Symmetrical Color-Spatial Feature for Medical Image Retrieval

Color feature of an image is one of the most common used features in content-based image retrieval (CBIR) systems. Combining the traditional colorhistogram with some spatial information will greatly increase the accuracy of color features. One advantage of color feature is that it is independent to the distortion of an image. However, with the introduction of the spatial information, this advantage will disappear. In this paper, we proposed a new symmetrical color-spatial method based on square loop. Experiment results show that the method has good performance when 90 or 180 degree rotation and flip. Its good efficiency makes it suitable for large numbers of images retrieval.