Hybrid Feature Descriptor Research Articles

Optimal multi-kernel SVM classifier with rotation, illumination and scale invariant hybrid DWT-Shearlet based GLCM feature descriptor and its application to face recognition

In computer vision, we must handle with the various structural aspects of image or video data. The texture is one of the most important aspects of this type of data, which is utilised to identify objects or regions of interest in an image. As imaging conditions change, textures inside actual images significantly change in brightness, contrast, size, and skew. To recognise textures in real-world images, a similarity measure that is invariant to these features must be used. Existing recognition techniques did not perform well due to issues such as illumination, scale, and subject rotation. To address this issue, invariant feature representation methods are being developed to generate features that are insensitive to such variations. In this paper, we proposed a robust hybrid feature descriptor and predicted the faces under illumination, scale, and pose variations using an optimum multi-kernel support vector machine. Additionally, the suggested robust hybrid feature descriptor is enhanced by combining a hybrid transform composed of discrete wavelet and discrete shearlet transforms with some image statistical textural data. The proposed face recognition system is implemented in MATLAB, and analysed using various parameters to show proposed methods improved performance as compared to the state of the art methods.

Development of a deep stacked ensemble with process based volatile memory forensics for platform independent malware detection and classification

Malware has become more complicated in its purpose and abilities over time, demanding continuous progress in detection and defense technologies. Malware designers use anti-analysis obfuscation techniques, including packing and encryption, to evade detection and hinder the analysis process. Current malware detection methods have shortcomings; thus, an alternative dynamic platform-independent scheme is proposed to extract harmful hardware impressions. This scheme includes extracting and converting a file from process memory dumps into an image. A combined structural and statistical image textural analysis is performed by designing a hybrid local and global feature descriptor. The hybrid feature descriptor helps to improve the data training ability of the proposed deep-stacked ensemble model by reducing input dimensions. A deep-stacked ensemble model is developed by combining prediction outputs from weak learners (CNNs) and feeding them into a meta-learner (MLP) as learning input. An explainable artificial intelligence-based approach is employed to interpret and validate the final results of the proposed scheme. Evaluations are conducted using three datasets: the publicly available Dumpware10 dataset, which contains 3686 samples from 10 different malware families; the publicly available CIC-MalMem-2022 dataset, which includes 2,916 samples from 15 different obfuscated malware families; and a real-world dataset, which contains 2375 samples of both malware and benign android apps. Experimental outcomes show that the proposed scheme achieved 99.1 % accuracy in analyzing Windows malware memory dumps, 94.3 % accuracy in analyzing Android malware memory dumps, and 99.8 % accuracy in analyzing Windows obfuscated malware memory dumps. The final results indicate that our vision-based system provides an excellent defense against malicious programs.

Identifying License Plates in Distorted Vehicle Images: Detecting Distorted Vehicle Licence Plates Using a Novel Preprocessing Methods With Hybrid Feature Descriptors

Intelligent transportation systems (ITSs) play a key role in many people’s lives with different aspects. Most of the ITS applications include a system for detecting license plates (LPs) in transportation vehicles. A new framework for such detection systems is introduced in this article. It includes a novel technique for preprocessing, extraction, and detection stages to identify LPs from distorted vehicle images. An efficient preprocessing method is developed in this study. An enhanced, contrast-limited adaptive histogram equalization method for filtering the unwanted LP features is proposed. At the features-extraction stage, strong hybrid features from extended local binary patterns with a median robust pattern descriptor and speeded-up robust feature descriptor are applied to extract complicated features from LP areas. Those hybrid features can enhance the useful information, and the detection system performed well under difficult scenarios. In the detection stage, the trained model by an extreme learning machine (ELM) classifier, with mean-shift algorithm, is used as a detector to decide output results. Performances of the proposed framework were compared with other classifiers using true- and false-positive rates. The system’s performance improvements by the proposed method were also compared with our previous methods and the existing detection methods in the literature. The experiments on an English car LP’s database and other language vehicle images showed that the proposed method made significant improvements to the accuracy and runtime speed for the detection system under difficult image conditions.

Satellite image matching and registration using affine transformation and hybrid feature descriptors

Image registration (IR) is an image processing technique to determine geometrical transformation that gives the most accurate match between reference and floating images. In existing IR work, the inliers ratio and outlier's ratios are equal. This reduces the image registration accuracy. So, to avoid the outlier's ratio and increase the inliers ratio, hybrid invariant local features descriptor is proposed. This feature descriptor consists of binary-robust-invariant-scalable-key point (BRISK), speed-up-robust-feature (SURF), and feature from accelerated segment test feature (FAST). The hybrid feature descriptor extracts the relevant features from the image. Then, the feature matching step finds the correct correspondences from the two sets of features. Also, affine transformation avoids the false feature matching points. An experimental analysis shows the inliers ratio and repeatability evaluation metrics performance of individual feature descriptor, combined feature descriptor and proposed feature descriptor. The proposed hybrid feature descriptor achieves inliers ratio of 1.913 and repeatability is 0.121.

Early detection of tuberculosis using hybrid feature descriptors and deep learning network.

To detect tuberculosis (TB) at an early stage by analyzing chest X-ray images using a deep neural network, and to evaluate the efficacy of proposed model by comparing it with existing studies. For the study, an open-source X-ray images were used. Dataset consisted of two types of images, i.e., standard and tuberculosis. Total number of images in the dataset was 4,200, among which, 3,500 were normal chest X-rays, and the remaining 700 X-ray images were of tuberculosis patients. The study proposed and simulated a deep learning prediction model for early TB diagnosis by combining deep features with hand-engineered features. Gabor filter and Canny edge detection method were applied to enhance the performance and reduce computation cost. The proposed model simulated two scenarios: without filter and edge detection techniques and only a pre-trained model with automatic feature extraction, and filter and edge detection techniques. The results achieved from both the models were 95.7% and 97.9%, respectively. The proposed study can assist in the detection if a radiologist is not available. Also, the model was tested with real-time images to examine the efficacy, and was better than other available models.

A Model for Fingerprint Liveness Detection Enabled by M-SSO Heuristic Algorithm Using Deep Learning Strategies

This paper plans to implement the benefit of deep hybrid learning for fingerprint liveness detection. The fingerprint image is subjected to background removal using Active contour. Further, the feature extraction is performed by the optimized Scale-Invariant Feature Transform (SIFT) and hybrid feature descriptor. New Modified Shark Smell Optimization (M-SSO) is used for developing optimized SIFT keypoints. The hybridization of the Local Directional Pattern (LDP) and Local Binary Pattern (LBP) is used as the feature pattern extraction. The classification phase combines Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN). The optimized SIFT keypoints are taken as input by RNN, and the patterns resulting from hybrid LDP and LBP are taken as input by CNN. The M-SSO optimizes the number of hidden neurons of both RNN and CNN to maximize classification accuracy. The proposed approach significantly improves the performance of FLD on different benchmark datasets over state-of-the-art models.

A Novel Hybrid Approach Based on Deep CNN Features to Detect Knee Osteoarthritis.

In the recent era, various diseases have severely affected the lifestyle of individuals, especially adults. Among these, bone diseases, including Knee Osteoarthritis (KOA), have a great impact on quality of life. KOA is a knee joint problem mainly produced due to decreased Articular Cartilage between femur and tibia bones, producing severe joint pain, effusion, joint movement constraints and gait anomalies. To address these issues, this study presents a novel KOA detection at early stages using deep learning-based feature extraction and classification. Firstly, the input X-ray images are preprocessed, and then the Region of Interest (ROI) is extracted through segmentation. Secondly, features are extracted from preprocessed X-ray images containing knee joint space width using hybrid feature descriptors such as Convolutional Neural Network (CNN) through Local Binary Patterns (LBP) and CNN using Histogram of oriented gradient (HOG). Low-level features are computed by HOG, while texture features are computed employing the LBP descriptor. Lastly, multi-class classifiers, that is, Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbour (KNN), are used for the classification of KOA according to the Kellgren–Lawrence (KL) system. The Kellgren–Lawrence system consists of Grade I, Grade II, Grade III, and Grade IV. Experimental evaluation is performed on various combinations of the proposed framework. The experimental results show that the HOG features descriptor provides approximately 97% accuracy for the early detection and classification of KOA for all four grades of KL.

Ensemble learning based automatic detection of tuberculosis in chest X-ray images using hybrid feature descriptors.

Tuberculosis (TB) remains one of the major health problems in modern times with a high mortality rate. While efforts are being made to make early diagnosis accessible and more reliable in high burden TB countries, digital chest radiography has become a popular source for this purpose. However, the screening process requires expert radiologists which may be a potential barrier in developing countries. A fully automatic computer-aided diagnosis system can reduce the need of trained personnel for early diagnosis of TB using chest X-ray images. In this paper, we have proposed a novel TB detection technique that combines hand-crafted features with deep features (convolutional neural network-based) through Ensemble Learning. Handcrafted features were extracted via Gabor Filter and deep features were extracted via pre-trained deep learning models. Two publicly available datasets namely (i) Montgomery and (ii) Shenzhen were used to evaluate the proposed system. The proposed methodology was validated with a k-fold cross-validation scheme. The area under receiver operating characteristics curves of 0.99 and 0.97 were achieved for Shenzhen and Montgomery datasets respectively which shows the superiority of the proposed scheme.

A hybrid feature descriptor with Jaya optimised least squares SVM for facial expression recognition

Facial expression recognition has been a long-standing problem in the field of computer vision. This paper proposes a new simple scheme for effective recognition of facial expressions based on a hybrid feature descriptor and an improved classifier. Inspired by the success of stationary wavelet transform in many computer vision tasks, stationary wavelet transform is first employed on the pre-processed face image. The pyramid of histograms of orientation gradient features is then computed from the low-frequency stationary wavelet transform coefficients to capture more prominent details from facial images. The key idea of this hybrid feature descriptor is to exploit both spatial and frequency domain features which at the same time are robust against illumination and noise. The relevant features are subsequently determined using linear discriminant analysis. A new least squares support vector machine parameter tuning strategy is proposed using a contemporary optimisation technique called Jaya optimisation for classification of facial expressions. Experimental evaluations are performed on Japanese female facial expression and the Extended Cohn–Kanade (CK+) datasets, and the results based on 5-fold stratified cross-validation test confirm the superiority of the proposed method over state-of-the-art approaches.

Automatic Recognition of Human Interaction via Hybrid Descriptors and Maximum Entropy Markov Model Using Depth Sensors.

Automatic identification of human interaction is a challenging task especially in dynamic environments with cluttered backgrounds from video sequences. Advancements in computer vision sensor technologies provide powerful effects in human interaction recognition (HIR) during routine daily life. In this paper, we propose a novel features extraction method which incorporates robust entropy optimization and an efficient Maximum Entropy Markov Model (MEMM) for HIR via multiple vision sensors. The main objectives of proposed methodology are: (1) to propose a hybrid of four novel features—i.e., spatio-temporal features, energy-based features, shape based angular and geometric features—and a motion-orthogonal histogram of oriented gradient (MO-HOG); (2) to encode hybrid feature descriptors using a codebook, a Gaussian mixture model (GMM) and fisher encoding; (3) to optimize the encoded feature using a cross entropy optimization function; (4) to apply a MEMM classification algorithm to examine empirical expectations and highest entropy, which measure pattern variances to achieve outperformed HIR accuracy results. Our system is tested over three well-known datasets: SBU Kinect interaction; UoL 3D social activity; UT-interaction datasets. Through wide experimentations, the proposed features extraction algorithm, along with cross entropy optimization, has achieved the average accuracy rate of 91.25% with SBU, 90.4% with UoL and 87.4% with UT-Interaction datasets. The proposed HIR system will be applicable to a wide variety of man–machine interfaces, such as public-place surveillance, future medical applications, virtual reality, fitness exercises and 3D interactive gaming.

Rapid Defect Detection for Spacecraft in Infrared Reconstructed Images Using Image Mosaic Technique

In order to satisfy the real-time and large scale requirement of spacecraft nondestructive testing using optical pulsed thermography, in this research, we propose a novel approach based on image mosaic technique which can create large scale or panoramic image mosaics from a set of ordered infrared reconstruction images with overlapping areas for defect detection. First, infrared reconstruction images are extracted from the original thermal video stream by the ICA method based on the idea of blind source signal processing. Then for this research’s special mosaic object, a fast and accurate registration scheme is proposed. Abundant scale rotation invariant feature points are quickly obtained by using the hybrid feature detector and descriptor. Moreover, the feature matching process is realized by applying two-way FLANN and MSAC, parameters of the geometric transformation matrix are estimated by MSAC, and image mosaic is realized according to the geometric transformation model. The experimental results convinced the validity and efficiency of the proposed method.

Determination of Color and Shape Features Based Image Retrieval with Hybrid Feature Descriptor Construction (HFDC)

Objectives: To implement a hybrid feature descriptor construction (HFDC) model to exercise the CBIR. Method/analysis: The model that combines color and shape features of visual content to produce a feature level fusion scheme is introduced. The RGB histogram, HSV histogram and the canny edge histogram features are extracted and fused to produce a hybrid feature vector. Then the determined feature vector through the fusion of the entire dataset is used to train the SVM using RBF kernel to retrieve relevant visual content through identifying the color distribution, and shape is focused here as the main objective. Since from the very beginning of the data usage to surf web information the classification of the similar related objects has been potentially provided a helpful contribution towards helping the users to identify and determine required knowledge from the large corpus of available digital information. Many algorithms and improvements have been in implementation, but the large quantity of available information provides complexity to these techniques to enhance computational hike. This feature level fusion contributes to reducing the overhead. Finding: The HFDC evolutions significantly contribute to achieving an accuracy of 84.60%. The experimental results have proven the efficiency of the HFDC by providing the maximum classification accuracy. Novelty: The results evidently show that (1) HDFC improve the performance by enhancing the feature level fusion process, (2) the fusion procedure produces increased solid and high indicative rendering and (3) by performing feature level fusion of data a core dictionary is provided for better CBIR performance. Improvement: In addition to color and shape feature fusion the texture features can also be combined to improve the performance significantly.Keywords: CBIR, HFDC, RGB, HSV, Canny

Emotion recognition from facial expressions using hybrid feature descriptors

Here, a hybrid feature descriptor-based method is proposed to recognise human emotions from their facial expressions. A combination of spatial bag of features (SBoFs) with spatial scale-invariant feature transform (SBoF-SSIFT), and SBoFs with spatial speeded up robust transform are utilised to improve the ability to recognise facial expressions. For classification of emotions, K-nearest neighbour and support vector machines (SVMs) with linear, polynomial, and radial basis function kernels are applied. SBoFs descriptor generates a fixed length feature vector for all sample images irrespective of their size. Spatial SIFT and SURF features are independent of scaling, rotation, translation, projective transforms, and partly to illumination changes. A modified form of bag of features (BoFs) is employed by involving feature's spatial information for facial emotion recognition. The proposed method differs from conventional methods that are used for simple object categorisation without using spatial information. Experiments have been performed on extended Cohn–Kanade (CK+) and Japanese female facial expression (JAFFE) data sets. SBoF-SSIFT with SVM resulted in a recognition accuracy of 98.5% on CK+ and 98.3% on JAFFE data set. Images are resized through selective pre-processing, thereby retaining only the information of interest and reducing computation time.

Hybrid feature descriptors to detect face spoof attacks

Hybrid feature descriptors to detect face spoof attacks

Hybrid feature descriptor and probabilistic neuro-fuzzy system for face recognition

PurposeThis paper aims to develop the Hybrid feature descriptor and probabilistic neuro-fuzzy system for attaining the high accuracy in face recognition system. In recent days, facial recognition (FR) systems play a vital part in several applications such as surveillance, access control and image understanding. Accordingly, various face recognition methods have been developed in the literature, but the applicability of these algorithms is restricted because of unsatisfied accuracy. So, the improvement of face recognition is significantly important for the current trend.Design/methodology/approachThis paper proposes a face recognition system through feature extraction and classification. The proposed model extracts the local and the global feature of the image. The local features of the image are extracted using the kernel based scale invariant feature transform (K-SIFT) model and the global features are extracted using the proposed m-Co-HOG model. (Co-HOG: co-occurrence histograms of oriented gradients) The proposed m-Co-HOG model has the properties of the Co-HOG algorithm. The feature vector database contains combined local and the global feature vectors derived using the K-SIFT model and the proposed m-Co-HOG algorithm. This paper proposes a probabilistic neuro-fuzzy classifier system for the finding the identity of the person from the extracted feature vector database.FindingsThe face images required for the simulation of the proposed work are taken from the CVL database. The simulation considers a total of 114 persons form the CVL database. From the results, it is evident that the proposed model has outperformed the existing models with an improved accuracy of 0.98. The false acceptance rate (FAR) and false rejection rate (FRR) values of the proposed model have a low value of 0.01.Originality/valueThis paper proposes a face recognition system with proposed m-Co-HOG vector and the hybrid neuro-fuzzy classifier. Feature extraction was based on the proposed m-Co-HOG vector for extracting the global features and the existing K-SIFT model for extracting the local features from the face images. The proposed m-Co-HOG vector utilizes the existing Co-HOG model for feature extraction, along with a new color gradient decomposition method. The major advantage of the proposed m-Co-HOG vector is that it utilizes the color features of the image along with other features during the histogram operation.

Build a Robust Learning Feature Descriptor by Using a New Image Visualization Method for Indoor Scenario Recognition.

In order to recognize indoor scenarios, we extract image features for detecting objects, however, computers can make some unexpected mistakes. After visualizing the histogram of oriented gradient (HOG) features, we find that the world through the eyes of a computer is indeed different from human eyes, which assists researchers to see the reasons that cause a computer to make errors. Additionally, according to the visualization, we notice that the HOG features can obtain rich texture information. However, a large amount of background interference is also introduced. In order to enhance the robustness of the HOG feature, we propose an improved method for suppressing the background interference. On the basis of the original HOG feature, we introduce a principal component analysis (PCA) to extract the principal components of the image colour information. Then, a new hybrid feature descriptor, which is named HOG–PCA (HOGP), is made by deeply fusing these two features. Finally, the HOGP is compared to the state-of-the-art HOG feature descriptor in four scenes under different illumination. In the simulation and experimental tests, the qualitative and quantitative assessments indicate that the visualizing images of the HOGP feature are close to the observation results obtained by human eyes, which is better than the original HOG feature for object detection. Furthermore, the runtime of our proposed algorithm is hardly increased in comparison to the classic HOG feature.

Hybridized Feature Descriptor (HFD) for Content Based Image Retrieval on Large Image Database

Objectives: The hybridized feature descriptor is constructed to describe the relevance between the query and database images in the database. The input query is in the form of text keywords, specifications, image properties, color/ texture patterns or image itself. Method: The layered approach has been used to design experimental model, which helps to match the image features one after one to prepare the final image ranking. The similarity factor is calculated by SVM based learning model. It can achieve very good results under the limited feature matching paradigm. Findings: The existing model is defeated by this model because of its hybrid feature descriptor solution, proposed by the amalgamation of the color and low ranked features computed with feature fitness validation. The performance has been evaluated by using various performance parameters like accuracy, ranking/index building time, library lookup time, precision, recall etc. Improvement: The proposed model has resulted in effective content based image retrieval system. The experimental result shows the efficiency and robustness of this model.

Statistical Texture and Normalized Discrete Cosine Transform-Based Automatic Soya Plant Foliar Infection Cataloguing

Soya beans are an important cash-crop, grown worldwide because of their use as a raw material in various industries involved in the production of sauces , mayonnaises, chocolates, baby-food, bakery, etc. Soya bean products are not only consu med by humans, but by pets too. They are also used as an alternative to fossil fuel in the form of bio-diesel. The research work presented in this paper highlights the problems associated with soya bean cultivation, and the reasons for yield loss in developing countries like India, C hina and others. In this paper, the colour image sensing and processing based infected lesion de tection method is proposed. Structural texture and normalized DCT-based feature descript ors for refined lesion histograms have been developed. Hybrid feature descriptors have been used as the input samples for four major soya plant foliar infections. The classification and testing accuracies are quite encouraging, and are above 89.9% and 92.3% respectively. Also, the results have been compared for only ST, ST-DCT, and ST-NDCT feature-based methods, and the use of STNDCT descriptors in cataloguing systems is suggested. Moreover, the method can classify four diseases, which creates confusion because of similar colour shades, and irregular and random shapes and sizes of lesions.