Segmentation Based on Shape Prior and Graph Model Optimization
A scheme of segmentation based on low-level and high-level cues is presented. Firstly, image-pyramid is obtained based on segmentation by Weighted Aggregation (SWA), the surtable coarse pixel image is selected to be as lowlevel segmentation cues. Kernel principal component analysis (KPCA) is used for building the space of shape to represent shape prior knowledge. The coarse pixel image is expressed through a graph model, based on high and low level cues, genetic algorithm (GA) is used to find out the optimal sub-grapb to segment object precisely. Experimental results demonstrate that our proposed approacb is able to accurately segment the objects with better performance than the existing methods.
object segmenting shape learning graph model genetic algorithm
Qinkun Xiao Nan Zhang Song Gao Fei Li Yue Gao
Depanment of Electronics Information Engineering Xian Technological University Xicm.China, 710032 Department of Electrorucs Information Engineering Tsinghua University Beijing, China, 100084
国际会议
The 2nd IEEE International Conference on Advanced Computer Control(第二届先进计算机控制国际会议 ICACC 2010)
沈阳
英文
405-408
2010-03-27（万方平台首次上网日期，不代表论文的发表时间）