Voice Pathology Detection Using Multiresolution Technique

Simple cells Gabor wavelet transform and human visual system in the visual stimulus response very similar. It has the good characteristics of the local space in the extraction of target and frequency domain information. Although the Gabor wavelet does not of itself constitute orthogonal basis, but in the specific parameters can form a tight frame. Gabor wavelet is sensitive to the image edge, can provide good direction and scale selection characteristics, but also insensitive to illumination changes, can provide the illumination change good adaptability. These features make Gabor wavelet is widely used in visual information understanding. The two-dimensional Gabor wavelet transform is an important tool for signal analysis and processing in frequency domain in, the coefficient of wavelet transform with the visual characteristics and good biology background, so it is widely used in image processing, pattern recognition and other fields.

Human age classification via face images becoming an interesting research area because of potential applications in the field of computer vision such as Age Specific Human Computer Interaction (ASHCI), biometrics, security and surveillance, etc. In this paper, a novel method for human age classification using facial skin analysis for aging feature extraction and Multi-class Support Vector Machine (M-SVM) for age classification is proposed to classify the face images into four age groups. Facial skin analysis consists of skin texture analysis and wrinkle analysis. Gabor wavelet is used to analyze the facial skin textural changes with age progression. Wrinkle analysis detects the wrinkle density changes at particular regions on face image with age progression. The performance evaluation of proposed age classification system is carried out by using face images from PAL face database. In this paper, the performance of M-SVM classifier is compared with the performance of Artificial Neural Network (ANN) classifier for the task of human age classification using Gabor wavelet and wrinkle analysis. The result analysis concludes that the best age classification accuracy of 93.61% is achieved by using proposed age classification system and M-SVM is an efficient classifier than the ANN classifier for the task of human age classification in combination with Gabor wavelet and wrinkle analysis.

An acoustic analysis of pathological voice and its application to the evaluation of laryngeal pathology

This paper proposes a method for recognizing human identity using gait features based on Gabor wavelets and modified gait energy images (GEIs). Identity recognition by gait generally involves gait representation, extraction, and classification. In this work, a modified GEI convolved with an ensemble of Gabor wavelets is proposed as a gait feature. Principal component analysis is then used to project the Gabor-wavelet-based gait features into a lower-dimension feature space for subsequent classification. Finally, support vector machine classifiers based on a radial basis function kernel are trained and utilized to recognize human identity. The major contributions of this paper are as follows: (1) the consideration of the shadow effect to yield a more complete segmentation of gait silhouettes; (2) the utilization of motion estimation to track people when walkers overlap; and (3) the derivation of modified GEIs to extract more useful gait information. Extensive performance evaluation shows a great improvement of recognition accuracy due to the use of shadow removal, motion estimation, and gait representation using the modified GEIs and Gabor wavelets.

Face detection is the first step in the face recognition system. The Neural network as well as Gabor wavelet based face detection is proposed in this paper. The proposed system applies neural network algorithm to make the slanting face upright and Gabor wavelet is used to extract the invariable features from the selected window. The principal component analysis is applied to identify the person from the data base. The Proposed system gives very high detection efficiency with low number of false alarms. We have shown the results on different test sets with different degrees of variability of the face patterns. In this paper, we present a new approach for determining the orientation of face in the selected window and then use this information to rotate the face upright

This paper presents an innovative investigation on prototyping a digital twin (DT) as the platform for human-robot interactive welding and welder behavior analysis. This human-robot interaction (HRI) working style helps to enhance human users' operational productivity and comfort; while data-driven welder behavior analysis benefits to further novice welder training. This HRI system includes three modules: 1) a human user who demonstrates the welding operations offsite with her/his operations recorded by the motion-tracked handles; 2) a robot that executes the demonstrated welding operations to complete the physical welding tasks onsite; 3) a DT system that is developed based on virtual reality (VR) as a digital replica of the physical human-robot interactive welding environment. The DT system bridges a human user and robot through a bi-directional information flow: a) transmitting demonstrated welding operations in VR to the robot in the physical environment; b) displaying the physical welding scenes to human users in VR. Compared to existing DT systems reported in the literatures, the developed one provides better capability in engaging human users in interacting with welding scenes, through an augmented VR. To verify the effectiveness, six welders, skilled with certain manual welding training and unskilled without any training, tested the system by completing the same welding job; three skilled welders produce satisfied welded workpieces, while the other three unskilled do not. A data-driven approach as a combination of fast Fourier transform (FFT), principal component analysis (PCA), and support vector machine (SVM) is developed to analyze their behaviors. Given an operation sequence, i.e., motion speed sequence of the welding torch, frequency features are firstly extracted by FFT and then reduced in dimension through PCA, which are finally routed into SVM for classification. The trained model demonstrates a 94.44% classification accuracy in the testing dataset. The successful pattern recognition in skilled welder operations should benefit to accelerate novice welder training.

Automatic voice pathology detection and classification systems effectively contribute to the assessment of voice disorders, enabling the early detection of voice pathologies and the diagnosis of the type of pathology from which patients suffer. This paper concentrates on developing an accurate and robust feature extraction for detecting and classifying voice pathologies by investigating different frequency bands using autocorrelation and entropy. We extracted maximum peak values and their corresponding lag values from each frame of a voiced signal by using autocorrelation as features to detect and classify pathological samples. We also extracted the entropy for each frame of the voice signal after we normalized its values to be used as the features. These features were investigated in distinct frequency bands to assess the contribution of each band to the detection and classification processes. Various samples of the sustained vowel /a/ for both normal and pathological voices were extracted from three different databases in English, German, and Arabic. A support vector machine was used as a classifier. We also performed u-Tests to investigate if there is a significant difference between the means of the normal and pathological samples. The best achieved accuracies in both detection and classification varied depending on the used band, method, and database. The most contributive bands in both detection and classification were between 1000 and 8000 Hz. The highest obtained accuracies in the case of detection were 99.69%, 92.79%, and 99.79% for Massachusetts eye and ear infirmary (MEEI), Saarbrücken voice database (SVD), and Arabic voice pathology database (AVPD), respectively. However, the highest achieved accuracies for classification were 99.54%, 99.53%, and 96.02% for MEEI, SVD, and AVPD, correspondingly, using the combined feature.

Automatic voice pathology detection and classification using vocal tract area irregularity

Linear projection for reducing data dimensionality is a common practice in various data processing applications. Among the existing projection methods, Principal Component Analysis (PCA) is arguably the most popular one. Standard PCA used in image preprocessing pursues the projection directions by minimizing the reconstruction error in a least square sense. However, since PCA does not adapt to the data or any specific domains, it may lead to severe loss of certain discriminative features during the projection, and damage the performance of either human perception (e.g. stimulus in the visual cortex, as modeled by Gabor wavelets), or machine perceptions (e.g. recognizing the images based on a certain type of visual features), or both. In this paper, we propose a novel Perception Preserving Projections (PPP) method to preserve the information for specific perception systems. In particular, PPP incorporates domain-specific feature extractor into the standard PCA formulation for the projection learning procedure. This enables PPP to make more sensible projections for feature based perception systems while retaining the simplicity and unsupervised manner of PCA. In experimental studies, PPP shows clear effectiveness and improvement over PCA in terms of two performance metrics: feature extraction deviation and the pattern recognition accuracy.

Chinese painting is famous for its special painting materials, techniques and final artistic effects. However, there also have been many fake paintings. These fake paintings are usually produced by using modern high-resolution scanning and printing techniques, making it challenging to identify fake paintings through human vision. To solve this tough problem, we propose a method for pigment classification and recognition based on hyperspectral imaging technology in this paper. Firstly, a video with a hyperspectral camera is used to scan Chinese paintings with spectral frequencies ranging from 400 to 900 nm. Subsequently, spectral and spatial features are extracted through principal component analysis and convolutional neural networks, respectively. Finally, the two functions are identified, and the feature set is entered into a support vector machine for classification. All Chinese paint samples come from Chinese local painting organizations. The experimental results show that the effectiveness of the method is 84.6%, which is significantly higher than other methods where only spectral or spatial features are used.

This chapter outlines a typical workflow for micraorray data analysis. It aims at explaining the background of the methods as this is necessary for deciding upon a specific numerical method to use and for understanding and interpreting the outcomes of the analyses. We focus on error handling, various steps during preprocessing (clipping, imputing missing values, normalization, and transformation of data), statistic tests for variable selection and the use of multiple hypothesis testing procedures, various metrics and clustering algorithms for hierarchical clustering, principles, and results from principal components analysis and discriminant analysis, partitioning, self-organizing map, K-nearest neighbor classifier, and the use of a neural network and a support vector machine for classification.

A novel Gabor-Kernel face recognition method is proposed in this paper. This involves convolving a face image with a series of Gabor wavelets at different scales, locations, and orientations and extracting features from resulting Gabor filtered images. kernel discriminant analysis (KDDA) is then applied to the feature vectors for dimension reduction as well as class separability enhancement. A database of 600 frontal-view face images from the FERET face database is used to test the method. Experimental results demonstrate the advantage of KDDA over other Kernel methods such as kernel principal component analysis (KPCA) and general discriminant analysis (GDA). Significant improvements are also observed when features are extracted from Gabor filtered images instead of the original images. A 94% accuracy has been observed for the novel Gabor + KDDA method on the FERET database using a simple classifier, which could be further improved by employing a more complex classifier and distance measurer.

This paper presents a novel Gabor-based kernel Principal Component Analysis (PCA) method by integrating the Gabor wavelet representation of face images and the kernel PCA method for face recognition. Gabor wavelets first derive desirable facial features characterized by spatial frequency, spatial locality, and orientation selectivity to cope with the variations due to illumination and facial expression changes. The kernel PCA method is then extended to include fractional power polynomial models for enhanced face recognition performance. A fractional power polynomial, however, does not necessarily define a kernel function, as it might not define a positive semidefinite Gram matrix. Note that the sigmoid kernels, one of the three classes of widely used kernel functions (polynomial kernels, Gaussian kernels, and sigmoid kernels), do not actually define a positive semidefinite Gram matrix either. Nevertheless, the sigmoid kernels have been successfully used in practice, such as in building support vector machines. In order to derive real kernel PCA features, we apply only those kernel PCA eigenvectors that are associated with positive eigenvalues. The feasibility of the Gabor-based kernel PCA method with fractional power polynomial models has been successfully tested on both frontal and pose-angled face recognition, using two data sets from the FERET database and the CMU PIE database, respectively. The FERET data set contains 600 frontal face images of 200 subjects, while the PIE data set consists of 680 images across five poses (left and right profiles, left and right half profiles, and frontal view) with two different facial expressions (neutral and smiling) of 68 subjects. The effectiveness of the Gabor-based kernel PCA method with fractional power polynomial models is shown in terms of both absolute performance indices and comparative performance against the PCA method, the kernel PCA method with polynomial kernels, the kernel PCA method with fractional power polynomial models, the Gabor wavelet-based PCA method, and the Gabor wavelet-based kernel PCA method with polynomial kernels.

New techniques for information extraction from multispectral data require physical modeling to understand the energy transfer at the atmosphere/surface interface and to develop appropriate inversion procedures, in combination with advanced processing techniques. A multi-step procedure is proposed in this work: the first step implies a binary decision about the second step to be applied in each case. If the pixel is considered as being a `pure' pixel, through a spectral/spatial classification procedure based on multiresolution techniques, then numerical inversion techniques, based on a multiple-scattering reflectance model, are used to extract parameters representing specific surface properties, which can only be defined for homogeneous pixels. If the pixel is considered from the first step as being a mixture of different elements, a linear unmixing approach is used to extract the amount of each component. For such heterogeneous pixels, effective values for the parameters are defined. Multiresolution techniques are applied to improve information extraction algorithms. The relation between spectral and spatial integration effects is discussed. Broad-band spectral integration is analyzed taking into account spatial integration over heterogeneous areas. The problem of the spatial scale is also considered, as the development of these techniques is closely related to the spatial/spectral resolution of the data. Applications of these algorithms to AVIRIS/TMS and Landsat TM/NOAA AVHRR data are an illustration of the capabilities and limits of such approaches.

A non-invasive cum robust voice pathology detection and classification architecture is proposed in the current manuscript. In place of the conventional feature-based machine learning techniques, a new architecture is proposed herein which initially performs deep learning-based filtering of the input voice signal, followed by a decision-level fusion of deep learning and a non-parametric learner. The efficacy of the proposed technique is verified by performing a comparative study with very recent work on the same dataset but based on different training algorithms.The proposed architecture has five different stages.The results are recorded in terms of nine (9) different classification score indices which are – mean average Precision, sensitivity, specificity, F1 score, accuracy, error, false-positive rate, Matthews Correlation Coefficient, and the Cohen’s Kappa index. The experimental results have shown that the use of machine learning classifier can get at most 96.12% accuracy, while the proposed technique achieved the highest accuracy of 99.14% in comparison to other techniques.