Improved Hu Moment Invariant Empowered Fast Image Contour Registration Algorithm

In order to solve the problems that the existing Hu moment invariants can't match quickly because of their high complexity, and the accuracy is not high when dealing with intra-class changes with geometric transformations (rotation and large-scale changes), an improved Hu moment invariants-enabled fast image contour registration algorithm is proposed. Firstly, the Canny operator is used to obtain the contour of the image to be recognized, and then the matching reference point and matching search path of Hu invariant matrix of the image to be recognized and the template image are optimized according to DTW algorithm, and the complexity of image contour registration is reduced by reducing the feature of traversing matching points. The experimental results show that this method has good stability when dealing with geometric transformations such as translation and scaling, and it has fast recognition speed and high shape classification accuracy when registering image contours.