Image Retrieval Algorithm Based on Texture and Color Features

摘要

A novel image retrieval algorithm based on texture and color feathers was proposed. Firstly, the image was divided into non-overlapped blocks with equal size, and every pixel was given a new value (0 or 1) according to different color, then do the second division to the whole image and coding new blocks, counting the probability of every code and primary color. Finally, texture and color feathers method was applied in image retrieval. Experimental results show that the proposed algorithm has reasonable and robust performance and is more effective.