Improving Object Classification Using Zernike Moment, Radial Cheybyshev Moment Based on Square Transform Features: A Comparative Study
Amitabh Wahi, Sri Krishna · 2014
In many applications, different kinds of moments have been utilized to classify images and object shapes. Moments are important features used in recognition of different types of images. In this paper, three kinds of moments: Structure Moments, Radial cheybyshev moments, Radial cheybyshev moments computation on square Transform have been evaluated for classifying object images using Back propagation classifier. Experiments are conducted using MIT, PASCAL VOC and ORL database which contains car, bicycle, Trucks and face images. The main objective is to make hybrid descriptor which combines structure moment with Zernike moments and Radial Cheybyshev Moments to capture shape and boundary information. In this paper the effect of Zernike moments, Radial Cheyshev moments on new density function in recognition rate improvement are studied. The test results are carried out and a comparative study with two of the existing techniques are included to show the effectiveness of the proposed technique.