Detection and amendment of shape distortions based on moment invariants for active shape models

摘要

The active shape model (ASM) is an ever-increasingly important method for object modelling, shape recognition and target localisation. During the process of shape fitting, however, distortions and displacements often occur when the target is not clear or with defects, and there is a lack of effective amendment strategies in ASM. In this study, inspired by physics, the boundary moment invariants are employed to resolve this difficulty. Moment invariants have been introduced into ASM for the first time for distortion detection and shape amendment. Using the proposed strategy, distortions are effectively avoided and the accuracy of the fitting result is obviously increased with a little extra time. Finally, the results of the authors?? practical implementation prove its satisfactory work.