Robust Feature Extraction Technique Research Articles

Fusion of Features: A Technique to Improve Autism Spectrum Disorder Detection Using Brain MRI Images

Autism Spectrum Disorder (ASD) is a major incident neurological disorder. Medical practitioners use different diagnostic techniques such as Electroencephalogram (EEG) Analysis, Magnetic Resonance Imaging (MRI) analysis, and traditional Behavioral Analysis for ASD detection. However, diagnosis success largely depends on specialists' knowledge and remains seldom accessible to remote patients. To address this issue, recently, various machine learning (ML) approaches have been developed for ASD detection using brain MRI images. The performance of these approaches is often limited because of poor feature discrimination, inferior quality of features, high feature length, and poor correlation of features. Thus, there is a need for robust feature extraction and selection techniques to improve the performance of ASD detection. The proposed work demonstrates a fusion of three features, namely Gray Level Co-occurrence Matrix (GLCM) based holistic texture features, Local Binary Pattern (LBP) based local texture features, and Geometrical Features of the Corpus Callosum (GFCC) from brain MRI images. Further, a correlation-based feature selection technique is employed for the salient feature selection from the GLCM, LBP, and GFCC set to improve the feature quality. The effectiveness of the selected feature is evaluated using three ML classifiers such as K-Nearest neighbor (KNN), Support Vector Machine (SVM), and Classification Tree (CT). The proposed ASD detection scheme provides an accuracy of 95.86% with 10-fold cross-validation with a CT classifier. It is observed that the accuracy of the proposed system is improved by 11.32% over the recent GLCM-based ASD system. The correlation-based feature selection techniques minimize the recognition time by 34.95% over the ASD system without feature selection.

LPI Radar Detection Based on Deep Learning Approach with Periodic Autocorrelation Function.

In electronic warfare systems, detecting low-probability-of-intercept (LPI) radar signals poses a significant challenge due to the signal power being lower than the noise power. Techniques using statistical or deep learning models have been proposed for detecting low-power signals. However, as these methods overlook the inherent characteristics of radar signals, they possess limitations in radar signal detection performance. We introduce a deep learning-based detection model that capitalizes on the periodicity characteristic of radar signals. The periodic autocorrelation function (PACF) is an effective time-series data analysis method to capture the pulse repetition characteristic in the intercepted signal. Our detection model extracts radar signal features from PACF and then detects the signal using a neural network employing long short-term memory to effectively process time-series features. The simulation results show that our detection model outperforms existing deep learning-based models that use conventional autocorrelation function or spectrogram as an input. Furthermore, the robust feature extraction technique allows our proposed model to achieve high performance even with a shallow neural network architecture and provides a lighter model than existing models.

Multi-Classification of Electroencephalogram Epileptic Seizures Based on Robust Hybrid Feature Extraction Technique and Optimized Support Vector Machine Classifier

Multi-Classification of Electroencephalogram Epileptic Seizures Based on Robust Hybrid Feature Extraction Technique and Optimized Support Vector Machine Classifier

Robust locally linear embedding and its application in analogue circuit fault diagnosis

During long-term operation of analogue circuits, fault diagnosis is important for preventing the occurrence of hazards. However, noise often accompanies sampled signals and makes the task of fault diagnosis more difficult. Therefore, developing a robust feature extraction technique is an indispensable part of fault diagnosis. The locally linear embedding (LLE) algorithm has recently emerged as a promising technique for dimensional reduction and feature extraction because it preserves linear neighborhoods, and it is quite effective when there is a locally linear dependent structure embedded in fault data. However, LLE is sensitive to noise. Therefore, the maximum correntropy criterion is adopted to resist non-Gaussian noise by seeking the optimal weight coefficient, and a half-quadratic optimization procedure is introduced to address the objective function. Moreover, softmax regression is applied to locate faults. Finally, two typical analogue circuit systems are used to demonstrate the robustness of the modified algorithm to non-Gaussian noise. The experimental results show that the robust LLE algorithm can outperform LLE in the extraction of fault features when there is non-Gaussian noise in the fault signals, and the proposed fault diagnosis method has a better effect in locating faults compared with other feature extraction methods.

Defect Detection in Printed Circuit Boards Using Leaky-LeNet 5

Each electronic device includes printed circuit boards (PCBs), where defect detection is an important process to enhance the quality of PCB production. To accomplish error-free PCBs, the researchers and experts converted traditional manual inspections into automated systems. The manual inspection results are ineffective, where the non-defective PCBs are classified as defective PCBs. A subsequent study added a technique called LeNetwork-5 (LeNet-5) and speeded up robust feature extraction (SURF) techniques to identify defects. The existing method was unreliable, so further research was conducted in this area using Leaky techniques. Two objectives are achieved using SURF technique: (1) registration of the PCB to be checked against a reference PCB and (2) identification of feature points on the PCB helps to find missing components. Additionally, the Leaky LeNet-5 classifier is employed to classify the defects in PCBs. The proposed method achieved accuracy of 99.83%, sensitivity of 96.26%, specificity of 99.15%, and F1-Score of 98.45%.

A Preliminary Study of Robust Speech Feature Extraction Based on Maximizing the Probability of States in Deep Acoustic Models

This study proposes a novel robust speech feature extraction technique to improve speech recognition performance in noisy environments. This novel method exploits the information provided by the original acoustic model in the automatic speech recognition (ASR) system to learn a deep neural network that converts the original speech features. This deep neural network is trained to maximize the posterior accuracy of the state sequences of acoustic models with respect to the speech feature sequences. Compared with the robustness methods that retrain or adapt acoustic models, the new method has the advantages of less computation load and faster training. In the experiments conducted on the medium-vocabulary TIMIT database and task, the presented method provides lower word error rates than the unprocessed baseline and speech-enhancement-based techniques. These results indicate that the presented method is promising and worth further developing.

Optical Ultrastructure of Large Mammalian Hearts Recovers Discordant Alternans by In Silico Data Assimilation.

Understanding and predicting the mechanisms promoting the onset and sustainability of cardiac arrhythmias represent a primary concern in the scientific and medical communities still today. Despite the long-lasting effort in clinical and physico-mathematical research, a critical aspect to be fully characterized and unveiled is represented by spatiotemporal alternans patterns of cardiac excitation. The identification of discordant alternans and higher-order alternating rhythms by advanced data analyses as well as their prediction by reliable mathematical models represents a major avenue of research for a broad and multidisciplinary scientific community. Current limitations concern two primary aspects: 1) robust and general-purpose feature extraction techniques and 2) in silico data assimilation within reliable and predictive mathematical models. Here, we address both aspects. At first, we extend our previous works on Fourier transformation imaging (FFI), applying the technique to whole-ventricle fluorescence optical mapping. Overall, we identify complex spatial patterns of voltage alternans and characterize higher-order rhythms by a frequency-series analysis. Then, we integrate the optical ultrastructure obtained by FFI analysis within a fine-tuned electrophysiological mathematical model of the cardiac action potential. We build up a novel data assimilation procedure demonstrating its reliability in reproducing complex alternans patterns in two-dimensional computational domains. Finally, we prove that the FFI approach applied to both experimental and simulated signals recovers the same information, thus closing the loop between the experiment, data analysis, and numerical simulations.

A Robust Feature Extraction Technique for Breast Cancer Detection using Digital Mammograms based on Advanced GLCM Approach

INTRODUCTION: Breast cancer is the most hazardous disease among women worldwide. A simple, cost-effective, and efficient screening called mammographic imaging is used to find the breast abnormalities to detect breast cancer in the early stages so that the patient’s health can be improved.OBJECTIVES: The main challenge is to extract the features by using a novel technique called Advanced Gray-Level Co-occurrence Matrix (AGLCM) from pre-processed images and to classify the images using machine learning algorithms.METHODS: To achieve this, we proposed a four-step process: image acquisition, pre-processing, feature extraction, and classification. Initially, a pre-processing technique called Contrast Limited Advanced Histogram Equalization (CLAHE) is used to increase the contrast of images and the features are retrieved using AGLCM which extracts texture, intensity and shape-based features as these are important to identify the abnormality.RESULTS: In our framework, a classifier called eXtreme Gradient Boosting (XGBoost) is applied on mammograms and the results are compared with other classifiers such as Random Forest (RF), K-Nearest Neighbor (KNN), Artificial Neural Networks (ANN), and Support Vector Machine (SVM). The experiments are done on the Mammographic Image Analysis Society (MIAS) dataset.CONCLUSION: The outcome achieved with CLAHE+ AGLCM+ XGBoost classifier is better than the existing methods. In future, we experiment on large datasets and also concentrate on optimal features selection to increase the classification.

Automatic Speech Recognition Features Extraction Techniques: A Multi-criteria Comparison

Features extraction is an important step in Automatic Speech Recognition, which consists of determining the audio signal components that are useful for identifying linguistic content while removing background noise and irrelevant information. The main objective of features extraction is to identify the discriminative and robust features in the acoustic data. The derived feature vector should possess the characteristics of low dimensionality, long-time stability, non-sensitivity to noise, and no correlation with other features, which makes the application of a robust feature extraction technique a significant challenge for Automatic Speech Recognition. Many comparative studies have been carried out to compare different speech recognition feature extraction techniques, but none of them have evaluated the criteria to be considered when applying a feature extraction technique. The objective of this work is to answer some of the questions that may arise when considering which feature extraction techniques to apply, through a multi-criteria comparison of different features extraction techniques using the Weighted Scoring Method.

RETRACTED ARTICLE: Development of hand gesture recognition system using machine learning

Human computer interaction (HCI) systems are increasing due to the demand for non-intrusive methods for communicating with machines. In this research article, vision based hand gesture recognition (HGR) System has been proposed using machine learning. This proposed system consists of three stages: segmentation, feature extraction and classification. The developed system is to be trained and tested using Sebastian Marcel static hand posture database which is available online. Discrete wavelet transform (DWT) along with modified Speed Up Robust Feature extraction technique has been used to extract rotation and scale invariant key descriptors. Then Bag of Word technique is used to develop the fixed dimension input vector that is required for the support vector machine. The classification accuracy of class 2 and class 4 which corresponds to the ‘No’ and ‘grasp’ gesture has reached 98%. The overall classification accuracy of the HGR system using SVM classifier is 96.5% with a recognition time of 0.024 s. Due to fast recognition time, this system can be employed in real time gesture image recognition system. Our HGR system addresses the complex background problem and also improves the robustness of hand gesture recognition.

L1‐norm based discriminant manifold learning for multi‐label image classification

Recently, L1-norm based robust discriminant feature extraction technique has been attracted much attention in dimensionality reduction. However, most existing approaches solve the column vectors of the optimal projection matrix one by one with a greedy strategy. Moreover, they are not suitable for solving the multi-label image classification. To solve these problems, the authors give a model named L1-norm based discriminant manifold learning in this study. An iterative non-greedy algorithm is proposed to solve the objective and the obtained optimal projection matrix necessarily best optimise the corresponding trace ratio objective function, which is the essential criterion function for general supervised dimensionality reduction. They also analyse the convergence of the authors’ proposed algorithm in detail. Extensive experiments on some databases illustrate the effectiveness of their proposed method.

A Language Identification System using Hybrid Features and Back-Propagation Neural Network

Language Identification (LID) is accurate identification of the unknown language by comparison of speech biometrics of test speech sample and language models accumulated beforehand. This paper presents and encourages the use of hybrid robust feature extraction techniques for spoken language identification (LID) system. In the feature extraction stage, different techniques are applied individually such as Mel frequency cepstral coefficients (MFCCs), perceptual linear prediction features (PLP), relative perceptual linear prediction features (RASTA-PLP). Later, performance of our LID system based on several combinations of the different features (hybrid features) are investigated such as MFCC, PLP, combined with their 1st order derivatives, MFCC + RASTA-PLP, MFCC + SDC (Shifted delta cepstral coefficients). Language identification phase or classification utilizes feed forward back-propagation neural network (FFBPNN) and comparison is based on two learning algorithms: the Levenberg–Marquardt “trainlm” and the scaled conjugate gradient “trainscg”. A comparative analysis in terms of performance is done between different hybrid feature extraction techniques and their individual counterparts. Results clearly indicates that improved performance is obtained with hybrid features with “trainlm” learning algorithm as compared to their individual counterparts. The results are very promising with MFCC-RASTA-PLP hybrid feature extraction technique in comparison to the other hybrid feature extraction techniques with overall accuracy of 94.6% and a minimum test error rate of 0.10. The efficiency of proposed hybrid approaches is determined by simulating several experiments on a user defined language database of speech signals in the working platform of MATLAB.

A real-time approach for automatic defect detection from PCBs based on SURF features and morphological operations

This paper presents an automatic inspection approach for Printed Circuit Boards (PCBs) with accurate determination of the fault location and identification of the fault type. This approach depends on several digital image processing techniques including registration, filtering, foreground segmentation, mathematical morphological operations, subtraction, feature extraction, and component matching. The Speeded Up Robust Feature extraction (SURF) technique is used for two purposes: registration of the PCB to be checked to a reference PCB and detection of feature points of each missing component on the PCB that is localized from the subtraction process from the reference PCB. Operation is performed on the hue component of the color PCB images. A dictionary is first built for all possible components on the available PCBs with SURF feature descriptors, and hence if a missing item is detected on a PCB during the inspection process, the SURF feature descriptors for features extracted from the difference between the tested and reference PCBs at the position of the lost component are matched with those in the built dictionary or database. A distance metric is used in the matching process. The importance of the proposed approach lies in its ability to build a dictionary of feature descriptors for all possible components in a diversity of PCBs and its ability to localize and identify the missing components regardless of the PCB position, rotation, or type. All operations are formulated in a Graphical User Interface (GUI) using MATLAB environment.

Rapid speedup segment analysis based feature extraction for hand gesture recognition

The dependency on computers and machines have progressively increased in the past few years and hence human interaction with computers is one of the most actively researched area in science. Many Hand Gesture Recognition (HGR) systems have been developed and they continue to evolve, where in which the gesture interaction becomes smoother and smarter. Gesture recognition is usually implemented in three phases- gesture segmentation, feature extraction and gesture classification, and it’s important that the processes involved in these stages are chosen appropriately such that the misrecognition rate will be kept to a minimum. This paper has proposed a novel algorithm that combines 2D-Discrete Wavelet Transform along with Speed Up Robust Feature (SURF) extraction technique to achieve a robust HGR system that is rotation and scale invariant. The proposed method has achieved an overall classification accuracy of 96.9% with the Radial Basis Function Neural Network (RBFNN) classifier.

An Improved Illumination Normalization and Robust Feature Extraction Technique for Face Recognition Under Varying Illuminations

Invariant feature extraction under diverse illuminations is challenging for face recognition. Light intensity variations in face images are predominant in large-scale features. In existing techniques, such features are truncated to achieve illumination-invariant features. However, salient features are lost during small-scale feature extraction that affect performance. Thus, objective in proposed work is to attain improved illumination normalization where large-scale and small-scale feature information is efficiently extracted for face recognition. First, reflectance ratio and histogram equalization (RRHE)-based new illumination normalization framework is proposed in which illumination deviations are annulled. Then, histogram equalization is employed to enhance contrast of reflectance ratio image by adjusting pixel intensities. Then, robust feature extraction in discrete wavelet packet transform domain (RFDWPT) from RRHE images is performed using various orthogonal wavelets with distinct vanishing moments. Here, small-scale features (noise effect) of RRHE images are discarded and final feature vector is formed by appropriate small-scale and large-scale features. This results in illumination-normalized salient features for eigen space analysis where nearest neighbor classification is performed on compact size training and test features. Compared with other face recognition techniques under different illumination conditions, significant enhancement in recognition accuracy is achieved on benchmark databases such as Yale B, CMU-PIE, Yale and extended Yale B.

Principal component analysis based on block-norm minimization

Principal Component Analysis (PCA) has attracted considerable interest for years in the studies of image recognition. So far, several state-of-the-art PCA-based robust feature extraction techniques have been proposed, such as PCA-L1 and R1-PCA. Since those methods treat image by its transferred vector form, it leads to the loss of latent information carried by images and loses sight of the spatial structural details of image. To exploit these two kinds of information and improve robustness to outliers, we propose principal component analysis based on block-norm minimization (Block-PCA) which employs block-norm to measure the distance between an image and its reconstruction. Block-norm imposes L2-norm constrain on a local group of pixel blocks and uses L1-norm constrain among different groups. In the case where parts of an image are corrupted, Block-PCA can effectively depress the effect of corrupted blocks and make full use of the rest. In addition, we propose an alternative iterative algorithm to solve the Block-PCA model. Performance is evaluated on several datasets and the results are compared with those of other PCA-based methods.

Robust optimal sub-band wavelet cepstral coefficient method for speech recognition

The objective of this paper is to propose a robust feature extraction technique for speech recognition system which is insusceptible in the adverse environments. Efficacy of the speech recognition system depends on the feature extraction method. This paper proposes an auditory scale like filter banks using optimal sub-band tree structuring based on wavelet transform. The optimised wavelet filter banks along with energy, logarithmic, discrete cosine transform and cepstral mean normalisation blocks form a robust feature extraction method. This method is validated on a hidden Markov model (HMM)-based single Gaussian isolated word recognition system for additive white Gaussian noise, street and airport noises with different noise levels. Compared with Fourier transform-based methods such as mel-frequency cepstral coefficient (MFCC) and perceptual linear predictive (PLP) methods, the wavelet transform-based method yielded significant improvement across all the noise levels. The experiments also performed with higher dimensions of MFCC features including delta, acceleration features (MFCC_D_A). This study proves that the outcome of wavelet transform-based method gives an increased recognition accuracy of 13% over MFCC_D_A for non-stationary noises.

Entropy‐based feature extraction and classification of vibroarthographic signal using complete ensemble empirical mode decomposition with adaptive noise

Non-invasive methods accomplished by a computer aided diagnosis of knee-joint disorders provide an effective tool. The objective of this study is to analyse vibroarthographic (VAG) signals using non-linear signal processing technique. This study includes different entropy-based feature extraction techniques to attain highly distinguishable features. The authors proposed to use a non-linear method known as complete ensemble empirical mode decomposition with adaptive white noise to decompose the VAG signals into intrinsic mode functions (IMFs). Entropy-based features involving approximate entropy, sample entropy, Shannon entropy, Renyi entropy, Tsallis entropy and permutation entropy (PeEn) are computed from dominant IMFs and reconstructed VAG signals. These extracted features are given as input to the least squares support vector machine as a classifier. The results illustrated that PeEn performed better with respect to other entropies. PeEn gives a classification accuracy of 86.61% and Matthews correlation coefficient of 0.7082. The computational complexity of entropies was also analysed. Results inferred that PeEn has a computational complexity of O ( N ) provided a simple, robust and low computational feature extraction technique. Analysis of VAG signals using non-linear preprocessing and entropy-based features can provide highly distinguishable features for accurate detection of knee-joint disorders.

${L_{2,1}}$ -Norm Discriminant Manifold Learning

Recently, ${L_{1}}$ -norm-based robust discriminant feature extraction technique has been attracted much attention in dimensionality reduction and pattern recognition. However, it does not relate to the scatter matrix which well characterizes the geometric structure of data. In this paper, we propose a robust formulation of graph embedding framework for dimensionality reduction. In this robust framework, we use ${L_{2}}$ -norm to measure the distance along space dimension and ${L_{1}}$ -norm to sum overall data points. The proposed robust graph embedding framework retains the traditional framework’s desirable properties, such as rotational invariance and well geometric structure, and simultaneously suppresses outliers. Based on this framework, we develop a simple and robust feature extraction method, namely ${L_{2,1}}$ -norm-based discriminant locality preserving projections ( ${L_{2,1}}$ -DLPP) and provide an effective iterative algorithm to solve ${L_{2,1}}$ -DLPP. Extensive experiments in artificial data and three popular face databases illustrate the effectiveness of our proposed method.

AUTHENTICATION BASED IMAGE FORGERY DETECTION USING OPTIMIZED FEATURES IN JPEG IMAGES

With the current development in technology, image manipulation and particularly image splicing has been termed as a regular and established concern. The swift growth in commercial image editing programs and software for instance Adobe Photoshop has significantly elevated the number of forged, doctored and tampered images on a daily basis. This situation has resulted into extreme consequences, minimizing the authenticity and reliability of such images as well as creating untrue beliefs in a wide range of ideal-world relevance. The authenticity of a digital image suffers from severe threats due to the rise of powerful digital image editing tools that easily alter the image contents without leaving any visible traces of such changes. The splicing forgery can be done by copied a one/more region from source image and pasted into a target image to produce a composite image called spliced image. Therefore, this type of forgery is considered very challenging from tampering detection point of view. To make the matter worst some post-processing effects such as blurring, JPEG compression, rotation and scaling maybe introduced in the spliced image. In previous paper, we study found the problems in forgery detection in Jpg images. Robust feature extraction techniques used in block based copy move image forgery detection require a high computation time. There is a need for reduced computation time for detection schemes to be practical for use with large images and in real time environments. Utilization of GPU to compute the processes can highly parallelize the tasks involved to reduce computation time. Current CPU based algorithms that have been designed are not suitable to be directly adopted in a GPU based scheme. It must be determined how a parallel copy move image forgery detection scheme can be designed for use with a GPU. Digital images provide a new way to represent pictures and scenes that only film and a darkroom could supply before. In this research work, we implement the feature extraction using principle component analysis and optimization (ant colony optimization) algorithm to detect the forgery image in JPG images. In optimization approach to classify the features and match the training feature if training and testing features has matching then detect the forgery image in the jpg images. Evaluate the performance parameters PSNR (Peak Signal to Noise Ratio), Error rate Accuracy and compare the existing parameters i.e accuracy. Keywords- Image Forgery, Robust feature extraction, Ant colony Approach and Neural Network