Image Retrieval Based on Color-Statistic Feature
Color is the most widely used visual feature in content based image retrievaL The visual coherence color space,HSV,is adopted to represent image.Hue component is used to denote color.Hue difference statistic is proposed to extract color change information as supplement to color feature.The image is divided into sub images equally.Color and change information is extracted in each region.After feature vector clustering and coding,image content can be expressed as vector codes.The text based analysis technology is used for image retrieval Experiments show that the proposed method can realize efficient retrieval for unconstrained scene images.
color change statistic image retrieval
Jinmei Liu Jizhong Li
School of Science and Information Qingdao Agriculture University Qingdao, China
国际会议
太原
英文
655-658
2013-04-06（万方平台首次上网日期，不代表论文的发表时间）