Abstract:This paper deals with frontal facial feature extraction in face recogn ition system. First human face is segmented from the input image by using region growth. Then by using edge detection, Hough transformation, template matching a nd variance projection, facial features such as eyes, nose and mouth are located quickly and effectively. Experiment results show that the method we present has a higher accuracy and robust performance to illumination.

Abstract:This paper analyses the general relation between rubber hardness and rubber mechanical constant symbolized by C1 and C2, which are determined through uniaxial tension test and finite element computation. On the basis of it, the large deformation of compressed rubber supporting about different hardness is researched and the relation between the rubber mechanical constants and the hardness is further discussed.

Abstract:Image semantic segmentation is one of the most important problems in computer vision, whose target is to assign a semantic label for each pixel of a given image and segment the image into several visually meaningful or interest regions,in order for the image analysis and vision un-derstanding .In recent years,tremendous progress has been made for semantic segmentation due to the development of deep convolutional neural network (DCNN).In this paper,we firstly dis-cuss the difficulties and challenges of semantic segmentation.Then,DCNN-based achievements in the study of semantic segmentation are reviewed.In addition,an analysis for semantic segmen-tation based on PASCAL VOC dataset is given,which is generally acknowledged as a popular public evaluation for semantic segmentation.Finally,some probable development directions of semantic segmentation are discussed.