Xuewen Wu

Combining Multimodal Features with Hierarchical Classifier Fusion for Emotion Recognition in the Wild

Emotion recognition in the wild is a very challenging task. In this paper, we investigate a variety of different multimodal features from video and audio to evaluate their discriminative ability to human emotion analysis. For each clip, we extract SIFT, LBP-TOP, PHOG, LPQ-TOP and audio features. We train different classifiers for every kind of features on the dataset from EmotiW 2014 Challenge, and we propose a novel hierarchical classifier fusion method for all the extracted features. The final achievement we gained on the test set is 47.17% which is much better than the best baseline recognition rate of 33.7%.

Combining Multimodal Features within a Fusion Network for Emotion Recognition in the Wild

In this paper, we describe our work in the third Emotion Recognition in the Wild (EmotiW 2015) Challenge. For each video clip, we extract MSDF, LBP-TOP, HOG, LPQ-TOP and acoustic features to recognize the emotions of film characters. For the static facial expression recognition based on video frame, we extract MSDF, DCNN and RCNN features. We train linear SVM classifiers for these kinds of features on the AFEW and SFEW dataset, and we propose a novel fusion network to combine all the extracted features at decision level. The final achievement we gained is 51.02% on the AFEW testing set and 51.08% on the SFEW testing set, which are much better than the baseline recognition rate of 39.33% and 39.13%.

Multi-feature-based robust face detection and coarse alignment method via multiple kernel learning

Face detection and alignment are two crucial tasks to face recognition which is a hot topic in the field of defense and security, whatever for the safety of social public, personal property as well as information and communication security. Common approaches toward the treatment of these tasks in recent years are often of three types: template matching-based, knowledge-based and machine learning-based, which are always separate-step, high computation cost or fragile robust. After deep analysis on a great deal of Chinese face images without hats, we propose a novel face detection and coarse alignment method, which is inspired by those three types of methods. It is multi-feature fusion with Simple Multiple Kernel Learning1 (Simple-MKL) algorithm. The proposed method is contrasted with competitive and related algorithms, and demonstrated to achieve promising results.

Alignment-free sparse representation based classification method via fast location

This paper aims at optimizing the efficiency of the sparse representation based classification (SRC) method in automatic recognition, which is a common problem with large quantity of sample images. An automated target recognition framework based on SRC method is proposed through fast locating to the region of interest (ROI) and dictionary filtering meanwhile. We solve the alignment problem through the fast locating and get an alignment-free SRC method for different poses of a 3D target. We propose two methods for the fast locating in the paper. The dictionary filtering is done according to the probe image. The proposed method has been operated on car and face databases. Car recognition aiming at multi-pose recognition, a car-model database is set up, and its capturing equipment and environments are introduced. On this database, the performance of the proposed method is assessed and compared with the original SRC method. Then, we have further performed the method on yawl B database for face recognition. Then we conclude that the proposed method improves the efficiency and accuracy of the original SRC method.

Research on clustering-weighted SIFT-based classification method via sparse representation

In recent years, sparse representation-based classification (SRC) has received significant attention for its high recognition rate. However, the original SRC method requires rigid alignment. By further considering the robustness of scale and affine in this paper, we explore the relationship of the similarity of the SIFT descriptors to a recognition task and propose a clustering-weighted SIFT-based SRC algorithm (CWS-SRC). The SIFT descriptors extracted from the samples are first clustered according to similarity. Next, the weight of each feature is calculated for a weighted classifier. Finally, the SRC method is operated on the SIFT descriptors extracted from a probe image, and its identity can be implemented via the weighted classifier. Using two public face databases (AR, Yale face database) and a self-built car-model database, the performance of the proposed method is evaluated and compared with that of SRC, SIFT matching and MKD-SRC method. The proposed CWS-SRC exhibits better performance for sufficient samples in the misalignment scenario.

Sparse presentation based classification with position-weighted block dictionary

This paper is aiming at applying sparse representation based classification (SRC) on general objects of a certain scale. Authors analyze the characteristics of general object recognition and propose a position-weighted block dictionary (PWBD) based on sparse presentation and design a framework of SRC with it (PWBD-SRC). Principle and implementation of PWBD-SRC have been introduced in the article, and experiments on car models have been given in the article. From experimental results, it can be seen that with position-weighted block dictionary (PWBD) not only the dictionary scale can be effectively reduced, but also roles of image blocks taking in representing a whole image can be embodied to a certain extent. In reorganization application, an image only containing partial objects can be identified with PWBD-SRC. Besides, rotation and perspective robustness can be achieved. Finally, a brief description on some remaining problems has been proposed in the article.

Optimized sparse presentation-based classification method with weighted block and maximum likelihood model

This paper is aiming at applying sparse representation based classification (SRC) on face recognition with disguise or illumination variation. Having analyzed the characteristics of general object recognition and the principle of the classifier of SRC method, authors focus on evaluating blocks of a probe sample and propose an optimized SRC method based on position-preserving weighted block and maximum likelihood model. Principle and implementation of the proposed method have been introduced in the article, and experiments on Yale and AR face database have been given too. From experimental results, it can be seen that the proposed optimized SRC method works well than existing methods.

Automatic target recognition using group-structured sparse representation

Sparse representation classification method has been increasingly used in the fields of computer vision and pattern analysis, due to its high recognition rate, little dependence on the features, robustness to corruption and occlusion, and etc. However, most of these existing methods aim to find the sparsest representations of the test sample y in an overcomplete dictionary, which do not particularly consider the relevant structure between the atoms in the dictionary. Moreover, sufficient training samples are always required by the sparse representation method for effective recognition. In this paper we formulate the classification as a group-structured sparse representation problem using a sparsity-inducing norm minimization optimization and propose a novel sparse representation-based automatic target recognition (ATR) framework for the practical applications in which the training samples are drawn from the simulation models of real targets. The experimental results show that the proposed approach improves the recognition rate of standard sparse models, and our system can effectively and efficiently recognize targets under real environments, especially, where the good characteristics of the sparse representation based classification method are kept.