Search

The performance of cross-correlation functions can decrease computational complexity under optimal fingerprint feature selection. In this paper, a technique is proposed to perform alignment of fingerprints followed by their matching in fewer computations. Minutiae points are extracted and alignment is performed on the basis of their spatial locations and orientation fields. Unlike traditional cross-correlation based matching algorithms, ridges are not included in the matching process to avoid redundant computations. However, optimal cross-correlation is chosen by correlating feature vectors accompanying x-y locations of minutiae points and their aligned orientation fields. As a result, matching time is significantly reduced with much improved accuracy.

Devising automated procedures for accurate vessel segmentation (retinal) is crucial for timely prognosis of vision-threatening eye diseases. In this paper, a novel supervised deep learning-based approach is proposed which extends a variant of the fully convolutional neural network. The existing fully convolutional neural network-based counterparts have associated critical drawbacks of involving a large number of tunable hyper-parameters and an increased end-to-end training time furnished by their decoder structure. The proposed approach addresses these intricate challenges by using a skip-connections strategy by sharing indices obtained through max-pooling to the decoder from the encoder stage (respective stages) for enhancing the resolution of the feature map. This significantly reduces the number of required tunable hyper-parameters and the computational overhead of the training as well as testing stages. Furthermore, the proposed approach particularly helps in eradicating the requirement for employing both post-processing and pre-processing steps. In the proposed approach, the retinal vessel segmentation problem is formulated as a semantic pixel-wise segmentation task which helps in spanning the gap between semantic segmentation and medical image segmentation. A prime contribution of the proposed approach is the introduction of external skip-connection for passing the preserved low-level semantic edge information in order to reliably detect tiny vessels in the retinal fundus images. The performance of the proposed scheme is analyzed based on the three publicly available notable fundus image datasets, while the widely recognized evaluation metrics of specificity, sensitivity, accuracy, and the Receiver Operating Characteristics curves are used. Based on the assessment of the images in {DRIVE, CHASE_DB1, and STARE}; datasets, the proposed approach achieves a sensitivity, specificity, accuracy, and ROC performance of {0.8252, 0.8440, and 0.8397};, {0.9787, 0.9810, and 0.9792};, {0.9649, 0.9722, and 0.9659};, and {0.9780, 0.9830, and 0.9810};, respectively. The reduced computational complexity and memory overhead along with improved segmentation performance advocates employing the proposed approach in the automated diagnostic systems for eye diseases.

Skin segmentation plays an important role in human activity recognition, video surveillance, hand gesture identification, face detection, human tracking and robotic surgery. The accurate segmentation of the skin is necessary to recognize the human activity. Segmentation of skin is easy to realize in ideal situations because of similar backgrounds. But it becomes complicated because of presence of skin-like pixels, background illuminations, and certain changes in environment. These problems are addressed by incorporating preprocessing stages in current studies, but this raises the total cost of the system. However, there are some limitations associated with these methods in terms of accuracy and processing speed. In this work, we propose a skin semantic segmentation network (SSS-Net) that is able to capture the multi-scale contextual information and refines the segmentation results especially along object boundaries. Moreover our network helps to reduce the cost of the preprocessing as well. We have performed experiments on the five open datasets of human activity recognition for the segmentation of skin. Experimental results show SSS-Net outperforms the state-of-the-art methods in skin segmentation in terms of accuracies.

Leather defect analysis is important for leather quality grading which directly effects the leather exports. Automated leather sample classification is vital due to slow and subjective nature of the manual process. The major challenges that exist in visual inspection of leather samples for categorization are: the morphology of defects significantly differs and their close examples are not available for transfer learning, unavailability of publicly available data and a benchmark. In this paper, we discuss three important aspects in the identification of industrial leather defects, i.e. the creation of an annotated wet-blue leather image dataset, the transfer of information from different domains to the leather image domain and the design of ensemble networks tailored to the task. We are therefore introducing a new database of wet-blue leather images (Wet-blue Leather Image Dataset (WBLID)) for the classification of defects along with expert annotation data. We proposed a new network EfficientNet-B3+ ResNext-101. The proposed EfficientNet-B3+ ResNext-101 ensemble architecture significantly outperforms all other state-of-the-art methods in terms of AUC and F1-score.

Glaucoma is an eye disease that can cause loss of vision by damaging the optic nerve. It is the world's second leading cause of blindness after cataracts. Early diagnosis of glaucoma is a key to prevent permanent blindness as it has no noticeable symptoms in its early stages. Color fundus photography is used for examining the optic disc (OD) which is an important step in the diagnoses of glaucoma. This is done by estimating the cup-to-disc ratio (CDR). In this paper, we proposed a Cup Disc Encoder Decoder Network (CDED-Net) for the joint segmentation of optic disc (OD) and optic cup (OC). We have eradicated the pre-processing and post-processing steps to reduce the computational cost of the overall system. Segmentation of (OD) and OC is modeled as a semantic pixel-wise labeling problem. The model was trained on the DRISHTI-GS, RIM-ONE and REFUGE datasets. Experiments show that our CDED-Net system achieves state-of-the-art OD and OC segmentation results on these datasets.

Glaucoma along with diabetic retinopathy is a major cause of vision blindness and is projected to affect over 80 million people by 2020. Recently, expert systems have matched human performance in disease diagnosis and proven to be highly useful in assisting medical experts in the diagnosis and detection of diseases. Hence, automated optic disc detection through intelligent systems is vital for early diagnosis and detection of Glaucoma. This paper presents a multi-parametric optic disk detection and localization method for retinal fundus images using region-based statistical and textural features. Highly discriminative features are selected based on the mutual information criterion and a comparative analysis of four benchmark classifiers: Support Vector Machine, Random Forest (RF), AdaBoost and RusBoost is presented. The results of the proposed RF classifier based pipeline demonstrate its highly competitive performance (accuracies of 0.993, 0.988 and 0.993 on the DRIONS, MESSIDOR and ONHSD databases) with the state-of-the-art, thus making it a suitable candidate for patient management systems for early diagnosis of the Glaucoma.

Computer-aided optic disk (OD) detection and segmentation is at the heart of modern fundus image screening systems for early detection and diagnosis of glaucoma and diabetic retinopathy. Algorithms that generalize well on fundus images with diseases, as well as screening images, are of utmost importance. This paper presents a method based on OD homogenization and subsequent contour estimation to address the challenges of OD detection in cases where either the OD boundary is discontinuous or very smooth, due to the presence of disease. This is achieved by local Laplacian filtering-based inpainting of the major vascular structure to complete the OD boundary and gradient-independent active contour estimation for unconstrained OD boundary detection. Experimental evaluation of the proposed method on three benchmark datasets and quantitative comparison with the best performing state-of-the-art methods in terms of four quantitative measures demonstrate its competitive performance and reliability for OD screening.

This paper presents a fully automated brain tissue classification method for normal and abnormal tissues and its associated region from Fluid Attenuated Inversion Recovery modality of Magnetic Resonance (MR) images. The proposed regional classification method is able to simultaneously detect and segment tumours to pixel-level accuracy. The region-based features considered in this study are statistical, texton histograms, and fractal features. This is the first study to address the class imbalance problem at the regional level using Random Majority Down-sampling-Synthetic Minority Over-sampling Technique (RMD-SMOTE). A comparison of benchmark supervised techniques including Support Vector Machine, AdaBoost and Random Forest (RF) classifiers is presented, where the RF-based regional classifier is selected in the proposed approach due to its better generalization performance. The robustness of the proposed method is evaluated on the standard publicly available BRATS 2012 dataset using five standard benchmark measures. We demonstrate that the proposed method consistently outperforms three benchmark tumour classification methods in terms of Dice score and obtains significantly better results as compared to its SVM and AdaBoost counterparts in terms of precision and specificity at the 5% confidence interval. The promising results of the proposed method support its application for early detection and diagnosis of brain tumours in clinical settings.

This paper presents a real-time iris segmentation technique that is well suited to a fast implementation on an FPGA. One major hurdle associated with iris segmentation techniques is the use of iterative processes that lead to expensive hardware implementations. To circumvent this, the proposed algorithm uses the sign image obtained from subtracting the background, along with morphological operators to localise the pupil. The outer boundary is located by first normalising a selected image region that contains the iris, and then using a first-order gradient operator. The proposed non-iterative algorithm is implemented on an FPGA. Four near infrared (NIR) iris public databases, namely: CASIA-IrisV3-Lamp, MMU v1.0, ND-IRIS-0405 and NIST ICE 2005, are used to test the proposed algorithm. The proposed method for iris segmentation and normalization gives much better accuracy than the existing state-of-the-art methods implemented on hardware. The proposed realisation requires about 45% fewer logic registers and 52% fewer logic elements than the existing state-of-the-art implementations.

As part of industrial quality control in the leather industry, it is important to identify the abnormal features in wet-blue leather samples. Manual inspection of leather samples is the current norm in industrial settings. To comply with the current industrial standards that advocate large-scale automation, visual inspection based leather processing is imperative. Visual inspection of irregular surfaces is a challenging problem as the characteristics of the abnormalities can take a variety of shape and color variations. The aim of this work is to automatically categorize leather images into normal or abnormal by visual analysis of the surfaces. To achieve this aim, a deep learning based approach is devised that learns to recognize regular and irregular leather surfaces and categorize leather images on its basis. To this end, we propose an ensemble of multiple convolutional neural networks for classifying leather images. The proposed ensemble network exhibited competitive performance obtaining 92.68% test accuracy on our own curated leather images dataset.

Automated detection of vision threatening eye disease based on high resolution retinal fundus images requires accurate segmentation of the blood vessels. In this regard, detection and segmentation of finer vessels, which are obscured by a considerable degree of noise and poor illumination, is particularly challenging. These noises include (systematic) additive noise and multiplicative (speckle) noise, which arise due to various practical limitations of the fundus imaging systems. To address this inherent issue, we present an efficient unsupervised vessel segmentation strategy as a step towards accurate classification of eye diseases from the noisy fundus images. To that end, an ensemble block matching 3D (BM3D) speckle filter is proposed for removal of unwanted noise leading to improved detection. The BM3D-speckle filter, despite its ability to recover finer details (i.e., vessels in fundus images), yields a pattern of checkerboard artifacts in the aftermath of multiplicative (speckle) noise removal. These artifacts are generally ignored in the case of satellite images, however, in the case of fundus images, these artifacts have a degenerating effect on the segmentation or detection of fine vessels. To counter that, an ensemble of BM3D-speckle filter is proposed to suppress these artifacts while further sharpening the recovered vessels. This is subsequently used to devise an improved unsupervised segmentation strategy that can detect fine vessels even in the presence of dominant noise and yields an overall much improved accuracy. Testing was carried out on three publicly available databases namely Structured Analysis of the Retina (STARE), Digital Retinal Images for Vessel Extraction (DRIVE) and CHASE_DB1. We have achieved a sensitivity of 82.88, 81.41 and 82.03 on DRIVE, SATARE, and CHASE_DB1, respectively. The accuracy is also boosted to 95.41, 95.70 and 95.61 on DRIVE, SATARE, and CHASE_DB1, respectively. The performance of the proposed methods on images with pathologies was observed to be more convincing than the performance of similar state-of-the-art methods.

In a fundus image, Vessel local characteristics like direction, illumination and noise vary considerably, making vessel segmentation a challenging task. Methods based upon deep convolutional networks have consistently yield state of the art performance. Despite effective, of the drawbacks of these methods is their computational complexity, whereby testing and training of these networks require substantial computational resources and can be time consuming. Here we present a multi-scale kernel based on fully convolutional layers that is quite lightweight and can effectively segment large, medium, and thin vessels over a wide variations of contrast, position and size of the optic disk. Moreover, the architecture presented here makes use of these multi-scale kernels, reduced application of pooling operations and skip connections to achieve faster training. We illustrate the utility of our method for retinal vessel segmentation on the DRIVE, CHASE_DB and STARE data sets. We also compare the results delivered by our method with a number of alternatives elsewhere in the literature. In our experiments, our method always provides a margin of improvement on specificity, accuracy, AUC and sensitivity with respect to the alternative.

Traditional one class support tensor machine (OCSTM) is a popular classifier that is widely adopted for one class classification, however, outliers in the data negatively affects its performance. To improve the robustness of OCSTM against outliers, in this paper, we present OCSTM with bounded loss function rather than finding optimized support vectors with unbounded loss function. To solve the corresponding optimization problem, we have presented half quadratic optimization to drive the problem to traditional OCSTM, followed by solving a typical OCSTM optimization problem iteratively. We further demonstrate our algorithms through experiments on eight real-world benchmark datasets. Experimental results show that the proposed approach separates well most of the samples of interested class from origin even in the presence of outliers.

Automatic classification of skin disease is a challenging task due to high similarity among them as well as complex nature of skin images i.e. hair, skin and nails and illumination conditions. It is one of the most common malignancy that becomes more difficult to treat and potential disfigurement or even death, if not diagnosed early. In this paper, we present a fully automatic skin lesion classification by leveraging three stage deep residual neural networks that is trained end-to-end and does not rely on prior knowledge of the data. Extensive experiment on ISIC-2018 challenges shows that our methods showed considerable improvement (96.07%) in the classification of skin melanoma by not only super-passing the ISIC-2018 challenges as well state of the art methods.

Accurate automatic segmentation of the retinal vessels is crucial for early detection and diagnosis of vision-threatening retinal diseases. This paper presents a lightweight convolutional neural network termed as Shallow Vessel Segmentation Network (SVSN) for vessel segmentation. To achieve semantic segmentation encoder-decoder structures embedded with spatial pyramid pooling modules are used. After checking the input features with pooling through multiple fields of view and rates, it becomes easy for the erstwhile networks to encode multi-scale contextual information. While boundaries for sharper objects are captured by the prevalent networks. Moreover, the need for pre- and post-processing steps are eradicated. Consequently, the detection accuracy is significantly improved with scores of 0.9625 and 0.9645 on DRIVE and STARE datasets respectively.

Accurate automatic segmentation of the retinal vessels is crucial for early detection and diagnosis of vision-threatening retinal diseases. A new supervised method using a variant of the fully convolutional neural network is pro-posed with the advantages of reduced hyper-parameters, reduced computational/memory requirements, and robust performance in capturing tiny vessel information. The fully convolutional architectures previously employed for vessel segmentation have multiple tunable hyperparameters and difficulty in end-to-end training due to their decoder structure. We resolve this problem by sharing information from the encoder for upsampling at the decoder stage, resulting in a significantly smaller number of tunable parameters and low computational overhead at the train and test stages. Moreover, the need for pre- and post-processing steps are eradicated. Consequently, the detection accuracy is significantly improved with scores of 0.9620, 0.9623, and 0.9620 on DRIVE, STARE, and CHASE_DB1 datasets respectively.

Reliably and effectively detecting and classifying leather surface defects is of great importance to tanneries and industries that use leather as a major raw material such as leather footwear and handbag manufacturers. This paper presents a detailed and methodical review of the leather surface defects, their effects on leather quality grading and automated visual inspection methods for leather defect inspection. A detailed review of inspection methods based on leather defect detection using image analysis methods is presented, which are usually classified as heuristic or basic machine learning based methods. Due to the recent success of deep learning methods in various related fields, various architectures of deep learning are discussed that are tailored to image classification, detection, and segmentation. In general, visual inspection applications, where recent CNN architectures are classified, compared, and a detailed review is subsequently presented on the role of deep learning methods in leather defect detection. Finally, research guidelines are presented to fellow researchers regarding data augmentation, leather quality quantification, and simultaneous defect inspection methods, which need to be investigated in the future to make progress in this crucial area of research.

There is a growing trend towards employing automatic fingerprint identification systems (AFIS) as a viable biometric tool for identity verification. However, this technology is often defeated when attempting to process low-quality fingerprints. A popular technique is to utilize Coherence-Enhancing Diffusion (CED) first to raise fingerprint quality to a level where any recognition takes place. One of the principal functions of CED is to extract orientations by referencing neighbouring gradients. Gradient computations are noise-prone and tend to deviate away from the actual underlying orientation field. This paper proposes a cluster-based computational approach for reliable orientation field estimation based on a directional filter bank framework. The orientations present in fingerprints cluster themselves in a contagious group in the directional bands, that can be exploited towards their reliable estimation. The estimated orientation field then becomes an input data for the CED engine as a pre-computed add-on module to provide much- needed enhancement in noisy fingerprints that subsequently attains in better recognition performance for a given Automated Fingerprint Identification System (AFIS). The experimental procedures reported in this study suggest more accurate orientation results in favour of proposed method than existing techniques even when processing very noisy real-life test data. The improvement in noisy fingerprints is also reported.

This paper presents a novel approach for image enhancement. In the proposed method, retinal image is divided into three sub-parts, optic disc region, vessels region and non-vessels region (black region outside vessels). Color image enhancement is then performed on these three regions in HSV domain. Then the color image is converted to gray using a multi-scale line detector based technique. For vessel detection, a modified Frangi vessels detector is used. This filter produces a nearly uniform response in every vascular structure and precisely boosts the border between the background and the vascular structures. This filter accomplished the best result in segmentation quantitative metrics performance, vessel enhancement signal-to-noise ratio and uniformity of the response in vascular structures as compared to other filters. Excremental results show that the performance of modified Frangi method is much better than the old Frangi and also comparable with most of the state-of-the-art methods.

In computer vision, blob detection is used to obtain regions of interest that could signal the presence of objects or parts with application to object recognition and object tracking. One of the more common blob detectors is based on the Laplacian of Gaussian (LoG). However, most blob detectors developed in the past assume circular blobs, and these detectors do not perform as well with elliptical blobs, a more prevalent scenario in real images. A generalised LoG (GLoG) detector was proposed recently to deal specifically with elliptical blobs. To formulate the GLoG in a multi-scale framework, its response must be made scale invariant. Toward that end, necessary and sufficient conditions are presented here, with the normalisation factors derived for a scale-invariant GLoG detector. The factors are validated with a synthetic example and are further tested with two real-world images.

Many chronic eye diseases can be conveniently investigated by observing structural changes in retinal blood vessel diameters. However, detecting changes in an accurate manner in face of interfering pathologies is a challenging task. The task is generally performed through an automatic computerized process. The literature shows that powerful methods have already been proposed to identify vessels in retinal images. Though a significant progress has been achieved toward methods to separate blood vessels from the uneven background, the methods still lack the necessary sensitivity to segment fine vessels. Recently, a multi-scale line-detector method proved its worth in segmenting thin vessels. This paper presents modifications to boost the sensitivity of this multi-scale line detector. First, a varying window size with line-detector mask is suggested to detect small vessels. Second, external orientations are fed to steer the multi-scale line detectors into alignment with flow directions. Third, optimal weights are suggested for weighted linear combinations of individual line-detector responses. Fourth, instead of using one global threshold, a hysteresis threshold is proposed to find a connected vessel tree. The overall impact of these modifications is a large improvement in noise removal capability of the conventional multi-scale line-detector method while finding more of the thin vessels. The contrast-sensitive steps are validated using a publicly available database and show considerable promise for the suggested strategy.

Vessel local characteristics such as noise, illumination, and direction vary significantly in a fundus image, making it difficult to segment the vessel tree structure as a whole. To facilitate vessel detection, an alternative procedure proposed here, whereby retinal vessels first classified into two categories, large and small. Then, for its unique characteristics, each group has been processed with its own enhancement and detection filter. The sensitivity of the proposed method is boosted by capturing tiny vessels through a directional filter bank followed by its associated triple-stick filtering. Additionally, the specificity of the proposed method is enhanced through noise suppression attributed largely to the proposed BM3D filtering and multi-scale line detection approach. As a result, the detection accuracy on the DRIVE, STARE, and CHASE DB1 datasets is significantly improved, with scores of 0.9610, 0.9586, and 0.9578, respectively.

An automatic retinal vessel segmentation method is proposed for quick and accurate segmentation of eye vessels. Such a method would play a vital role in analyzing many eye diseases. A retinal fundus image contains varying low contrasts, which undermine the performance of the segmentation process. Independent component analysis (ICA) is largely used for noise removal and consists of two architectures, designated as ICA1 and ICA2. We have validated both ICA architectures on retinal color fundus images and selected the one that provides improved contrast values. For retinal fundus, ICA2 architecture performed better than ICA1 by virtue of being more effective in compensating the low contrast values. Experiments conducted here validated the improvements over previously reported state-of-the-art methods. The impact of proposed segmentation model was assessed on publicly available databases like DRIVE and STARE. In case of the DRIVE database, the sensitivity increased 3% by (from 72% to 75%) while maintaining a segmentation accuracy of around 96%.

The correlation between retinal vessel structural changes and the progression of diseases such as diabetes, hypertension, and cardiovascular problems has been the subject of several large-scale clinical studies. However, detecting structural changes in retinal vessels in a sufficiently fast and accurate manner, in the face of interfering pathologies, is a challenging task. This significantly limits the application of these studies to clinical practice. Though monumental work has already been proposed to extract vessels in retinal images, they mostly lack necessary sensitivity to pick low-contrast vessels. This paper presents a couple of contrast-sensitive measures to boost the sensitivity of existing retinal vessel segmentation algorithms. Firstly, a contrast normalization procedure for the vascular structure is adapted to lift low-contrast vessels to make them at par in comparison with their high-contrast counterparts. The second measure is to apply a scale-normalized detector that captures vessels regardless of their sizes. Thirdly, a flood-filled reconstruction strategy is adopted to get binary output. The process needs initialization with properly located seeds, generated here by another contrast-sensitive detector called isophote curvature. The final sensitivity boosting measure is an adoption process of binary fusion of two entirely different binary outputs due to two different illumination correction mechanism employed in the earlier processing stages. This results in improving the noise removal capability while picking low-contrast vessels. The contrast-sensitive steps are validated on a publicly available database, which shows considerable promise in the strategy adopted in this research work.

The enhancement of coherent flow-like structures is desired for many image processing tasks, such as segmentation and feature detection. This task can be accomplished in a natural way by adopting anisotropic diffusion filtering using a diffusion matrix adapted to the local structure. This method is referred to as coherence-enhancing diffusion (CED). The performance of CED can be analyzed by observing the evolution of the orientation field (OF) associated with an evolving diffusion matrix. It was revealed from a series of experiments that the final OF from a CED-enhanced image sometimes strays from its true underlying OF (marked by a human expert), degrading its performance. In this paper, a strategy is proposed which repeatedly cleans the OF associated with a diffusion matrix. Thus, for every iteration of CED, its OF is diffused separately until it converges and is then fed back to the CED process to move forward. This hypothesis is tested with the motive of getting an enhanced CED performance. The proposed scheme is validated using fingerprint data, and their numerical results are displayed.

Bone fracture detection from the digital image segmentation is a well-known image processing application which is frequently used to process biomedical images. Hardware realization of different image processing algorithm specially utilizing Field Programmable Gate Array (FPGA) has been gained a great interest among the researchers. FPGA has many significant features like spatial and temporal parallelism that best suits for real-time implementation of image processing. To gain the benefit from these characteristics of a FPGA, a new method for bone fracture detection is proposed and its performance is validated through real-time implementation. Simulation results show that the proposed method give superior performance than the existing method.

Eye-related disease such as diabetic retinopathy (DR) is a medical ailment in which the retina of the human eye is smashed because of damage to the tiny retinal blood vessels in the retina. Ophthalmologists identify DR based on various features such as the blood vessels, textures and pathologies. With the rapid development of methods of analysis of biomedical images and advanced computing techniques, image processing-based software for the detection of eye disease has been widely used as an important tool by ophthalmologists. In particular, computer vision-based methods are growing rapidly in the field of medical images analysis and are appropriate to advance ophthalmology. These tools depend entirely on visual analysis to identify abnormalities in Retinal Fundus images. During the past two decades, exciting improvement in the development of DR detection computerised systems has been observed. This paper reviews the development of analysing retinal images for the detection of DR in three aspects: automatic algorithms (classification or pixel to pixel methods), detection methods of pathologies from retinal fundus images, and extraction of blood vessels of retinal fundus image algorithms for the detection of DR. The paper presents a detailed explanation of each problem with respect to retinal images. The current techniques that are used to analyse retinal images and DR detection issues are also discussed in detail and recommendations are made for some future directions.

Retinal vessel segmentation plays a major role in the detection of many eye diseases, and it is required to implement an automated algorithm for analyzing the progress of eye diseases. A variety of automated segmentation methods have been presented but almost all studies to date showed weakness in their low sensitivity toward narrow low-contrast vessels. A new segmentation method is proposed to address the issue of low sensitivity, by including modules such as principal component analysis-based color-to-gray conversion, scale normalization factors for improved narrow vessel detection, anisotropic diffusion filtering with an adequate stopping rule, and edge pixel-based hysteresis threshold. The impact of these additional steps is assessed on publicly available databases like DRIVE and STARE. For the case of DRIVE database, the sensitivity is raised from 73 to 75%, while maintaining the accuracy of 96.5%, and found to provide evidence of improved sensitivity.

Anisotropic diffusion is an important noise reduction process in many pattern recognition systems. The local orientations and shape are encoded in a descriptor, called second-moment matrix, to be used as the central part of the process. For a noisy image, it becomes hard to find the elements of the matrix with reasonable accuracy. Two layers of subsequent Gaussian smoothing are applied conventionally: One is referred to as noise scale and the other integration scale. It is still not guaranteed that a second-moment matrix is correctly aligned with underlying pattern flow directions. It is largely believed that the integration scale handles this orientation discrepancy. Therefore, some researchers suggested a space-dependent integration scale strategy. We propose here a calibration strategy using directional filterbank (DFB). The second-moment matrix is rotated to go along the proper ridge directions with an angle correction term from DFB. The experiments conducted show promise for the calibrated anisotropic diffusion process in terms of improved recognition rate over that of the un-calibrated process.

A real-time image filtering technique is proposed which could result in faster implementation for fingerprint image enhancement. One major hurdle associated with fingerprint filtering techniques is the expensive nature of their hardware implementations. To circumvent this, a modified anisotropic Gaussian filter is efficiently adopted in hardware by decomposing the filter into two orthogonal Gaussians and an oriented line Gaussian. An architecture is developed for dynamically controlling the orientation of the line Gaussian filter. To further improve the performance of the filter, the input image is homogenized by a local image normalization. In the proposed structure, for a middle-range reconfigurable FPGA, both parallel compute-intensive and real-time demands were achieved. We manage to efficiently speed up the image-processing time and improve the resource utilization of the FPGA. Test results show an improved speed for its hardware architecture while maintaining reasonable enhancement benchmarks.

Deep learning-based side channel attacks are burgeoning due to their better efficiency and performance, suppressing the traditional side-channel analysis. To launch the successful attack on a particular public key cryptographic (PKC) algorithm, a large number of samples per trace might need to be acquired to capture all the minor useful details from the leakage information, which increases the number of features per instance. The decreased instance-feature ratio increases the computational complexity of the deep learning-based attacks, limiting the attack efficiency. Moreover, data class imbalance can be a hindrance in accurate model training, leading to an accuracy paradox. We propose an efficient Convolutional Neural Network (CNN) based approach in which the dimensionality of the large leakage dataset is reduced, and then the data is processed using the proposed CNN based model. In the proposed model, the optimal number of convolutional blocks is used to build powerful features extractors within the cost limit. We have also analyzed and presented the impact of using the Synthetic Minority Over-sampling Technique (SMOTE) on the proposed model performance. We propose that a data-balancing step should be mandatory for analysis in the side channel attack scenario. We have also provided a performance-based comparative analysis between proposed and existing deep learning models for unprotected and protected Elliptic curve (ECC) Montgomery Power ladder implementations. The reduced network complexity, together with an improved attack efficiency, promote the proposed approach to be effectively used for side-channel attacks.

In this paper, we present a gradient-free approach for training multi-layered neural networks based upon quantum perceptrons. Here, we depart from the classical perceptron and the elemental operations on quantum bits, i.e. qubits, so as to formulate the problem in terms of quantum perceptrons. We then make use of measurable operators to define the states of the network in a manner consistent with a Markov process. This yields a Dirac–Von Neumann formulation consistent with quantum mechanics. Moreover, the formulation presented here has the advantage of having a computational efficiency devoid of the number of layers in the network. This, paired with the natural efficiency of quantum computing, can imply a significant improvement in efficiency, particularly for deep networks. Finally, but not least, the developments here are quite general in nature since the approach presented here can also be used for quantum-inspired neural networks implemented on conventional computers.

The automatic detection of retinal blood vessels by computer aided techniques plays an important role in the diagnosis of diabetic retinopathy, glaucoma, and macular degeneration. In this paper we present a semantically flexible feature fusion network that employs residual skip connections between adjacent neurons to improve retinal vessel detection. This yields a method that can be trained employing residual learning. To illustrate the utility of our method for retinal blood vessel detection, we show results on two publicly available data sets, i.e. DRIVE and STARE. In our experimental evaluation we include widely used evaluation metrics and compare our results with those yielded by alternatives elsewhere in the literature. In our experiments, our method is quite competitive, delivering a margin of sensitivity and accuracy improvement as compared to the alternatives under consideration.

Fundus examination is a non-invasive procedure of observing changes in retinal vasculature linked with the identification and progression of certain ocular diseases. Segmenting vessels from the rest of the structure is found helpful in analyzing and later tracking the changes. Manual vessel segmentation requires clinical expertise, and with large scale screening certainly puts a burden on already scarce clinical resources. A computer-aided diagnosis (CAD) recently emerged to alleviate this burden. A variety of computerized methods have emerged recently with the primary aim of providing accurate vessel segmentation. One particularly interesting approach is multi-scale line filtering. However, its response diminishes in low-contrast areas of the image causing certain vessels to be missed. In this paper, we investigate the use of phase symmetry detector to get help with low-contrast vessel detection. This specific detector does not make any assumptions about the luminance profile of the vessel but then has major drawback of being sensitive to background noise. To reduce the noise sensitivity, we adopted the multi-scale line filtering with an improved vessel uniformity function as an input to the phase symmetry detector. The low-contrast vessel information thus made available helps in providing an improved accuracy for automated vessel segmentation algorithms. The quantitative tests are conducted for two publicly available databases (DRIVE, STARE) of fundus images that shows promise of improvements in all three performance categories called accuracy, sensitivity, and specificity.

Persistent changes in the diameter of retinal blood vessels may indicate some chronic eye diseases. Computer-assisted change observation attempts may become challenging due to the emergence of interfering pathologies around blood vessels in retinal fundus images. The end result is lower sensitivity to thin vessels for certain computerized detection methods. Quite recently, multi-scale line detection method proved to be worthy for improved sensitivity toward lower-caliber vessels detection. This happens largely due to its adaptive property that responds more to the longevity patterns than width of a given vessel. However, the method suffers from the lack of a better aggregation process for individual line detectors. This paper investigates a scenario that introduces a supervised generalized Gaussian mixture classifier as a robust solution for the aggregate process. The classifier is built with class-conditional probability density functions as a logistic function of linear mixtures. To boost the classifier’s performance, the weighted scale images are modeled as Gaussian mixtures. The classifier is trained with weighted images modeled on a Gaussian mixture. The net effect is increased sensitivity for small vessels. The classifier’s performance has been tested with three commonly available data sets: DRIVE, SATRE, and CHASE_DB1. The results of the proposed method (with an accuracy of 96%, 96.1% and 95% on DRIVE, STARE, and CHASE_DB1, respectively) demonstrate its competitiveness against the state-of-the-art methods and its reliability for vessel segmentation.

For visible wavelengths, a new method is introduced using truncated LoG filter with specific preprocessing to deal with challenges of eyebrows, illumination variation, eyelid masking, perspective, and movements. Here, the iris boundary is detected first and then pupil is marked with maximally stable extremal regions. The experiments conducted on challenging database UBIRIS v2 demonstrate the improved segmentation accuracy of the proposed methods. The comparison with other popular methods provides promise in terms of accuracy and speed.

A timely diagnosis of Glaucoma has crucial importance in preventing blindness. As this disease exists in the immediate vicinity of the optical disk (OD), its precise localization and segmentation are critical in its accurate diagnosis. OD consists of two parts, namely: neuroretinal and optic cup (OC). In the proposed work, the problem of OD and OC segmentation is modeled as a semantic pixel-wise labeling problem, thus bridging the gap between medical image segmentation and semantic segmentation. The proposed method eliminates the need for pre- and post-processing steps. The proposed method is evaluated for the segmentation of OD and OC on Drishti and Rim-one datasets. The offered low computational and resource requirements along with the observed state-of-the-art accuracy of the proposed method support its implementation in the real-time automatic screening of the Glaucoma disease.

Fingerprints are the oldest and most widely used form of biometric identification. Many researchers have addressed the fingerprint classification problem and significant progress has been made in designing automatic fingerprint identification systems (AFIS) over the past two decades. However, some design factors such as lack of reliable minutia extraction algorithms, difficulty in quantitatively defining a reliable match between fingerprint images, poor image acquisition, low contrast images create bottlenecks in achieving the desired performance. Noticeable among them is the fact that digitally acquired fingerprint images are rarely of perfect quality to be used directly with AFIS; one important step is fingerprint enhancement. Conventional fingerprint enhancement methods, such as Gabor and anisotropic filters, do fill the holes and gaps in ridge lines but lack the necessary capability to tackle scar lines. For scar lines, an explicit filling process is proposed that is a mix of Fourier and spatial domain strategies. The proposed method is to make use of the Fourier domain directional field to trace an appropriate candidate for the scar pixels to be replaced with. The necessary components of the process are locating scars, estimating directional field, and the filling strategy. This process can act as front-end to the subsequent Gabor and anisotropic diffusion filtering. The simulation results for synthetic, as well as real fingerprints, show improved performance regarding better extraction of genuine minutia points. HighlightsWe Model a new proposed method to make use of the Fourier domain directional field to trace an appropriate candidate for the scar pixels to be replaced with.The necessary components of the process are locating scars, finding the directional field, and the filling strategy.The strategy relies on the fact that in these linear scars, the ridge/valley pattern is still intact across the scar region.Using this information, the scar boundary is filled with appropriate normal region pixels using the local orientation field.This process can act as front-end to the subsequent Gabor and anisotropic diffusion filtering.

Vessel segmentation has come a long way in terms of matching the experts at detection accuracy, yet there is potential for further improvement. In this regard, the accurate detection of vessels is generally more challenging due to the high variations in vessel contrast, width, and the observed noise level. Most vessel segmentation strategies utilize contrast enhancement as a preprocessing step, which has an inherent tendency to aggravate the noise and therefore, impede accurate vessel detection. To alleviate this problem, we propose to use the state-of-the-art Probabilistic Patch-Based (PPB) denoiser within the framework of an unsupervised retinal vessel segmentation strategy based on the Frangi filter. The PPB denoiser helps preserve vascular structure while effectively dealing with the amplified noise. Also, the modified Frangi filter is evaluated separately for tiny and large vessels, followed by individual segmentation and linear recombination of the binarized outputs. This way, the performance of the modified Frangi filter is significantly enhanced. The performance evaluation of the proposed method is evaluated on two recognized open-access datasets, viz: DRIVE and STARE. The proposed strategy yields competitive results for both preprocessing modalities, i.e., Contrast Limited Adaptive Histogram Equalization (CLAHE) and Generalized Linear Model (GLM). The performance observed for CLAHE over DRIVE and STARE datasets is (Sn = 0.8027, Acc = 0.9561) and (Sn = 0.798, Acc = 0.9561), respectively. For GLM, it is observed to be (Sn = 0.7907, Acc = 0.9603) and (Sn = 0.7860, Acc = 0.9583) over DRIVE and STARE datasets, respectively. Furthermore, based on the conducted comparative study, it is established that the proposed method outperforms various notable vessel segmentation methods available in the existing literature.

Coherence-enhancing diffusion filtering is a striking application of the anisotropic diffusion in image processing. The technique deals with the problem of completion of interrupted lines and enhancement of flow-like features in fingerprint images. However, an anisotropic diffusion process is an iterated process, initializes with a poor quality image, and converges at the end towards a completely blurred image, with no structure surviving at the end. In anisotropic diffusion, one important question is how to find boundary between the under-smoothing and over-smoothing regions of the anisotropic diffusion process. The entropy change is found to be one such measure to describe that boundary adequately and thus provides a reasonable stopping rule for anisotropic diffusion. Numerical experiments with test pattern images confirm the desirable qualities of gap-closing and flow-enhancing qualities, along with the identification of frontier of useful smoothing. The proposed scheme is evaluated with the help of simulated images, and compared with other state of the art schemes using an objective criterion.

The objective of this paper is to design a model which can integrate a range sensor with real time image processing. An FPGA provides physical solutions for most image processing problems and offers a new hardware acceleration opportunity. In this paper we implemented image normalization along with edge detection on real time images and then integrated the range sensor. The model is validated using Spartan-3 FPGA.

Vector quantization (VQ) techniques have been used for a number of years for developing successful data compression and classification algorithms. Vector quantization is inherently an unsupervised data clustering technique that smartly adopts to the given data statistics and is thus used in large variety of tasks. The gains associated with a VQ system are largely linked to the size of the block used. However, the complexity increases exponentially with an increase in block length. In conventional methods, a dimensional reduction pre-processing step is invoked before the VQ system in order to reduce the block length. For some data sources this may be unacceptable approach such as with hyper-spectral data. Therefore, a large block VQ is needed to fully exploit the linear and non-linear correlation in a data source. We propose an entropy-constrained reflected residual VQ (EC-RRVQ) as one alternative for large block vector quantization. The reflected residual VQ, a type of multistage VQ, has constrained structure with multiple stages having small-size code-books. The use of multiple code-books and a reflection constraint makes the computational complexity linearly depend on the number of stages involved. The linear increase in complexity prompted us to pose EC-RRVQ as a contender in the list of options of large block vector quantization implementation algorithms. Experimental results indicate that good image reproduction quality can be accomplished at relatively low bit rates. The performance of a 64-stage 16 × 16 EC-RRVQ at 0.175 bits per pixel is 23.75 dB with 96 vector distortion calculations per source vector, while the number for previously proposed large-dimensional entropy-constrained residual VQ (EC-RVQ) designed under the same specifications is 21.17 dB with 1212 vector distortion calculations per source vector.

Automatic optic disc (OD) localization and segmentation is not a simple process as the OD appearance and size may significantly vary from person to person. This paper presents a novel approach for OD localization and segmentation which is fast as well as robust. In the proposed method, the image is first enhanced by de-hazing and then cropped around the OD region. The cropped image is converted to HSV domain and then V channel is used for OD detection. The vessels are extracted from the Green channel in the cropped region by multi-scale line detector and then removed by the Laplace Transform. Local adaptive thresholding and region growing are applied for binarization. Furthermore, two region properties, eccentricity, and area are then used to detect the true OD region. Finally, ellipse fitting is used to fill the region. Several datasets are used for testing the proposed method. Test results show that the accuracy and sensitivity of the proposed method are much higher than the existing state-of-the-art methods.

The main task of a fingerprint image enhancement is to enhance the image in such a way that it not only remove the noise but also enhance the reliable minutiae points. For this purpose, in this paper we propose a multi-scale decimation-free directional filter bank method for reliable orientation estimation. This reliable orientation is used in coherence enhancement diffusion and in Gabor filter based enhancement, which overcomes the drawbacks of these two methods. Experimental results show that the proposed method not only enhances the images but also facilitates the minutiae algorithm, by enhancing the true minutiae points.

The advances in recording, editing, and broadcasting multimedia contents in digital form motivate to protect these digital contents from illegal use, such as duplication, manipulation, and redistribution. However, watermarking algorithms are designed to satisfy requirements of applications, as different applications have different concerns. We intend to design a watermarking algorithm for applications which require high embedding capacity and imperceptibility, to maintain the integrity of the host signal as well as embedded information. Reversible watermarking is a promising technique which satisfies our requirements. In this paper, we concentrate on improving the watermark capacity and reducing the perceptual degradation of an image. We investigated the Luo's [1] additive interpolation-error expansion algorithm and enhanced it by incorporating with two intelligent techniques: genetic algorithm (GA), and particle swarm optimization (PSO). Genetic algorithm is applied to exploit the correlation of image pixel values to obtain better estimation of neighboring pixel values, which results in optimal balance between information storage capacity and imperceptibility. Particle swarm optimization (intelligent technique) is also applied for the same purpose. Experimental results show that PSO and GA nearly give the same results, but GA outperforms the PSO. Experimental results also reveal that the proposed strategy outperforms the state of art works in terms of perceptual quality and watermarking payload.

In this paper, Coherence Enhancement Diffusion (CED) is boosted feeding external orientation using new robust orientation estimation. In CED, proper scale selection is very important as the gradient vector at that scale reflects the orientation of local ridge. For this purpose a new scheme is proposed in which pre calculated orientation, by using local and integration scales. From the experiments it is found the proposed scheme is working much better in noisy environment as compared to the traditional Coherence Enhancement Diffusion

The assessment of transformations in the retinal vascular structure has a strong potential in indicating a wide range of underlying ocular pathologies. Correctly identifying the retinal vessel map is a crucial step in disease identification, severity progression assessment, and appropriate treatment. Marking the vessels manually by a human expert is a tedious and time-consuming task, thereby reinforcing the need for automated algorithms capable of quick segmentation of retinal features and any possible anomalies. Techniques based on unsupervised learning methods utilize vessel morphology to classify vessel pixels. This study proposes a directional multi-scale line detector technique for the segmentation of retinal vessels with the prime focus on the tiny vessels that are most difficult to segment out. Constructing a directional line-detector, and using it on images having only the features oriented along the detector&rsquo, s direction, significantly improves the detection accuracy of the algorithm. The finishing step involves a binarization operation, which is again directional in nature, helps in achieving further performance improvements in terms of key performance indicators. The proposed method is observed to obtain a sensitivity of 0.8043, 0.8011, and 0.7974 for the Digital Retinal Images for Vessel Extraction (DRIVE), STructured Analysis of the Retina (STARE), and Child Heart And health Study in England (CHASE_DB1) datasets, respectively. These results, along with other performance enhancements demonstrated by the conducted experimental evaluation, establish the validity and applicability of directional multi-scale line detectors as a competitive framework for retinal image segmentation.

DIBR-3D technology has evolved over the past few years with the demands of consumers increasing in recent times for future free-view 3D videos on their home televisions. The main issue in 3D technology is the lack of 3D content available to watch using the traditional TV systems. Although, some sophisticated devices like stereoscopic cameras have been used to fill the gap between the 3D content demand and 3D content supply. But the content generated through these sophisticated devices can not be displayed on the traditional TV systems, so there needs to be some mechanism which is inline with the traditional TV. Furthermore, the huge collection of existing 2D content should be converted to 3D using depth image-based rendering techniques. This conversion technique can highly contribute in overcoming the shortage problem of the 3D content. This paper presents a novel approach for converting 2D degraded image for DIBR 3D-TV view. This degraded or noisy/blur image is enhanced through image dehazing and Directional Filter Bank (DFB). This enhancement is necessary because of the occlusion effect or hole filling problem that occurs due to imperfect depth map. The enhanced image is then segmented into the foreground image and the background image. After the segmentation, the depth map is generated using image profiles. Moreover, Stereoscopic images are finally produced using the DIBR procedure which is based on the 2D input image and the corresponding depth map. We have verified the results of the proposed approach by comparing the results with the existing state-of-the-art techniques.

A new method based upon data driven tool, principal component analysis (PCA), for fingerprint enhancement is proposed in this paper. PCA is a very useful statistical technique that has found application in many different fields like image compression, face recognition and is commonly used for finding patterns in data of high dimension. In the proposed method, the input image is first decomposed into directional images using decimation free Directional Filter Bank (DDFB). Then these directional images are normalized. A data driven technique PCA is applied to these normalized directional fingerprint images, which gives the PCA filtered images. These are basically directional images. Then these directional images are reconstructed into one image which is the enhanced one. Simulation results are included illustrating the capability of the proposed method.

Retinal vessel segmentation plays a key role in the detection of numerous eye diseases, and its reliable computerised implementation becomes important for automatic retinal disease screening systems. A large number of retinal vessel segmentation algorithms have been reported, primarily based on three main steps including uniforming background, using the second-order Gaussian detector and applying binarization. These methods though improve the accuracy levels, their sensitivity to low-contrast in vessels still needs attention. In this paper, some contrast-sensitive approaches are discussed and embedded in the conventional algorithms, resulting in improved sensitivity for a given retinal vessel extraction technique. The proposed method gives good performance on both publicly databases with the accurate vessel extraction on STARE database. The proposed unsupervised method achieves the accuracy of 94.41%, much better than some existing unsupervised methods and comparable to some supervised methods. Its efficiency with different image conditions, together with its simplicity and fast operation, makes the blood vessel segmentation application suitable for retinal image computer analyses such as automated screening for early diabetic retinopathy detection.