点击次数：

发布时间：2019-03-10

论文类型：会议论文

发表时间：2016-06-12

收录刊物：Scopus、CPCI-S、EI

卷号：2016-September

页面范围：1837-1841

摘要：In this paper, a novel image descriptor, called Color Binary Correlation (CBC), is proposed for image retrieval. This method defines and describes the structure elements utilizing binary patterns based on colors and edge orientation respectively, and thus integrate texture with the other two properties. Besides, its variants CBCri and CBCu2, which are presented for rotated invariance and "unform" patterns respectively, are presented and analyzed for image retrieval. The experimental results in Corel-1K and Corel-10K datasets demonstrate that our descriptors are more robust and discriminative than other methods and CBC shows better performance than CBCri and CBCu2 because of taking more possible patterns into consideration.