Subpixel Extraction in Images using Orthogonal Moments (Zernike7) and Spatial Moments (Spatial5)

In this paper, we demonstrate a program that employs orthogonal moments (specifically Zernike7 moments) and spatial moments (Spatial5 moments) for subpixel-level feature extraction in images. This technique enables superior image analysis and understanding, particularly in high-precision applications where exact feature localization is critical. The implementation typically involves calculating Zernike moments through polynomial basis functions for rotational invariance, while spatial moments handle geometric property extraction using weighted pixel intensity summations. By combining these two moment types, the algorithm achieves precise information extraction from images, enhancing both accuracy and efficiency in image processing tasks. Furthermore, this methodology finds extensive applications in medical image processing, computer vision, and machine learning domains, providing robust solutions for practical challenges such as edge detection, object recognition, and pattern analysis with subpixel accuracy.