针对使用三角形区域表示描述子对相似形状进行匹配时，对微小形变比较敏感以及区分剧烈变化的不相似形状时判别能力较弱的问题，提出一种结合轮廓点空间关系特征的多尺度形状特征描述子。通过分析不同尺度下参考点与其他采样点之间的位置关系，利用对应角度信息来对形状进行表示，并在此基础上构造出一种新的形状特征描述子。本文所提特征提取方法能对形状的局部及全局信息更准确地描述，具有较好的鲁棒性和判别能力。在形状特征匹配阶段，利用轮廓点集顺序关系已知这一优势，引入动态规划及形状复杂度分析的方法，分析形状间的匹配结果，能够得到较好的形状匹配精度。通过对不同形状数据集行仿真实验，证明本文方法能够有效地实现形状识别和检索。%In order to improve the sensibility and discrimination power of triangle-area representation, a shape matching method using multi-scaled contour space relationship is proposed. The angle information in multi-scales, which is used to represent shape contours, can be obtained by analyzing the spatial relationship of different points, and a new shape descriptor is further constructed. With the proposed descriptor, the multi-scaled information of contours can be expressed accurately, and the cost for descriptors of the corresponding points from similar shapes can be effectively decreased. As the orders of all the contour points are already known, a dynamic programming method and shape complexity can be used to guarantee the matching accuracy during the feature matching step. The proposed algorithm has been tested on different shape databases, and the performances are superior to many other methods.
展开▼
