结合边缘信息的图像检索技术

Image Retrieval Based on Edge Information

针对基于内容的图像检索技术中因忽略人眼视觉的影响而造成的检索率偏低问题,提出了一种新的图像检索算法.首先,结合人眼的视觉特性,借鉴方块编码的思想提取对表征图像内容有意义的子特征,该特征不仅体现了图像的边缘信息,而且在一定程度上对整幅图像的纹理特征也进行了较好地描述;在此基础上,定义图像的特征描述符.针对描述符自身的特点,采用图像的互信息作为最后的相似性度量准则.实验结果表明同以往算法相比,该算法具有较高的检索效率.

A novel method is proposed in this paper to solve the disadvantage of ignoring the visual feature in image retrieval. Firstly, combining the visual feature with principle of the block truncation code （BTC）, the significant image feature is extracted and a novel descriptor is def＇lned which can embody the edge and texture information of the image. Based on the analysis of the characters of the descriptor, the mutual information is chosen to image retrieval. Compared with the other algorithms, experiments show the proposed approach has good effect.