Improved Accuracy in Shape Based Image Retrieval with Complex Zernike Moments Using Wavelets

Zernike Moments (ZMs) have been most widely used in extracting the region based shape features of an image related to Logo, Trademark, Clip art search etc. Still retrieval of accurate images is an issue. In most of the researches, emphasis is given only on magnitude of ZMs. Complex Zernike Moments (CZMs) takes both Phase and Magnitude component for feature extraction. The concept of wavelets is also combined with CZMs and it has been found that the use of wavelets with CZMs result in improved accuracy of retrieved results because of better classification ability of wavelets. Angle and magnitude based distance has been used to see the similarity of images. Shape database of 100 images of different classes is used in the study. Rotational database is generated using these images. It is found that wavelets based CZMs can capture better features as compared to magnitude based ZMs.