Image retrieval based on RGB edge and color
Tai De-ya · Microcomputer Information · 2010
A new image retrieval algorithm based on image edge detection in RGB color space and color histogram entropy in each sub-block is proposed. Shape features are extracted by image edge detection. Sub -block number and weight value depends on the percentage of the main target in image. The similarity between color images is computed by using a combined feature index based on shape and color histogram entropy. Experimental results show this system is surpassed the single image retrieval.