Feature extraction using partial overlapping block-based reconstruction with exact continuous moments: Legendre and Gegenbauer

This paper presents an enhanced algorithm for pattern recognition using an partial overlapping method of a 4x4 block and exact computation moments: Legendre and Gegenbauer. By employing a limited number of moments (order 0), the methods achieve high accuracy while maintaining a low computational cost. It also provides better recognition rates compared to conventional methods based on calculating moments on the entire image, which involve higher orders. Experimental results highlights the superior performance of the proposed method, particularly with Legendre moments, compared to existing techniques.