The performance study of facial expression recognition via sparse representation

Facial expressions play important role in human communication. The understanding of facial expression is a basic requirement in the development of next generation human computer interaction systems. Researches show that the intrinsic facial features always hide in low dimensional facial subspaces. This paper presents facial parts based facial expression recognition system with sparse representation classifier. Sparse representation classifier exploits sparse representation to select face features and classify facial expressions. The sparse solution is obtained by solving l¹ -norm minimization problem with constraint of linear combination equation. Experimental results show that sparse representation is efficient for facial expression recognition and sparse representation classifier obtain much higher recognition accuracies than other compared methods.

A new method classifying power quality disturbances (PQD) based on random matrix transform (RMT) and sparse representation classification (SRC) by L1-minimization is presented. First, the PQD signals are characterized by random matrix lower-dimensional projection based on compressive sensing theory. Then, every test sample from feature vectors is represented as a sparse linear combination of training samples. The PQD type assign to the object class that minimizes the residual between test sample and its sparse representation by solving L1-minimization problem. RMT feature extraction method is extremely efficient to generate and independent of the training dataset. Compared with support vector machine (SVM), the SRC algorithm needs neither training process nor combination of two-class classifiers for multiclass classification. Simulation results show that the proposed feature extraction and classification method has high classification correct ratio in strong noise condition.

Aiming at the problems of traditional sparse representation algorithms that has a large amount of calculation and low recognition rate under the condition of small samples, a sparse representation classification algorithm (PCA-SRC) combined with principal component feature extraction is proposed. The algorithm can maintain the manifold structure of the finger vein space, solve the singularity problem of the characteristic equation matrix in small sample image recognition. Principal component analysis (PCA) is used to reduce the dimension of the feature matrix to eliminate redundancy. Construct an over-complete dictionary of sparse representation, and design a classifier based on sparse representation to get the classification results. The finger vein feature matching experiment is carried out using the self-built finger vein data set, and the algorithm proposed in this paper is compared with the traditional algorithm. The results show that the recognition rate of the four algorithms can reach more than 94%. The fusion of PCA and SRC speeds up the recognition speed. The recognition rate is higher than the traditional algorithm under different numbers of training samples, and the best recognition rate is 100%. The algorithm has high finger vein recognition rate and low dependence on the training sample set, which provides a new idea for the realization of finger vein recognition.

Based on multiple maximum scatter difference discrimination Dictionary learning, a novel face recognition algorithm is proposed. Dictionary used for sparse coding plays a key role in sparse representation classification. In this paper, a multiple maximum scatter difference discriminated criterion is used for dictionary learning. During the process of dictionary learning, the multiple maximum scatter difference computes its discriminated vectors from both the range of the between class scatter matrix and the null space of the within-class scatter matrix. The proposed algorithm is theoretically elegant and easy to calculate. Extensive experimental studies conducted on the AR database and Extended Yale Database B in comparison with existing basic sparse representation and other classification methods, it shows that the performance is a little better than the original sparse representation methods with lower complexity.

Circuit breaker plays an important part in power system. Mechanical faults are the main reason of the malfunction of circuit breaker. In order to diagnose the mechanical faults of circuit breaker, in this paper, the Mel Frequency Cepstrum Coefficients (MFCC) of the closing sound signals of circuit breaker are extracted based on the characteristics of human hearing. Then the Kernel Principal Component Analysis (KPCA) algorithm is applied to reduce the dimension of MFCC. The dimensionality reduction results of MFCC are taken as the feature vectors of closing sound signals. Sparse Representation Classification (SRC) algorithm is used to recognize the feature vectors. Meanwhile, the concept of scatter in Linear Discriminant Analysis (LDA) is applied into the objective function of SRC to improve the performance of SRC. Experimental results show that the method proposed in this paper can identify the circuit breaker mechanical faults accurately. MFCC could reflect the difference information of various mechanical states properly. Compared with SRC, the improved SRC algorithm that takes the with-class scatter and between-class scatter of the representation coefficients of feature vectors into account has better recognition performance. The identification process could provide theoretical guidance for field applications.

We proposed a facial motion tracking and expression recognition system based on video data. By a 3D deformable facial model, the online statistical model (OSM) and cylinder head model (CHM) were combined to track 3D facial motion in the framework of particle filtering. For facial expression recognition, a fast and efficient algorithm and a robust and precise algorithm were developed. With the first, facial animation and facial expression were retrieved sequentially. After that facial animation was obtained, facial expression was recognized by static facial expression knowledge learned from anatomical analysis. With the second, facial animation and facial expression were simultaneously retrieved to increase the reliability and robustness with noisy input data. Facial expression was recognized by fusing static and dynamic facial expression knowledge, the latter of which was learned by training a multi-class expressional Markov process using a video database. The experiments showed that facial motion tracking by OSM+CHM is more pose robust than that by OSM, and the facial expression score of the robust and precise algorithm is higher than those of other state-of-the-art facial expression recognition methods.

Spectrum analysis can quickly extract and analyze frequency domain features of signal, and it has been widely applied in fields of image processing, noise processing and signal processing. Fast Fourier transform (FFT) is fast and efficient, because it can efficiently decrease complexity of discrete Fourier transform. As a consequence, FFT is a very good method for image frequency spectrum analysis. In this paper, we propose to consolidate frequency domain representation by sparse representation (SR) and collaborative representation classification (CRC) which has excellent performance in comparison with general sparse representation-associated classification algorithms. Our proposed novel method has three main phases. The first phase utilizes FFT to extract frequency domain features of original images, which are complementary with representations of the original images. The second phase of our proposed novel method exploits CRC or SR to obtain scores of original images and obtained features, respectively. The third phase integrates the scores of original images and obtained features and uses them to classify images. The major contribution of the proposed method is that it is usually more robust than methods using only FFT, CRC or state-of-art method CIRLRC for image classification. The experiments of image classification demonstrate that the simultaneous use of FFT and CRC or sparse representation classification has high accuracy on image recognition.

Identifying glass defects through machine visual has a vital importance for the efficient production of high quality glass. In this paper, a method based on the combination of Non-negative Matrix Factorization (NMF) and Sparse Representation Classification (SRC) was proposed for the identification of glass defects. According to the properties of glass defect image, NMF algorithm is used to decompose a defect image into one base image and another weighted coefficient matrix, so the defect image is characterized by the coefficient matrix. Then, SRC algorithm is used to classify glass defects. Simulation results show that, with NMF and SRC, glass defects images could be effectively identified.

Facial expressions recognition and synthesis are important research fields to study how human beings reflect to environments in affective computing. With the rapid development of mathematical theory on multivariate statistics and multi-media technology especially image processing, facial expressions recognition researchers have achieved many useful results. Recently studies show that approaches to facial modeling and expressions recognition and synthesis analysis could be adapted to control security or even real-time health monitoring in the real world. Similarity, how to achieve facial expressions recognition and synthesis for independent-free mechanism is a central design in general. Based on the cognitive analysis of independent user's affective facial recognition researches we proposed an emotions composition model to dope out what are the user's new affective facial expressions. At this point, principal component, cluster and discriminate analysis were applied to show and verify independent user's affective expressions can be composited for synthesis by basic facial expressions such as happy, neutral and unhappy. Experiments were conducted to prove our models to be very significant.

In this paper, a novel facial expression recognition method based on sparse representation is proposed. Most contemporary facial expression recognition systems suffer from limited ability to handle image nuisances such as low resolution and noise. Especially for low intensity expression, most of the existing training methods have quite low recognition rates. Motivated by sparse representation, the problem can be solved by finding sparse coefficients of the test image by the whole training set. Deriving an effective facial representation from original face images is a vital step for successful facial expression recognition. We evaluate facial representation based on weighted local binary patterns, and Fisher separation criterion is used to calculate the weighs of patches. A multi-layer sparse representation framework is proposed for multi-intensity facial expression recognition, especially for low-intensity expressions and noisy expressions in reality, which is a critical problem but seldom addressed in the existing works. To this end, several experiments based on low-resolution and multi-intensity expressions are carried out. Promising results on publicly available databases demonstrate the potential of the proposed approach.

Semi-supervised two phase test sample sparse representation classifier

This paper proposes a novel vehicle-type classifier named SRCVT that uses video data collected from video detection units. The SRCVT uses the sparse representation classifier (SRC) technique without the requirement of an additional training procedure to construct the classification model. It classifies preceding vehicles directly from the testing samples’ sparse representation, without the need for explicit model selection. The SRCVT consists of four steps: data preparation, principal component analysis transformation, realization, and classification output. The classifier has been compared with the traditional method of using a supported vector machine. The results show that the SRCVT is more promising for vehicle-type classification in terms of classification accuracy and ease of use.

Hyperspectral imagery (HSI) consists of hundred or thousand of spectral bands and provides a wealth of spectral information. Although several parametric and non-parametric classifiers have been built with the purpose of efficiently and fully utilizing the spectral information in HSI, few of them are designed to exploit the underlying sparsity in HSI. In recent work, a joint sparsity model (JSM) based on the sparse representation theory was developed for HSI classification. In JSM, contextual information of HSI was exploited, where a rectangular window is employed to select neighboring pixels of a test pixel with the goal of providing spatial context to traditional per-pixel spectral classification. In this work, we propose a region growing approach to select the neighboring pixels of a test sample instead of the rectangular window and hence further improve the performance of such sparse representation classifiers. Experimental results with two different types of real-world hyperspectral datasets are reported to quantify the efficacy of the proposed approach.

In this paper, a new method for facial expression classification is proposed, which uses the histograms of oriented gradients (HOG) algorithm to extract facial expression features and the sparse representation classifier (SRC) to classify facial expressions with a large variation of poses. The HOG algorithm was selected due to its effectiveness in picking up both local and global facial expression features in different orientations and scales, and the SRC was chosen because of its proven effectiveness in face recognition. A novelty of the proposed approach is that given a facial image for classification, its pose is determined first to select a pose-dependent dictionary for the SRC procedure. The paper also discusses ways of selecting parameters for improving the effectiveness of the HOG algorithm. The proposed method was applied to two multi-pose facial expression databases and satisfactory results were obtained for the majority of facial expressions under various poses.

Multivariate classification techniques have been widely applied to decode brain states using functional magnetic resonance imaging (fMRI). Due to variabilities in fMRI data and the limitation of the collection of human fMRI data, it is not easy to train an efficient and robust supervised-learning classifier for fMRI data. Among various classification techniques, sparse representation classifier (SRC) exhibits a state-of-the-art classification performance in image classification. However, SRC has rarely been applied to fMRI-based decoding. This study aimed to improve SRC using unlabeled testing samples to allow it to be effectively applied to fMRI-based decoding. We proposed a semisupervised-learning SRC with an average coefficient (semiSRC-AVE) method that performed the classification using the average coefficient of each class instead of the reconstruction error and selectively updated the training dataset using new testing data with high confidence to improve the performance of SRC. Simulated and real fMRI experiments were performed to investigate the feasibility and robustness of semiSRC-AVE. The results of the simulated and real fMRI experiments showed that semiSRC-AVE significantly outperformed supervised learning SRC with an average coefficient (SRC-AVE) method and showed better performance than the other three semisupervised learning methods.