Image Retrieval Based on Image Entropy and Regional Expansion
Chen Shuying, Zhiyong An · International Journal of Control and Automation · 2016
This paper uses the image entropy directly on the color image to express the integral color image information and color spatial distribution of the neighborhood, then the image is divided into blocks, for each block we use the Pelaez Aggregation to determine the seed, after that we use the regional expansion method for color image blocks to extract the color characteristic of color image. The centroid was extracted from the segmented image and combined with variance as the similarity metric standard. Result shows that, this method is not only simple and efficient, but also improves the performance of image retrieval.