Detection and amendment of shape distortions based on moment invariants for active shape models
Detection and amendment of shape distortions based on moment invariants for active shape models
复制标题
DOI：
10.1049/iet-ipr.2007.0110
复制
发表时间：
2011-04-01
影响因子：
2.3
通讯作者：
Liu, S.
中科院分区：
文献类型：
--
作者：
Chen, S. Y.;Zhang, J.;Liu, S.
主动形状模型是一种越来越重要的目标建模、形状识别和目标定位方法。然而，在形状拟合过程中，当目标不清晰或有缺陷时，往往会出现变形和位移，ASM缺乏有效的修正策略。在本研究中，受物理学的启发，使用边界矩不变量来解决这一困难。本文首次将矩不变量引入到ASM中，用于变形检测和形状修正。该方法有效地避免了图像的失真，并且在不增加一点时间的情况下，明显提高了拟合结果的精度。最后，作者的实际实施结果证明了其令人满意的工作。
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.