Domain adaptive sparse representation-based classification

In this paper, we present a facial expression recognition method based on Gabor feature and sparse representation. Sparse Representation based Classification (SRC) has been widely used in computer vision and pattern recognition. And Gabor filter banks can be used to approximately model the signal processing in visual primary cortex. We believe that the nature of the attractive performance of SRC and Gabor feature lies in that they both followed the natures of signal perception of retina and information processing of cortex in human vision. Therefore, we combined the Gabor feature and SRC for facial expression recognition. The comparison experiments of proposed Gabor+SRC algorithm and straightforward SRC application are conducted on JAFFE database. And the experimental results showed the attractive performance of the proposed Gabor+SRC method.

Sparse representation based classification (SRC) has gained great success in image recognition. In this paper, we propose a generalized CRC method, essentially a SRC using Euler sparse representation, for image classification. To be specific, our CRC first maps the image into a complex space by Euler representation with a negligible effect for outliers and illumination, and then performs a complex SRC method. We also present a fast and efficient algorithm to solve Euler SRC subproblems. Extensive experimental results illustrate that our method outperforms traditional SRC methods and achieves better performance for image classification.

We propose a fast kernel sparse representation based classification (SRC) for undersampling problem, i.e., each class has very few training samples, in face recognition. The proposed algorithm exploits a nonlinear mapping to map the data from the original input space into a high-dimensional feature space. Then, it performs very fast sparse representation and classification of samples in this space. Similar to the typical SRC methods, the proposed approach is based on the L1 norm minimization, whose direct solution can be very time-consuming. In order to improve the computational efficiency, our method uses the coordinate descent method in the feature space, which can avoid directly solving the L1 norm minimization problem, and significantly expedites the computational procedure. Compared with other SRC methods based on the L1 norm minimization, our proposed method achieves very high computational efficiency, without significantly degrading the classification performance. Several experiments on popular face databases demonstrate that our method is a promising efficient kernel SRC based method.

This paper presents a method to perform sparse representation based classification (SRC) in a more accurate and efficient way. In this method, training data is first mapped into different feature spaces and multiple dictionaries are built by utilizing a Fisher discriminative based method. These dictionaries can be considered as efficient representations of the data which are then used in a multimodal SRC framework to classify test samples. In comparison to the original SRC method where only one modality of training space is utilized, the proposed method classifies test samples in a more accurate and efficient way. Experimental results from two different face datasets show that the proposed multimodal method has higher recognition rate compared to single-modality SRC based methods. The accuracy of the proposed method is also compared to other multi-modality classifiers and the results confirm that higher recognition rates are achieved in comparison with other common classification algorithms.

The sparse representation based classification (SRC) can effectively improve the face recognition rate. Smoothed l 0 algorithm has much faster calculation speed and requires fewer measured values than the other sparse representation method. In this paper, the sparse representation and smoothed l 0 algorithm for face recognition are presented to improve the face recognition under various conditions such as face disguise, illumination and pose changes, etc. The experiments on the AR, Extended Yale B and FERET face database verify the effectiveness of the presented method. The experimental results show that the face recognition algorithm increases to a certain extent in terms of recognition robustness and time than the original SRC.

Joint predictive model and representation learning for visual domain adaptation

We present a transductive deep learning-based formulation for the sparse representation-based classification (SRC) method. The proposed network consists of a convolutional autoencoder along with a fully connected layer. The role of the autoencoder network is to learn robust deep features for classification. On the other hand, the fully connected layer, which is placed in between the encoder and the decoder networks, is responsible for finding the sparse representation. The estimated sparse codes are then used for classification. Various experiments on three different datasets show that the proposed network leads to sparse representations that give better classification results than state-of-the-art SRC methods. The source code is available at: github.com/mahdiabavisani/DSRC.

Sparse representation based classification (SRC) and collaborative representation based classification (CRC) are two well-known methods in representation-based classification for face recognition. SRC emphasizes on the role of sparsity in coding, while CRC obtains an enhanced sparse representation with collaborative contributions from all classes. Previous studies show that sparsity of representation coefficients of SRC and CRC is significant for robust classification that may amplify the nonlocal contribution from other classes. However, the parameters are closely associated with the sparsity and it is very difficult to solve the optimal solutions. This paper proposed a novel representation-based image classification method that integrates SRC with CRC by a multiplication operation on the solutions to obtain enhanced sparse representation. We conducted experiments on several benchmark face databases and the experimental results showed that our algorithm produces higher accuracy on classification than both SRC and CRC.

Mutually exclusive-KSVD: Learning a discriminative dictionary for hyperspectral image classification

We address the problem of sparse channel representation for downlink channel estimation in multi-user frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems. Existing methods typically adopt discrete Fourier transform (DFT) matrix as a sparse basis to represent sparse channels. However, a sparse basis constructed through dictionary learning method has proven to have strong sparse channel representation. In this work, we develop a discriminative dictionary learning-based sparse channel representation for downlink channel estimation in a multi-user FDD massive MIMO systems. Considering partially shared support between near users, we present a new discriminative dictionary learning (DDL) method for sparse channel representation, based on which the channel estimation scheme is developed. Compared with learning a shared dictionary for all users, it can provide a better representation, thus improving the performance of recovery in the compressive sensing process. Numerical results demonstrate the superior performance of discriminative dictionary as compared to the shared dictionary in terms of normalized mean square error (NMSE) and symbol error rate (SER).

Dimensionality reduction has emerged as one of the prominent fields of research since it provides a solution to a wide class of problems, such as compression, classification, regression, feature analysis, and visual recognition. Generally, subspace learning algorithms find a low-dimensional subspace from a given high-dimensional data, wherein samples from different classes can be well separated. In the past decades, several types of dimensionality reduction and subspace selection algorithms have been widely used for visual data analysis. Conventional algorithms such as principal component analysis (PCA) and linear discriminant analysis (LDA), perform well under the assumption that training and test data follow similar distributions. However, the main drawback still remains in the sense that the distribution of the training data and that of the test data are mismatched when samples are drawn from different but related sources. They also fail to incorporate temporal statistical variations in data distribution when applied to time-series data(videos). Consequently they result in unsatisfactory recognition performance when they deal with real world visual analysis problems. To overcome the above issues, in this research, our aim is to consider invariance and stationarity in subspace analysis pertaining to many computer vision applications such as video retrieval, human behaviour analysis, event analysis and activity recognition. More specifically, we will address the challenging and fundamental tasks of 1. Video Classification (Scene, dynamic texture and action recognition) 2. Visual Domain Adaptation. To address the first task, we propose a subspace learning approach that focuses on extracting the stationary parts of all videos in the same class. The notion of stationarity is intuitively well-adapted to model the temporal nature of the video signal and lets us make use of many image features. Instead of modeling temporal information in the features, our method explicitly accounts for it when learning the latent space. As a consequence, the resulting video representation is particularly well-suited for classification purpose. Our experimental evaluation shows that our approach outperforms baselines from the different groups of methods in several video classification tasks such as dynamic texture recognition, scene classification and action recognition.The second task addressed by this work is domain adaptation for visual recognition. In our proposed approach, we follow the intuitive idea of learning the domain invariant subspace by matching the distributions of the transformed training and test data using Maximum Mean Discrepancy (MMD). This, we believe, makes better use of the expressive power of the kernel in MMD compared to the other approaches like Transfer Component Analysis (TCA). Although motivated by MMD, in TCA, the distance between the sample means is measured in a lower-dimensional space rather than in Reproducing Kernel Hilbert Space (RKHS), which somewhat contradicts the intuition behind the use of kernels. Furthermore, we extend the framework for the semi-supervised scenario. Experiments on benchmark domain adaptation dataset for visual recognition, show that in comparison to well-known methods, the proposed approach obtains a significant improvement in classification accuracy. To address the second task, we propose another domain adaptation method that exploits the Riemannian structure of the statistical manifold when learning the invariant subspaces or samples. To this end, we introduce the use of the Hellinger distance which is related to the geodesic distance on the space of probability distributions. While the Hellinger distance has been employed for dimensionality reduction, to the best of our knowledge, our approach is the first attempt at exploiting the Riemannian geometry of the statistical manifold for domain adaptation. We showed that our sample-selection and subspace-based approaches in conjunction with Hellinger distance for distribution matching consistently outperform the similar approaches on the tasks of visual domain adaptation and WiFi localization.

Robust automatic facial expression detection method based on sparse representation plus LBP map

The sparse representation based classification methods has achieved significant performance in recent years. To fully exploit both the holistic and locality information of face samples, a series of sparse representation based methods in spatial pyramid structure have been proposed. However, there are still some limitations for these sparse representation methods in spatial pyramid structure. Firstly, all the spatial patches in these methods are directly aggregated with same weights, ignoring the differences of patches reliability. Secondly, all these methods are not quite robust to poses, expression and misalignment variations, especially in under-sampled cases. In this paper, a novel method named robust sparse representation based classification in an adaptive weighted spatial pyramid structureRSRC-ASP) is proposed. RSRC-ASP builds a spatial pyramid structure for sparse representation based classification with a self-adaptive weighting strategy for residuals aggregation. In addition, three strategies, local-neighbourhood representation local intra-class Bayesian residual criterion and local auxiliary dictionary are exploited to enhance the robustness of RSRC-ASP. Experiments on various data sets show that RSRC-ASP outperforms the classical sparse representation based classification methods especially for under-sampled face recognition problems.

Aiming at the limitation of single feature classification, this paper proposes a facial expression recognition algorithm based on feature fusion and sparse representation residual fusion. The proposed method is composed of three components. Firstly, a feature fusion method based on local binary quantization (LBP) and local phase quantization (LPQ) is proposed. The LBP/LPQ features are an expression feature with image space and frequency domain. Second, Curvelet transform is used to extract the global features of facial expression, which is a very effective multi-scale, band-pass and direction analysis tool. Finally, the LBP/LPQ features and the Curvelet feature are classified by the sparse representation based classification (SRC) with stronger discrimination and robustness respectively. According to the sparse residuals of LBP/LPQ+SRC and Curvelet+SRC, a classification method of residual fusion is proposed. Experiments on JAFFE database and Cohn-Kanade database show that the proposed method effectively improves the ability of facial expression recognition and achieves a high recognition rate.

This paper analyzes the role of dictionary selection in Sparse Representation-based Classification (SRC). While SRC introduces interesting results in the field of classification, its performance is highly limited by the number of training samples to form the classification matrix. Different studies addressed this issue by using a more compact representation of the training data in order to achieve higher classification speed and accuracy. Representative selection methods which are analyzed in this paper include Metaface dictionary learning, Fisher Discriminative Dictionary Learning (FDDL), Sparse Modeling Representative Selection (SMRS), and random selection of the training samples. The first two methods build their own dictionaries via an optimization process while the other two methods select the representatives directly from the original training samples. These methods, along with the original method which uses all training samples to form the classification matrix, were examined on two face datasets and one digit dataset. The role of feature extraction was also studied using two dimensionality reduction methods, down-sampling and random projection. The results show that the FDDL method leads to the best classification accuracy followed by the SMRS method as the second best. On the other hand, the SMRS method requires a much smaller learning time which makes it more appropriate for dynamic situations where the dictionary is regularly updated with new samples. The accuracy of the Metaface dictionary learning method was specifically less than the other two methods. As expected, using all the training samples as the dictionary resulted in the best recognition rates in all the datasets but the classification times for this approach were far larger than the required time using any of the three dictionary learning methods.