A New NAM-based Algorithm for Computing Hu Moments of Binary Images

摘要

Hu moments are very important in the fields of image analysis and object representation. In this paper, inspired by the idea of computing moments on a block representation, we put forward a new algorithm for computing the Hu moments on the Non-symmetry and Anti-packing Model (NAM) representation of binary images, which takes O(N) time where N is the number of NAM blocks. By taking four idiomatic standard binary images 'Peppers', 'Goldhill', 'Lena', and 'F16' in the field of image processing as typical test objects, and by comparing our proposed NAM-based algorithm with the traditional and the popular Bintree-based algorithm for computing the Hu moments, the theoretical and experimental results presented in this paper show that the average execution time improvement ratios of our proposed NAM-based algorithm over the Bintree-based algorithm and the traditional algorithm are 92.76% and 99.70%, respectively. Therefore, in the case of computing lower order moments of binary images, our proposed algorithm is much faster than the Bintree-based and the traditional algorithms.