Weber Local Descriptor Research Articles

Water Wheel Plant Dingo Optimizer enabled Deep Convolutional Neural Network for disease detection using hyperspectral leaf image

ProblemIn many countries, agriculture is themain sourceofpeople’s livelihoodandsatisfiestheir nutritional needs.Earlydetection ofplantdiseases throughagriculturalremote monitoringis important to prevent the disease’s spread. The traditional methods require sampling and can damage the plant, but hyperspectral imaging is non-destructive. AimThe major aim of this research is to devise a Water Wheel Plant Dingo Optimizer_Deep Convolutional Neural Network (WWPDO_Deep CNN) for disease detection using a hyperspectral leaf image. MethodsInitially, the input leaf image is given into the leaf segmentation phase, which is done using the proposed Water Wheel Plant Dingo Optimizer (WWPDO), which is the amalgamation of the Water Wheel Plant Algorithm (WWPA) and Dingo Optimizer (DOX). The selected bands’ outputs are subjected to leaf segmentation and which is carried out by employing Bayesian Fuzzy Clustering (BFC). Thereafter, leaf segmented outputs are fussed using the majority voting method. Fused output and individual leaf segmentation output are given into the feature extraction process to extract features, such as local binary patterns and Weber local descriptors. Finally, leaf disease detection is performed using a deep Convolutional Neural Network (Deep CNN) for normal and abnormal cases. The hyperparameters of the Deep CNN are fine-tuned based on the proposed WWPADO. ResultsThe proposed WWPDO_Deep CNN achieved an excellent performance with an accuracy of 91.35 %, a True Positive Rate (TPR) of 93.13 % and a True Negative Rate (TNR) of 90.76 %. ConclusionThe WWPDO_Deep CNN is applicable for early diagnosis under the new classification system and provides a new direction for early diagnosis based on hyperspectral images. Also, the devised model provides an accurate diagnosis of plant diseases. Early and accurate detection allows targeted treatment, reduces the need for widespread pesticide application and promotes more sustainable farming practices.

Copy-Move Forgery Verification in Images Using Local Feature Extractors and Optimized Classifiers

Passive image forgery detection methods that identify forgeries without prior knowledge have become a key research focus. In copy-move forgery, the assailant intends to hide a portion of an image by pasting other portions of the same image. The detection of such manipulations in images has great demand in legal evidence, forensic investigation, and many other fields. The paper aims to present copy-move forgery detection algorithms with the help of advanced feature descriptors, such as local ternary pattern, local phase quantization, local Gabor binary pattern histogram sequence, Weber local descriptor, and local monotonic pattern, and classifiers such as optimized support vector machine and optimized NBC. The proposed algorithms can classify an image efficiently as either copy-move forged or authenticated, even if the test image is subjected to attacks such as JPEG compression, scaling, rotation, and brightness variation. CoMoFoD, CASIA, and MICC datasets and a combination of CoMoFoD and CASIA datasets images are used to quantify the performance of the proposed algorithms. The proposed algorithms are more efficient than state-of-the-art algorithms even though the suspected image is post-processed.

Parameter optimization of histogram-based local descriptors for facial expression recognition.

An important task in automatic facial expression recognition (FER) is to describe facial image features effectively and efficiently. Facial expression descriptors must be robust to variable scales, illumination changes, face view, and noise. This article studies the application of spatially modified local descriptors to extract robust features for facial expressions recognition. The experiments are carried out in two phases: firstly, we motivate the need for face registration by comparing the extraction of features from registered and non-registered faces, and secondly, four local descriptors (Histogram of Oriented Gradients (HOG), Local Binary Patterns (LBP), Compound Local Binary Patterns (CLBP), and Weber's Local Descriptor (WLD)) are optimized by finding the best parameter values for their extraction. Our study reveals that face registration is an important step that can improve the recognition rate of FER systems. We also highlight that a suitable parameter selection can increase the performance of existing local descriptors as compared with state-of-the-art approaches.

Classification of intracranial hemorrhage CT images based on texture analysis using ensemble-based machine learning algorithms: A comparative study

Blood vessels in the brain tissue can leak or burst, causing an intracranial hemorrhage, a potentially fatal disorder. One of the critical steps in brain stroke imaging is the categorization of intracranial hemorrhages. This article aims to perform texture-based intracranial hemorrhage computed tomography image classification with ensemble and machine learning classifiers using local binary pattern, local ternary pattern, and Weber local descriptor approach. The most common texture feature extraction method is a local binary pattern; however, other methods such as local ternary pattern, Weber local descriptor, and local binary pattern are also utilized for texture feature extraction. For all the extracted texture codes, histograms are applied, and finally, single feature vector texture codes by performing the concatenation of the bin. The efficacy of feature descriptors for classifying images into abnormal and normal classes was assessed using ten distinct classifiers. The result shows that Weber's local descriptor shows promising results in texture code classification for ensemble-based classification. For all texture-based methods, classification accuracy was better than standard machine learning. According to the findings of the experiment, the Random Forest classifier outperformed all other classifiers in terms of classification accuracy (86.55%), recall (86.31%), precision (87.23%), sensitivity (86.31%), specificity (86.81%), and F1-score (86.77%) for the Weber local descriptor.

A Robust Local Texture Descriptor in the Parametric Space of the Weibull Distribution

Research in texture feature approximation is still in the embryonic stage because of difficulties in developing a sound theoretical model to express the unique pattern in the intensity-variation of pixels in the neighbourhood of the pixel-of-interest so that it can sufficiently discriminate different textures. Local texture descriptors are widely used in image segmentation as they comprise pixel-wise features. The Weber local descriptor (WLD) with differential excitation and gradient orientation components, inspired by Weber's Law, has been leveraged in the state-of-the-art iterative contraction and merging (ICM) image segmentation technique. However, WLD has inherent drawbacks in the formulation of the components that limit its discriminatory capability. This paper introduces a novel texture descriptor by directly modelling the distribution of intensity-variation in the parametric space of the Weibull distribution using its shape and scale parameters. A unified ‘joint scale’ texture property is introduced, which can discriminate textures better than the individual parameters while keeping the length of the descriptor shorter. Additionally, the accuracy of WLD's gradient orientation component is improved by using an extended Sobel operator and expressing gradients in <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$[-\pi /2,\pi /2)$</tex-math></inline-formula> range. When incorporated in ICM, the proposed texture descriptor has consistently outperformed WLD and a recent enhancement with radial mean WLD (RM-WLD) on three benchmark datasets. It has also outperformed two other texture segmentation techniques and their deep learning based improvements.

A Scheme for Effective Skin Disease Detection using Optimized Region Growing Segmentation and Autoencoder based Classification

Detecting skin disorders just through visual inspection is difficult due to the complicated and overlapping nature of sick lesions, background skin textures, skin hair, low illumination, etc. Computer Vision and Machine Learning are playing a great role in identifying the correct type of diseased lesion. However, in the presence of the aforementioned artefacts, current computational approaches are equally limited in their ability to detect complicated lesion structures. We provide a novel detection framework to enhance skin disease diagnosis. Beginning with segmentation and feature extraction from diseased lesions, this framework uses autoencoder based classification model. Diseased lesions are segmented using Optimized Region Growing using Grey Wolf Optimization (GWO). Texture features are extracted from the segmented lesion using Gray Level Co-occurrence Matrix (GLCM), and Weber Local Descriptor (WLD). Finally, a reduced feature set is generated through latent representation using the autoencoder. An integrated convolutional neural network is used to classify the diseased lesions from latent representation. The proposed framework significantly outperformed the traditional deep classification strategies, according to experimental findings.

Image copy-move forgery detection based on dynamic threshold with dense points

Copy-move tampering is one of the most popular tampering techniques at present. The tampered region of the image has good fusion with the original image, which increases the difficulty of detection. After years of research, the current detection method based on key points still has the following problems: 1) Failure to achieve forgery detection of small areas/self-similar areas/smooth areas, 2) Lack of reasonable feature point extraction methods, 3) The various stages of copy-move forgery detection (CMFD) work are relatively independent and lack close connections, 4) A fixed threshold is used as the region of interest similarity metric in the matching and localization stages. The failure to consider tampered images and the diversity of tampered regions leads to the limited detection capability of the algorithm. Considering the actual situation of tampering with the picture, to solve the above problems, we propose a copy-move forgery detection method based on the dynamic threshold. First, we determine the point extraction strategy in each super pixel block according to the size of the simple line interface calculation (SLIC) super pixel block and the Weber local descriptor (WLD) descriptor to ensure the reasonable allocation of feature points and reduce unnecessary points. These key points are then characterized by the scaling, flip and rotation invariants of the fractional general Jacobi-Fourier moments (FJFMs). Then, the matching and mismatch filtering thresholds of each feature point are determined through the WLD and SLIC features, and the SLIC feature is used to replace the distance threshold to improve the detection accuracy of small manufacturing areas. Finally, based on the matching results and SLIC features, an effective positioning method is proposed to improve the speed and accuracy of positioning. Experimental results show that the proposed algorithm is superior to the classic methods in recent years in terms of time and accuracy.

Hybrid Pattern Extraction with Deep Learning-Based Heart Disease Diagnosis Using Echocardiogram Images

Echocardiography represents a noninvasive diagnostic approach that offers information concerning hemodynamics and cardiac function. It is a familiar cardiovascular diagnostic test apart from chest X-ray and echocardiography. The medical knowledge is enhanced by the Artificial Intelligence (AI) approaches like deep learning and machine learning because of the increase in the complexity as well as the volume of the data that in turn unlocks the clinically significant information. Similarly, the usage of developing information as well as communication technologies is becoming important for generating a persistent healthcare service via which the chronic disease and elderly patients get their medical facility at their home that in turn enhances the life quality and avoids hospitalizations. The main intention of this paper is to design and develop a novel heart disease diagnosis using speckle-noise reduction and deep learning-based feature learning and classification. The datasets gathered from the hospital are composed of both the images and the video frames. Since echocardiogram images suffer from speckle noise, the initial process is the speckle-noise reduction technique. Then, the pattern extraction is performed by combining the Local Binary Pattern (LBP), and Weber Local Descriptor (WLD) referred to as the hybrid pattern extraction. The deep feature learning is conducted by the optimized Convolutional Neural Network (CNN), in which the features are extracted from the max-pooling layer, and the fully connected layer is replaced by the optimized Recurrent Neural Network (RNN) for handling the diagnosis of heart disease, thus proposed model is termed as CRNN. The novel Adaptive Electric Fish Optimization (A-EFO) is used for performing feature learning and classification. In the final step, the best accuracy is achieved with the introduced model, while a comparative analysis is accomplished over the traditional models. From the experimental analysis, FDR of A-EFO-CRNN at 75% learning percentage is 21.05%, 15%, 48.89%, and 71.95% progressed than CRNN, CNN, RNN, and NN, respectively. Thus, the performance of the A-EFO-CRNN is enriched than the existing heuristic-oriented and classifiers in terms of the image dataset.

A Deep Learning and Handcrafted Based Computationally Intelligent Technique for Effective COVID-19 Detection from X-ray/CT-scan Imaging.

The world has witnessed dramatic changes because of the advent of COVID19 in the last few days of 2019. During the last more than two years, COVID-19 has badly affected the world in diverse ways. It has not only affected human health and mortality rate but also the economic condition on a global scale. There is an urgent need today to cope with this pandemic and its diverse effects. Medical imaging has revolutionized the treatment of various diseases during the last four decades. Automated detection and classification systems have proven to be of great assistance to the doctors and scientific community for the treatment of various diseases. In this paper, a novel framework for an efficient COVID-19 classification system is proposed which uses the hybrid feature extraction approach. After preprocessing image data, two types of features i.e., deep learning and handcrafted, are extracted. For Deep learning features, two pre-trained models namely ResNet101 and DenseNet201 are used. Handcrafted features are extracted using Weber Local Descriptor (WLD). The Excitation component of WLD is utilized and features are reduced using DCT. Features are extracted from both models, handcrafted features are fused, and significant features are selected using entropy. Experiments have proven the effectiveness of the proposed model. A comprehensive set of experiments have been performed and results are compared with the existing well-known methods. The proposed technique has performed better in terms of accuracy and time.

Carp-DCAE: Deep convolutional autoencoder for carp fish classification

The fisheries industry relies heavily on automatic fish species identification for its socio-economic well-being. Due to the similarity in shape and size of the major carps , it can be difficult to recognise them using morphological features. To recognise these species automatically, our proposed autoencoder network models have been applied to a fish dataset containing 1500 images of three major carps of India. As a feature, the autoencoder model’s latent representation is used. After the training phase is complete, the decoder is removed and fish species are categorised using several classifiers. Different variations of autoencoders, such as the Simple Autoencoder, the Deep Autoencoder, and the Deep Convolutional Autoencoder are applied with different hyper parameters. An encouraging maximum accuracy rate of 97.33% is obtained in 250 epochs with a learning rate of 0.0001 using Deep Convolutional Autoencoder. Some well-known machine learning classifiers, such as Logistic Regression, Naive Bayes, K-Nearest Neighbor, Support Vector Machine, and Random Forest, are also used to evaluate the latent representation’s effectiveness using the latent representation as a feature vector. The Support Vector Machine-based latent representation of the Deep Convolutional Autoencoder outperformed all other approaches significantly. The models’ performance is compared to that of Hu moments, Haralick texture, Weber local descriptor, HOG descriptor etc. with best classifiers along with different deep learning models, such as InceptionV3, InceptionResNetV2, MobileNet, VGG16 and VGG19. The Deep Convolutional Autoencoder outperforms the other models by 52%, 43.55%, 13.77%, 6.67%, 22.22%, 15.11%, 6.66%, 4.89%, and 9.78% respectively. It demonstrates the efficacy of this systematic study in identifying major carps.

Methods of local features extraction in person authentication task by face thermographic image

The paper presents a methods of image local features extraction research in relation to people authentication problem by face thermogram. As a part of the study, there were formed two datasets for methods training and testing: photographic images and face images in the long-wavelength infrared specter (LWIR) with various factors. The novelty of this study is due to the approach to collecting datasets to verify the accuracy of authentication methods. The dataset was collected with more realistic conditions that affect the quality of authentication, such as changing facial expressions, wearing glasses, medical masks, applying make-up/cosmetics, changing the lighting and temperature conditions of the environment, rotating the head. The methods core is based on the idea of constructing a vector of image features while reducing the dimension and highlighting the boundaries. Likewise, the methods of this group cope well with extracting features task on images and are widely used in the tasks of authentication by 2D face image, as well as in other computer vision tasks. In this paper, four classical methods of local feature extraction are considered: the method of locally binary templates, Gabor wavelets, scale-invariant feature transformation, and Weber’s local descriptor. The classifiers for the feature vectors comparison in this research are SVM and the simplest Perceptron — the basic methods of machine learning. As part of the study, a comparative analysis of each method was carried out in relation to the collected datasets. The methods were trained and tested on a collected face dataset of over 632,000 images of 152 people. As a result of the comparative analysis, it can be concluded that the method of local binary features demonstrates the best result among the considered methods for both types of data: for face thermograms (for SVM — 0,57, for Perceptron — 0,58), for photographic images (for SVM — 0,71, for Perceptron — 0,73). Furthermore, the SIFT method showed similar results: for face thermograms (for SVM — 0,58, for Perceptron — 0,55), for photographic images (for SVM — 0,72, for Perceptron — 0,74). Gabor filters and Weber local descriptor application demonstrate a low accuracy rate in the authentication task by both types of data. The results of the work can be used in access control and management systems to increase the fault tolerance of person authentication. The appliance of the considered methods are effective in the tasks such as processing thermograms for authentication a person by so-called “secondary” signs, for example, by the veins and vessels on face patterns, in cases of facial expressions and appearance changes.

Secure and efficient privacy protection system for medical records

The healthcare sector has witnessed robust growth in the realm of medical information and its application during the last two decades. Consequently, the universal availability of patient records using web-based technology has acquired great significance in providing quality healthcare services on a global scale. With paramount aspects such as medical records confidentiality, it is an important consideration of modern times to secure medical information like CT-scan, X-Ray, and MRI when transmitted across public networks. Combining watermarking and BioHashing in medical image protection provides the means to safely transmit data over the internet and enhance authentication. In this context, we present a BioHashing and watermarking-based technique capable of providing integrity, authenticity, and confidentiality to different medical images. At the sender side, first, the BioHashing method is used to generate the watermark which is then embedded in weber local descriptor excitation component images using discrete cosine transform. The proposed technique meets all the requirements of robustness and imperceptibility. The experimental and comparison results demonstrate that the proposed method is superior to existing methods.

Classification of Acute Lymphoblastic Leukemia through the Fusion of Local Descriptors

Leukemia is characterized by an abnormal proliferation of leukocytes in the bone marrow and blood, which is usually detected by pathologists using a microscope to examine a blood smear. Leukemia identification and diagnosis in advance are a trending topic in medical applications for decreasing the death toll of individuals with Acute Lymphoblastic Leukemia (ALL). It is critical to analyze the white blood cells for the identification of ALL for which the blood smear images are utilized. This paper discusses and presents a micro-pattern descriptor, called Local Directional Number Pattern along with Multi-scale Weber Local Descriptor for feature extraction task to determine cancerous and noncancerous blood cells. A balanced dataset with 260 blood smear images from the ALL-IDB2 dataset was used as training data. Consequently, a proposed model was constructed by applying different individual and combined feature extraction methods, and fed into the machine learning classifiers (Decision Tree, Ensemble, K-Nearest Neighbors, Naïve Bayes, and Random Forest) to determine cancerous and noncancerous blood cells. Experimental results indicate that the developed feature fusion technique assured a reasonable performance compared to other existing works with a testing average accuracy of 97.69 ± 1.83% using Ensemble classifier.

A comparative study of shallow learning and deep transfer learning techniques for accurate fingerprints vitality detection

• Deep Transfer Learning architectures are compared against shallow learning image descriptors under the same conditions. • Deep transfer learning for fingerprint liveness detection is a viable way. • XAI shows that deep transfer learning extracts complex nonlinear patterns able to discern minutiae for liveness detection. This work inspects deep learning architectures and shallow learning techniques to determine whether the image of a fingerprint is real (Live) or not (Fake). It is known that Deep Learning techniques deliver, in general, good accuracies being able to automatically extract relevant patterns, at the same time, it is also known that these algorithms require large amounts of data. For this reason, transfer learning aims to transfer the knowledge learnt over a huge dataset to a new, smaller dataset. In this work, because of the limited size of the LivDet2019 dataset, three well known deep learning architectures such as Inception V3, ResNet50 and NASNet Large have been modified to perform transfer learning from the huge imagenet dataset to the smaller LivDet2019. The hypothesis at the very basis of this work is that the deep learning architectures trained on the huge imagenet dataset would learn to extract relevant patterns like lines, shapes, curves, jump between curves, etc… Later, the extracted knowledge, is fine-tuned on the LivDet2019 dataset to recognize fingerprint minuities as a non-linear combination of the previously learned patterns. For sake of completeness, state of art shallow learning image descriptors, finetuned for fingerprint recognition, such as Binarized Statistical Image Features (BSIF), Local Phase Quantization (LPQ) and Weber Local Descriptor (WLD) are used for extracting features from the LivDet2019 dataset. The classification on each of these extracted features is performed both with a linear and non-linear (gaussian) support vector machine. Accuracies suggest that both shallow learning and deep learning techniques are on par with the accuracies of reviewed works and thus transfer learning in fingerprint liveness detection is a feasible strategy that deserve attention and future research with the aim of increasing fingerprint detection accuracies.

Comparison of two-dimensional synthesized mammograms versus original digital mammograms: a quantitative assessment.

This study objectively evaluates the similarity between standard full-field digital mammograms and two-dimensional synthesized digital mammograms (2DSM) in a cohort of women undergoing mammography. Under an institutional review board-approved data collection protocol, we retrospectively analyzed 407 women with digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM) examinations performed from September 1, 2014, through February 29, 2016. Both FFDM and 2DSM images were used for the analysis, and 3216 available craniocaudal (CC) and mediolateral oblique (MLO) view mammograms altogether were included in the dataset. We analyzed the mammograms using a fully automated algorithm that computes 152 structural similarity, texture, and mammographic density-based features. We trained and developed two different global mammographic image feature analysis-based breast cancer detection schemes for 2DSM and FFDM images, respectively. The highest structural similarity features were obtained on the coarse Weber Local Descriptor differential excitation texture feature component computed on the CC view images (0.8770) and MLO view images (0.8889). Although the coarse structures are similar, the global mammographic image feature-based cancer detection scheme trained on 2DSM images outperformed the corresponding scheme trained on FFDM images, with area under a receiver operating characteristic curve (AUC) = 0.878 ± 0.034 and 0.756 ± 0.052, respectively. Consequently, further investigation is required to examine whether DBT can replace FFDM as a standalone technique, especially for the development of automated objective-based methods.

Palmvein Recognition Using Block-Based WLD Histogram of Gabor Feature Maps and Deep Neural Network With Bayesian Optimization

The demand on devices and systems empowered by biometric verification and identification mechanisms has been increasing in recent years as they have become a significant part of our lives. Palm vein biometric is an emerging technology that has drawn considerable attention from researchers and scientists over the last decade. In the present work, a novel feature extraction methodology named GPWLD combing the Gabor features with positional Weber's local descriptor (PWLD) features is proposed. WLD is a highly representative micro-pattern descriptor that performs well against noise and illumination changes in images. However, it lacks the ability to capture the vein pattern features at different orientations. Moreover, its descriptor packs the local information content into a single histogram that does not take the spatial locality of micro-patterns into consideration. To solve these two issues, firstly, the palm vein image is passed through Gabor filter with different orientations to capture the salient rotational features found in the output feature maps. Secondly, the spatiality is achieved by uniformly dividing each feature map into several blocks. Next, Weber's law feature descriptor (WLD) histogram is computed for each block in every feature map. Finally, these histograms are concatenated to compose the final feature vector. Due to the high dimensionality of the final feature vector, Principal component analysis (PCA) algorithm is utilized for feature size reduction. In the classification stage, a deep neural network (DNN) comprising an optimized stacked autoencoder (SAE) with Bayesian optimization and a softmax layer is used. Optimization of the SAE is carried out by using Bayesian optimization to find the optimal SAE structure and the options of the training algorithm. The Experimental results verify the discriminative power of the extracted features and the accuracy of the proposed DNN. For both Identification and verification experiments, the proposed method attains higher identification rate and lower EER than state-of-the-art methods.

Pedestrian Detection Using Quaternion Gradient Based Weber Local Descriptor

In the past decades, pedestrian detection has attracted more attention in many practical applications. In this paper, a novel pedestrian detection method using Quaternion Gradient based Weber Local Descriptor (QGWLD) is proposed. Unlike many other local pedestrian detectors that only extracted features from the gray-scale image, which ignored the color information, a new powerful and robust local pedestrian detector is developed, which integrates the advantages of both the color and texture information and can be used to address the pedestrian detection problem well. As we know, the quaternion can entirely characterize a color object well and the WLD feature consisting of the gradient orientation and differential excitation has acquired a good performance for pedestrian detection. Therefore, combining the WLD feature with the quaternion representation, the QGWLD pedestrian detector is presented. Firstly, the quaternion gradient representation is performed on the color image in the sliding window, and then the Weber Local Descriptor (WLD) is extracted over the quaternion gradient feature map. After that, the QGWLD histogram is constructed to characterize the sliding window. Experimental results on INRIA and PennFudanPed pedestrian databases validate the effectiveness of the proposed QGWLD pedestrian detector. Comparing with the similar pedestrian detectors, the proposed QGWLD pedestrian detector performs better.

Moving Vehicle Detection and Classification Using Gaussian Mixture Model and Ensemble Deep Learning Technique

In recent decades, automatic vehicle classification plays a vital role in intelligent transportation systems and visual traffic surveillance systems. Especially in countries that imposed a lockdown (mobility restrictions help reduce the spread of COVID‐19), it becomes important to curtail the movement of vehicles as much as possible. For an effective visual traffic surveillance system, it is essential to detect vehicles from the images and classify the vehicles into different types (e.g., bus, car, and pickup truck). Most of the existing research studies focused only on maximizing the percentage of predictions, which have poor real‐time performance and consume more computing resources. To highlight the problems of classifying imbalanced data, a new technique is proposed in this research article for vehicle type classification. Initially, the data are collected from the Beijing Institute of Technology Vehicle Dataset and the MIOvision Traffic Camera Dataset. In addition, adaptive histogram equalization and the Gaussian mixture model are implemented for enhancing the quality of collected vehicle images and to detect vehicles from the denoised images. Then, the Steerable Pyramid Transform and the Weber Local Descriptor are employed to extract the feature vectors from the detected vehicles. Finally, the extracted features are given as the input to an ensemble deep learning technique for vehicle classification. In the simulation phase, the proposed ensemble deep learning technique obtained 99.13% and 99.28% of classification accuracy on the MIOvision Traffic Camera Dataset and the Beijing Institute of Technology Vehicle Dataset. The obtained results are effective compared to the standard existing benchmark techniques on both datasets.

Weber local descriptor for image analysis and recognition: a survey

Weber local descriptor (WLD) is applied for addressing the challenges in image/pattern problems, especially in computer vision and pattern recognition domains. In this paper, we review literature on theories and applications of WLD. Using WLD, we address the different challenges of image analysis and recognition features with respect to illumination changes, contrast differences, and geometrical transformations like rotation, scaling, translation, and mirroring. Further, the role of the classifiers and experimental protocols used in the different applications are discussed. Applications include texture classification, medical imaging, agricultural safety, fingerprint analysis, forgery analysis, and face recognition.

A comparative study of handcrafted local texture descriptors for fingerprint liveness detection under real world scenarios

Authentication using fingerprints is widely deployed in various applications to ensure a secure and efficient method for access control. However, fingerprint recognition systems can be deceived by spoofing attacks. Therefore, it is necessary to ensure the security of fingerprint-based recognition system using liveness detection. The work presented in this paper evaluates the potential of various handcrafted texture features under cross-dataset, cross-sensor, cross-material, unknown-material, and combined datasets experimental scenarios. We have considered Binarized Statistical Image Features (BSIF), Local Phase Quantization (LPQ), Weber Local Descriptor (WLD), Local Contrast Phase Descriptor (LCPD), and Rotation Invariant Co-occurrence among adjacent Local Binary Pattern (RicLBP) for liveness detection of fingerprint images. The performance of these descriptors against novel spoof materials, different sensors, and different acquisition environments reflect their robustness under real world attack scenarios. The experimental evaluations are performed on LivDet 2011, 2013, and 2015 databases using Support Vector Machine (SVM) classifier. The experimental evaluation shows that LCPD and WLD are the most effective descriptors for liveness detection under diverse testing conditions. The comparative performance evaluation of these handcrafted texture features with learning based features also indicate their effectiveness in real world attack scenarios. Experimental evaluation using the combination of best performing LCPD and WLD features further improve the performance of fingerprint liveness detection. The experimental outcome of the current research clearly indicates the superiority of handcrafted local texture descriptor in the real world presentation attack scenarios. Also, it is advantageous to use local texture descriptor as they provide a simple and faster approach for fingerprint liveness detection in real world applications of fingerprint recognition systems.