Zernike moments are used as a shape descriptor for complex shapes that are difficult to be defined with a single contour such as trademarks. The Zernike moments of a given shape are calculated as correlation values of the shape with Zernike basis functions in that all the pixels of the shape regardless of their positions contribute with the same weight to the Zernike moments. The proposed modified Zernike Moment descriptor is obtained by the following two steps: firstly divide the original shape into three parts of inner

middle and outer regions with tow predetermined radius

then calculate the Zernike moment of each part reseparateively. The modified descriptor takes account of the partition radius of the shape according to human perception

meanwhile

using relevance feedback technology to fix the importance of the each part as mentioned above could improve the efficiency of retrieval process. Euclidean distance is used to compute the distance between two shapes. Experimentation under various test conditions shows the effectiveness of the proposed modified method.