No abstract

In this work, a novel facial feature extraction method is proposed for automatic facial expressions recognition, which detecting local texture information, global texture information and shape information of the face automatically to form the facial features. First, Active Appearance Model (AAM) is used to locate facial feature points automatically. Then, the local texture information in these feature points and the global texture feature information of the whole face area are extracted based on the Local Binary Pattern (LBP) techniques, and also the shape information of the face are detected. Finally, all the information are combined together to form the feature vector. The proposed feature extraction method is tested by the JAFFE database and experimental results show that it is promising.

Bio-inspired hardware (BHW) refers to hardware that can change its architecture and behaviour dynamically and autonomously by interacting with its environment, and ant colony optimization is a meta-heuristic algorithm for the approximate solution of combinatorial optimization problems that has been inspired by the foraging behaviour of real ant colonies. In this paper, we take a broad survey on the recent progresses of ant colony optimization-based BHW, which includes ant colony optimization-based fuzzy controller, ant colony optimization-based hardware for the Travelling Salesman Problem (TSP), digital circuits, digital infinite impulse-response (IIR) filters, hardware-oriented ant colony optimization with look-up table and hardware/software partition. Some important issues of the challenges of ant colony optimization-based BHW are also presented. Online realization, robustness, generalization, disaster problems, theoretical analysis, implementation, swarm robotics, applications and hybrid approaches are eight key challenging issues for the ant colony optimization-based BHW.

Abstract. Facial expression recognition has widely been investigated in the literature. The need of accurate facial alignment has however limited the deployment of facial expression systems in real-world applications. In this paper, a novel feature extraction method is proposed. It is based on extracting local binary patterns (LBP) from image key points. The face region is first segmented into six facial components (left eye, right eye, left eyebrow, right eyebrow, nose, and mouth). Then, local binary patterns are extracted only from the edge points of each facial component. Finally, the local binary pattern features are collected into a histogram and fed to an SVM classifier for facial expression recognition. Compared to the traditional LBP methodology extracting the features from all image pixels, our proposed approach extracts LBP features only from a set of points of face components, yielding in more compact and discriminative representations. Furthermore, our proposed approach does not require face alignment. Extensive experimental analysis on the commonly used JAFFE facial expression benchmark database showed very promising results, outperforming those of the traditional local binary pattern approach.

Recently, unmixing methods based on nonnegative tensor factorization have played an important role in the decomposition of hyperspectral mixed pixels. According to the spatial prior knowledge, there are many regularizations designed to improve the performance of unmixing algorithms, such as the total variation (TV) regularization. However, these methods mostly ignore the similar characteristics among different spectral bands. To solve this problem, this paper proposes a group sparse regularization that uses the weighted constraint of the L2,1 norm, which can not only explore the similar characteristics of the hyperspectral image in the spectral dimension, but also keep the data smooth characteristics in the spatial dimension. In summary, a non-negative tensor factorization framework based on weighted group sparsity constraint is proposed for hyperspectral images. In addition, an effective alternating direction method of multipliers (ADMM) algorithm is used to solve the algorithm proposed in this paper. Compared with the existing popular methods, experiments conducted on three real datasets fully demonstrate the effectiveness and advancement of the proposed method.