A New Retrieval Method Based on YUV Clour Information for Digital Libraries

Image retrieval is the core technology to the further development of the digital library. At present, image retrieval is mainly restricted by the conflict between retrieval accuracy and retrieval speed. In order to solve this problem, an image retrieval method based on wavelet decomposition of YUV component images had been proposed in this paper. First, YUV component images were computed from original image information. Second, every component image was carried out wavelet decomposition, and then low-frequency component was extracted. Finally, similarity function was generated by fusing low-frequency of three component images. Experimental results demonstrated that the method proposed in this paper has a high retrieval accuracy at a fast speed.