No abstract

No abstract

No abstract

This paper incorporates principal component analysis (PCA) with support vector machine-particle swarm optimization (SVM-PSO) for developing real-time face recognition systems. The integrated scheme aims to adopt the SVM-PSO method to improve the validity of PCA based image recognition systems on dynamically visual perception. The face recognition for most humanrobot interaction applications is accomplished by PCA based method because of its dimensionality reduction. However, PCA based systems are only suitable for processing the faces with the same face expressions and/or under the same view directions. Since the facial feature selection process can be considered as a problem of global combinatorial optimization in machine learning, the SVM-PSO is usually used as an optimal classifier of the system. In this paper, the PSO is used to implement a feature selection, and the SVMs serve as fitness functions of the PSO for classification problems. Experimental results demonstrate that the proposed method simplifies features effectively and obtains higher classification accuracy.

The paper proposes design concepts of a vision-based shopping assistant robot which can serve people in a mall. By using such robots, a mall could not only save human resources effectively but also improve the quality of information service. In general, a mall always provides three kinds of customer services as guiding, communication and accompanying. In this paper, a fuzzy collision-free guiding controller and a fuzzy following controller are proposed for guiding and accompanying services respectively. For collision-free controls, a named "warning area" will be preplanned in the image plane to check whether there are objectives and/or obstacles in front of the robot. Besides, the eigenblock of objectives could be determined by using color image processing methods. The color recognition and size filter are used to search for proper objective image blocks and their relative locations. Based on a fuzzy following controller, the robot will accomplish the mobility of following the specified customer. Several experiments demonstrate the feasibility of the proposed robotic system.