To reduce the negative impact of inhomogeneous regions and weak edges,a foreground extraction model based on per-ception of regional context was proposed.An image was divided into on-intersecting regions in terms of the color similarity and the intensity gradient properties.The color in a region was homogeneous,and there were significant differences between adjacent regions.The color distribution was analyzed,the regions similarity matrix and perception space were constructed.The fore-ground extraction was transformed to the binary classification problem in the perception space.Numerical examples indicate that,comparing to the traditional model,this model has better segmentation results for natural image with weak edges and inhomoge-neous regions.
关键词
前景提取/区域信息/LAB颜色空间/高斯混合模型/亮度感知/特征提取/上下文
Key words
foreground extraction/region information/LAB color space/Gaussian mixture model/brightness perception/fea-ture extraction/context of region
维普
万方数据