the negative extreme and homogeneity at the positive extreme of this dimension. We chose to call this dimension visual texture complexity. Several texture measures including the first-order image statistics, co-occurrence matrix, local binary pattern, and Gabor features were computed for images of the textiles in sRGB, and four luminance-chrominance color spaces (i.e., HSV, YCbCr, Ohta's I1I2I3, and CIELAB). The relationships between the visually quantified texture complexity of the textiles and the corresponding texture measures of the images were investigated. Analyzing the relationships showed that simple standard deviation of the image luminance channel had a strong correlation with the corresponding visual ratings of texture complexity in all five color spaces. Standard deviation of the energy of the image after convolving with an appropriate Gabor filter and entropy of the co-occurrence matrix, both computed for the image luminance channel, also showed high correlations with the visual data. In this comparison, sRGB, YCbCr, and HSV always outperformed the I1I2I3 and CIELAB color spaces. The highest correlations between the visual data and the corresponding image texture features in the luminance-chrominance color spaces were always obtained for the luminance channel of the images, and one of the two chrominance channels always performed better than the other. This result indicates that the arrangement of the image texture elements that impacts the observer's perception of visual texture complexity cannot be represented properly by the chrominance channels. This must be carefully considered when choosing an image channel to quantify the visual texture complexity. Additionally, the good performance of the luminance channel in the five studied color spaces proves that variations in the luminance of the texture, or as one could call the luminance contrast, plays a crucial role in creating visual texture complexity. [ABSTRACT FROM AUTHOR]

On an MRI scan of the brain, the boundary between endocrine tissues is highly convoluted and irregular. Outdated segmentation algorithms face a severe test. Machine learning as a new sort of learning Here, researchers categorize normal and abnormal tissue using the fuzzy min-max neural network approach, which helps classify normal and abnormal tissues such as GM, CSF, WM, OCS, and OSS. This classification helps to explain the fuzzy min-max neural network method. Osseous Spongy Substance, SCALP, and Osseous Compact Substance are all MRI-classified as aberrant tissue in these tissues. Denoising and improving images can be accomplished using the Gabor filtering technique. Using the filtering method, the tumour component will be accurately identified during the segmentation operation. A dynamically changed region growing approach may be applied to a picture by modifying the Modified Region Growing method's two thresholds. This helps to raise Modified Region Growing's upper and lower bounds. Once the Region Growth is accomplished, the edges may be observed using the Modified Region Growing segmented image's Edge Detection approach. After removing the texture, an entropy-based method may be used to abstract the colour information. After the Dynamic Modified Region Growing phase findings have been merged with those from the texture feature generation phase, a distance comparison within regions is performed to combine comparable areas in the region merging phase. After tissues have been identified, a Fuzzy Min-Max Neural Network may be utilised to categorise them.

Bear time records, which are the accumulations of spatial spectrum estimates on the time axis, are often employed for passive sonar information processing. Multi-target jamming is a common difficulty in this approach due to the constraints of Rayleigh limit, and neither the conventional beamforming (CBF) nor minimum variance distortionless response (MVDR) technique can handle it well. This work presents a post-processing tracking framework based on visual pattern recognition algorithms to track weak acoustic targets within jamming environments, which includes target motion analysis, matched filtering, and principal component analysis-based denoising, and we call this 'P-Gabor' algorithm. The simulations and sea-trial experiments show that the proposed method can track a weak target successfully under −23 dB (signal-to-interference ratio) SIR, which is more effective than the references, especially in terms of using real-world data from sea trials. We further demonstrate that the method also has stable tracking performance at even −25 dB SNR (signal-to-noise ratio) circumstances. [ABSTRACT FROM AUTHOR]

Advances in hyperspectral remote sensing have instigated multitude of applications for better understanding of our planet through remote data acquisition and observation of natural phenomena such as weather monitoring and prediction to include tornado, wild fires, global warming, etc. For this, data analysis methods that exploit the rich spectral and spatial information in hyperspectral data are often employed to gain insights about the natural phenomenon. This work presents a new deep learning based hyperspectral data analysis framework, which efficiently utilizes both spatial and spectral information present in the data to achieve superior classification performance. Gabor filtering is used for spatial feature extraction in conjunction with sparse random projections for spectral feature extraction and dimensionality reduction. Finally, supervised classification using a 3-D convolutional neural network was employed to perform a volumetric hyperspectral data analysis. Experimental results reveal that the proposed spatial–spectral hyperspectral data analysis frameworks outperform the conventional 2-D convolution neural network-based spectral–spatial feature extraction techniques.

Complexity is one of the major attributes of the visual perception of texture. However, very little is known about how humans visually interpret texture complexity. A psychophysical experiment was conducted to visually quantify the seven texture attributes of a series of textile fabrics: complexity, color variation, randomness, strongness, regularity, repetitiveness, and homogeneity. It was found that the observers could discriminate between the textures with low and high complexity using some high-level visual cues such as randomness, color variation, strongness, etc. The results of principal component analysis (PCA) on the visual scores of the above attributes suggest that complexity and homogeneity could be essentially the underlying attributes of the same visual texture dimension, with complexity at the negative extreme and homogeneity at the positive extreme of this dimension. We chose to call this dimension visual texture complexity. Several texture measures including the first-order image statistics, co-occurrence matrix, local binary pattern, and Gabor features were computed for images of the textiles in sRGB, and four luminance-chrominance color spaces (i.e., HSV, YCbCr, Ohta’s I1I2I3, and CIELAB). The relationships between the visually quantified texture complexity of the textiles and the corresponding texture measures of the images were investigated. Analyzing the relationships showed that simple standard deviation of the image luminance channel had a strong correlation with the corresponding visual ratings of texture complexity in all five color spaces. Standard deviation of the energy of the image after convolving with an appropriate Gabor filter and entropy of the co-occurrence matrix, both computed for the image luminance channel, also showed high correlations with the visual data. In this comparison, sRGB, YCbCr, and HSV always outperformed the I1I2I3 and CIELAB color spaces. The highest correlations between the visual data and the corresponding image texture features in the luminance-chrominance color spaces were always obtained for the luminance channel of the images, and one of the two chrominance channels always performed better than the other. This result indicates that the arrangement of the image texture elements that impacts the observer’s perception of visual texture complexity cannot be represented properly by the chrominance channels. This must be carefully considered when choosing an image channel to quantify the visual texture complexity. Additionally, the good performance of the luminance channel in the five studied color spaces proves that variations in the luminance of the texture, or as one could call the luminance contrast, plays a crucial role in creating visual texture complexity.

The dynamic variation in the water surfaces of the river networks within the Qinghai-Tibet Plateau affects the water resource availability for downstream ecosystems and human activities. Small rivers (with a river width less than 30 m) are an important component of this network, but are difficult to map in the Qinghai-Tibet Plateau. Firstly, the width of most rivers is very narrow, at around 20 m, which appears as only one or two pixels in Sentinel-2 images and thus is susceptible to salt-and-pepper noise. Secondly, local mountain shadows, cloud shadows, and snow pixels have spectral characteristics similar to those of rivers, leading to misclassification. Therefore, we propose an automated small river mapping (ASRM) method based on Sentinel-2 imagery to address these two difficulties. A preprocessing procedure was designed to remove the salt-and-pepper noise and enhance the linear characteristic of rivers with specific widths. A flexible digital elevation model (DEM)-based post-processing was then imposed to remove the misclassifications caused by mountain shadows, cloud shadows, and snow pixels. The ASRM results achieved an overall accuracy of 87.5%, outperforming five preexisting remote sensing-derived river network products. The proposed ASRM method has shown great potential for small river mapping in the entire Qinghai-Tibet Plateau.

Bear time records, which are the accumulations of spatial spectrum estimates on the time axis, are often employed for passive sonar information processing. Multi-target jamming is a common difficulty in this approach due to the constraints of Rayleigh limit, and neither the conventional beamforming (CBF) nor minimum variance distortionless response (MVDR) technique can handle it well. This work presents a post-processing tracking framework based on visual pattern recognition algorithms to track weak acoustic targets within jamming environments, which includes target motion analysis, matched filtering, and principal component analysis-based denoising, and we call this ‘P-Gabor’ algorithm. The simulations and sea-trial experiments show that the proposed method can track a weak target successfully under −23 dB (signal-to-interference ratio) SIR, which is more effective than the references, especially in terms of using real-world data from sea trials. We further demonstrate that the method also has stable tracking performance at even −25 dB SNR (signal-to-noise ratio) circumstances.

Spectral–spatial Gabor filtering, which is based on 3-D local harmonic analysis, has been a powerful spectral–spatial feature extraction tool for hyperspectral image (HSI) classification. However, existing spectral–spatial Gabor approaches are prone to oversmoothing, neglecting the existences of edges and negatively affecting the classification. In this article, we propose a new HSI Gabor filtering concept, called spectral–spatial-range Gabor filtering, which intends to restrain edge interference from disturbing local spectral–spatial harmonic components. Contributions and novelties of our work can be identified as follows: 1) an HSI filtering framework is created, which can accommodate various Gabor filtering procedures and hence offer the potential to guide the design of new Gabor filters; 2) following such a unified filtering framework and taking into consideration both local spectral–spatial harmonic characteristics and range domain variations, we develop a new concept of spectral–spatial-range Gabor filtering; and 3) utilizing this proposed Gabor prototype and elaborating mathematical derivations, we achieve a novel discriminative spectral–spatial-range Gabor filtering method, which can deal with discriminative local harmonics and edge interference simultaneously along the spectral–spatial-range domain, obtaining highly discriminative Gabor features while yielding linear computational complexity. Our novel method is evaluated on four real HSI data sets and achieves excellent performances. [ABSTRACT FROM AUTHOR]

Mobile devices have become ubiquitous nowadays and so is the need of secure access to these devices. Iris being the most reliable and hard-to-tamper biometric trait, can serve the aforementioned purpose. Iris recognition on mobile phones has become a significant and challenging task for the research community. With advancement in technology, it has now become feasible to use mobile devices' in-built cameras to unlock the device through the user's iris. This paper presents a convenient and efficient approach: optimal bit-transition codes (OBTC), for representing mobile iris images in a more distinctive manner. The approach is derived from the texture analysis property of 2D Gabor filters. Optimization of Gabor parameters is performed for iris images from two challenging mobile iris databases: MICHE I (which comprises of eye images acquired from three different smartphones: iPhone5, Galaxy S4 and Galaxy Tab2) and VISOB (which contains eye images acquired from iPhone5S, Samsung Note 4 and Oppo N1). After filtering, the image responses are converted to binary numbers and stored in concatenated vectors. Later, the concatenated vectors produce binary strings across the direction of concatenation and number of bit-transitions in these binary strings are encoded to form the complete feature vectors. A capacious experimentation is performed on the challenging MICHE I and VISOB iris databases. Comparison of the proposed approach with several state-of-the-art approaches clearly shows its expediency. More importantly, the proposed iris recognition approach performs at par with a commercial iris matcher, named VeriEye, which proves its usefulness. [ABSTRACT FROM AUTHOR]

In this paper, a new hyperspectral image classification method based on 2-dimensional complex Gabor filtering and deep convolutional neural networks is proposed. Specifically, as a deep learning model, convolutional neural network is aimed to extract distinctive high-level features. Deep-learned and Gabor feature extraction methodologies are simultaneously performed on the input hyperspectral samples. Gabor features are calculated by implementing complex Gabor filtering only on the first three principal components of the hyperspectral image. The proposed hybrid model uses Gabor transform to obtain local image features, such as edges, corners and texture. The Gabor features of the images are calculated at multiple orientations and frequencies. Then, deep features and Gabor features are fused to obtain a more robust and discriminative feature vector. Hybrid feature vector is used as input to a softmax classifier for hyperspectral image classification. The parameters of the proposed deep learning architecture are optimized using a small training set. Thus, the over-fitting problem of the proposed convolutional neural network has been reduced to some extent. Experiments performed on two popular hyperspectral datasets show that the proposed method can achieve better classification performance than some conventional methods. Classification results demonstrates that the proposed hybrid model is an efficient method for feature extraction and classification of hyperspectral images. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Signal Processing is the property of Journal of Signal Processing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Texture classification plays an important role in computer vision, and Gabor filtering (GF) is a promising direction of texture classification for its desirable characteristics. However, traditional GF methods are too coarse to achieve satisfactory classification performance. To address this problem, this paper presents an effective texture classification method by combing multi-resolution global and local Gabor features in pyramid space. First, a pyramid space for each image is constructed via upsampling and downsampling to represent the images with different resolutions. Second, GF is applied to each image at different scales and orientations, and then the magnitude and phase components of filtered images are calculated. Third, the global and local Gabor features are extracted, where the global Gabor feature is represented by the mean and variance of the magnitude component, and the local Gabor feature is represented by the joint coding of both magnitude and phase components in a histogram form. Finally, the fusion of global and local Gabor features and the texture classification are implemented in the framework of nearest subspace classifier. Experimental results on CUReT and KTH-TIPS databases demonstrate that the proposed method significantly improves the performance of GF-based texture classification methods. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The defect detection procedure of a radiographic image is a very important task. This is because of its importance regarding the safety of different industrial equipment. The defect detection procedures must reveal the defect region with the edges preserved. The radiography images are degraded by different noises caused by photon x-ray scattering, data acquisition and system errors. Due to the noise, radiography experts may encounter certain difficulties when extracting the defect region in the noisy images. This article presents a novel implementation of the Gabor filtering algorithm to improve contrast and denoise radiography images and detect the defects. Gabor filtering with automatic detection of noise level is a powerful contrast enhancement algorithm, but it tends to remove specific details from the processed images passing them off as noise. The performance of the proposed approach, the region defect, is revealed in radiographic images of different welded specimens. Results show major improvement not only in the noise attenuation, but also in the preservation of small details and the defect region. [ABSTRACT FROM AUTHOR]

Forests provide various important things to human life. Fire is one of the main disasters in the world. Nowadays, the forest fire incidences endanger the ecosystem and destroy the native flora and fauna. This affects individual life, community and wildlife. Thus, it is essential to monitor and protect the forests and their assets. Nowadays, image processing outputs a lot of required information and measures for the implementation of advanced forest fire-fighting strategies. This work addresses a new color image segmentation method based on principal component analysis (PCA) and Gabor filter responses. Our method introduces a new superpixels extraction strategy that takes full account of two objectives: regional consistency and robustness to added noises. The novel approach is tested on various color images. Extensive experiments show that our method obviously outperforms existing segmentation variants on real and synthetic images of fire forest scenes, and also achieves outstanding performance on other popular benchmarked images (e.g., BSDS, MRSC). The merits of our proposed approach are that it is not sensitive to added noises and that the segmentation performance is higher with images of nonhomogeneous regions.

Image hashing is a useful multimedia technology for many applications, such as image authentication, image retrieval, image copy detection and image forensics. In this paper, we propose a robust image hashing based on random Gabor filtering and discrete wavelet transform (DWT). Specifically, robust and secure image features are first extracted from the normalized image by Gabor filtering and a chaotic map called Skew tent map, and then are compressed via a single-level 2-D DWT. Image hash is finally obtained by concatenating DWT coefficients in the LL sub-band. Many experiments with open image datasets are carried out and the results illustrate that our hashing is robust, discriminative and secure. Receiver operating characteristic (ROC) curve comparisons show that our hashing is better than some popular image hashing algorithms in classification performance between robustness and discrimination. [ABSTRACT FROM AUTHOR]

Silhouette-based gait representations are widely used in the current gait recognition community due to their effectiveness and efficiency, but they are subject to changes in covariate conditions such as clothing and carrying status. Therefore, we propose a gait energy response function (GERF) that transforms a gait energy (i.e., an intensity value) of a silhouette-based gait feature into a value more suitable for handling these covariate conditions. Additionally, since the discrimination capability of gait energies, as well as the degree to which they are affected by the covariate conditions, differs among body parts, we extend the GERF framework to spatially dependent GERF (SD-GERF) which accounts for spatial dependence. Moreover, the proposed GERFs are represented as a vector in the transformation lookup table and are optimized through an efficient generalized eigenvalue problem in a closed form. Finally, two post-processing techniques, Gabor filtering and spatial metric learning, are employed for the transformed gait features to boost the accuracy. Experimental results with three publicly available datasets including clothing and carrying status variations show the state-of-the-art performance of the proposed method compared with other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Active learning (AL) has obtained a great success in supervised remotely sensed hyperspectral image classification, since it is able to select highly informative training samples. As an intrinsically biased sampling approach, AL generally favors the selection of samples following discriminative distributions, which are located in low-density areas. However, hyperspectral data are often highly class-mixed, i.e., most samples fluctuate in the overlapping regions of distributions of different classes. In this case, the potential of AL to select effective training samples is more limited. As AL strongly depends on the features, a possibility to increase its capabilities is to transfer the data into a highly discriminative feature space, in which the mixture of distributions that different classes of data follow tends to reduce. Based on this observation, in this paper, we introduce the concept of feature-driven AL, namely, the sample selection is going to be conducted in a given optimized feature space whose superiority is measured by an overall error probability. For illustrative purposes, we used Gabor filtering and morphological profiles for instantiation. Our experimental results, obtained on three real hyperspectral data sets, indicate that the proposed approach can significantly improve the potential of AL for hyperspectral image classification. [ABSTRACT FROM AUTHOR]

Glaucoma is the most common cause of blindness in India. Diagnosis of glaucoma is based on measurement of intraocular pressure by cup area to disc area ratio from the color fundus images. When this intraocular pressure (IOP) is increased in internal eye, vision starts to decline. So, detection of glaucoma is essential for minimizing the vision loss. An approach for detection of glaucoma using fundus images is developed. The Region of interest (ROI) based segmentation is used for the detection of disc. The optic cup and disc localization are used for detecting the region of interest, and Gabor filter is used for edge detection. A Semi automated method using CDR ratio in glaucoma detection of a fundus image has been proposed. The Cup to Disc Ration (CDR) is defined as the ratio of the area between Optic Cup and Optic Disk. Optic cup size increases while the Optic Disc size remains same for a patient in Glaucoma detection and the CDR will be high for a glaucoma patient when comparing with normal fundus image. In this paper the Cup to disc ratio calculation is discussed for detection and classification of glaucoma. [ABSTRACT FROM AUTHOR]

According to spectral homogeneity and ribbon-like shape of road, this letter presents a simple yet effective method of delineating road networks from high-resolution remote sensing images. The proposed method consists of three main steps. First, the mean shift algorithm is utilized to detect the modes of density of image points in spectral-spatial space which contain potential road center points and then detected mode points are classified into different classes by mean shift-based clustering on the basis of spectral information. Next, the combination of Gabor filtering and tensor encoding is used to identify the road class and to extract road center points. Lastly, road network is generated from detected road center points by means of tensor voting and connected component analysis. The experimental results demonstrate good performances of the proposed method in road network extraction from high-resolution remote sensing images. [ABSTRACT FROM AUTHOR]

Recently, the capability of deep learning-based approaches, especially deep convolutional neural networks (CNNs), has been investigated for hyperspectral remote sensing feature extraction (FE) and classification. Due to the large number of learnable parameters in convolutional filters, lots of training samples are needed in deep CNNs to avoid the overfitting problem. On the other hand, Gabor filtering can effectively extract spatial information including edges and textures, which may reduce the FE burden of the CNNs. In this letter, in order to make the most of deep CNN and Gabor filtering, a new strategy, which combines Gabor filters with convolutional filters, is proposed for hyperspectral image classification to mitigate the problem of overfitting. The obtained results reveal that the proposed model provides competitive results in terms of classification accuracy, especially when only a limited number of training samples are available. [ABSTRACT FROM PUBLISHER]

This study presents a new method for enhancing fingerprint image. The process of the enhancement is divided into two phases: fingerprint is first enhanced using Gabor filtering and then the enhanced fingerprint can be further enhanced by using sparse representation with the priori information of ridge pattern based on classification dictionaries learning. In the second stage, first, the orientations of fingerprint patches are estimated by the weighted linear projection analysis and the quality of patches are evaluated by the coherence of point orientations. Second, the training patches are classified into eight groups based on their own orientations, and the training samples of each class are selected from candidate patches by their own quality. The corresponding classification dictionaries are learned in frequency domain. Finally, the fingerprint image is enhanced based on spectra diffusion by using classification dictionaries learning. The experiments are carried out using various fingerprint enhancement methods. The experiments show that the proposed method achieves better results in comparison with other methods, and can significantly improve the performance of automatic fingerprint identification system. [ABSTRACT FROM AUTHOR]

Ocular biometrics refers to the use of features of the eye for person recognition. For instance, the unique and stable texture of the iris has been recognised as a powerful ocular biometric characteristic. In this study, the authors propose to improve biometric authentication with a multimodal ocular biometric system based on the iris pattern and the three‐dimensional shape of the cornea. They show how the cornea can be used as a biometric trait for person recognition and then, they propose an intra‐ocular fusion with iris features to improve the overall performance of the system. Feature extraction was done by modelling the shape of the cornea with a Zernike polynomial expansion. Then the best linear combinations of Zernike coefficients were found with linear discriminant analysis and used as biometric identifier. The iris texture was analysed with a typical methodology using Gabor filtering and phase encoding. The fusion was performed at the matching score level using min, max, sum and weighted‐sum rule. The experimental results on a new database constructed for this bi‐modal study showed impressive performance of the proposed ocular biometric system with equal error rate decreasing to 0% with the weighted‐sum rule. [ABSTRACT FROM AUTHOR]

Purpose Initial auto-adjustment of the window level WL and width WW applied to mammographic images. The proposed intensity windowing ( IW) method is based on the maximization of the mutual information ( MI) between a perceptual decomposition of the original 12-bit sources and their screen displayed 8-bit version. Besides zoom, color inversion and panning operations, IW is the most commonly performed task in daily screening and has a direct impact on diagnosis and the time involved in the process. Methods The authors present a human visual system and perception-based algorithm named GRAIL (Gabor-relying adjustment of image levels). GRAIL initially measures a mammogram's quality based on the MI between the original instance and its Gabor-filtered derivations. From this point on, the algorithm performs an automatic intensity windowing process that outputs the WL/ WW that best displays each mammogram for screening. GRAIL starts with the default, high contrast, wide dynamic range 12-bit data, and then maximizes the graphical information presented in ordinary 8-bit displays. Tests have been carried out with several mammogram databases. They comprise correlations and an ANOVA analysis with the manual IW levels established by a group of radiologists. A complete MATLAB implementation of GRAIL is available at . Results Auto-leveled images show superior quality both perceptually and objectively compared to their full intensity range and compared to the application of other common methods like global contrast stretching ( GCS). The correlations between the human determined intensity values and the ones estimated by our method surpass that of GCS. The ANOVA analysis with the upper intensity thresholds also reveals a similar outcome. GRAIL has also proven to specially perform better with images that contain micro-calcifications and/or foreign X-ray-opaque elements and with healthy BI- RADS A-type mammograms. It can also speed up the initial screening time by a mean of 4.5 s per image. Conclusions A novel methodology is introduced that enables a quality-driven balancing of the WL/ WW of mammographic images. This correction seeks the representation that maximizes the amount of graphical information contained in each image. The presented technique can contribute to the diagnosis and the overall efficiency of the breast screening session by suggesting, at the beginning, an optimal and customized windowing setting for each mammogram. [ABSTRACT FROM AUTHOR]

Most existing tracking approaches are based on either the tracking by detection framework or the tracking by matching framework. The former needs to learn a discriminative classifier using positive and negative samples, which will cause tracking drift due to unreliable samples. The latter usually performs tracking by matching local interest points between a target candidate and the tracked target, which is not robust to target appearance changes over time. In this paper, we propose a novel tracking by matching framework for robust tracking based on basis matching rather than point matching. In particular, we learn the target model from target images using a set of Gabor basis functions, which have large responses on the corresponding spatial positions after a max pooling. During tracking, a target candidate is evaluated by computing the responses of the Gabor basis functions on their corresponding spatial positions. The experimental results on a set of challenging sequences validate that the performance of the proposed tracking method outperforms those of several state-of-the-art methods. [ABSTRACT FROM PUBLISHER]

Spectral–spatial classification of remotely sensed hyperspectral images has attracted a lot of attention in recent years. Although Gabor filtering has been used for feature extraction from hyperspectral images, its capacity to extract relevant information from both the spectral and the spatial domains of the image has not been fully explored yet. In this paper, we present a new discriminative low-rank Gabor filtering (DLRGF) method for spectral–spatial hyperspectral image classification. A main innovation of the proposed approach is that our implementation is accomplished by decomposing the standard 3-D spectral–spatial Gabor filter into eight subfilters, which correspond to different combinations of low-pass and bandpass single-rank filters. Then, we show that only one of the subfilters (i.e., the one that performs low-pass spatial filtering and bandpass spectral filtering) is actually appropriate to extract suitable features based on the characteristics of hyperspectral images. This allows us to perform spectral–spatial classification in a highly discriminative and computationally efficient way, by significantly decreasing the computational complexity (from cubic to linear order) compared with the 3-D spectral–spatial Gabor filter. In order to theoretically prove the discriminative ability of the selected subfilter, we derive an overall classification risk bound to evaluate the discriminating abilities of the features provided by the different subfilters. Our experimental results, conducted using different hyperspectral images, indicate that the proposed DLRGF method exhibits significant improvements in terms of classification accuracy and computational performance when compared with the 3-D spectral–spatial Gabor filter and other state-of-the-art spectral–spatial classification methods. [ABSTRACT FROM PUBLISHER]