Image Retrieval Based on Color and Shape Features of Interest Points
Baolong Guo · Microelectronics & Computer · 2006
This paper presents a novel algorithm for image retrieval based on interest points, which utilizes the location information of the interest points, extracts the local color moment feature and shape invariant moment feature. This algorithm is not only robust to translation and rotation, but also avoids the drawbacks of losing the location information in color moment and shape invariant moment. Experimental results show that this algorithm effectively improves the image retrieval accuracy due to combining color and shape features.