Abstract
In this paper we present a new method for shape recognition based on dynamic programming. First, each contour of shape is represented by a set of points. After alignment and matching between two shapes, the outline of the shape is divided into parts according to N angular and M radial sectors , Each Sector contains a portion of the contour; this portion is divided at the inflexion points into convex and concave sections, and the information about sections are extracted in order to provide a semantic content to the outline shape, then this information are coded and transformed into a string of symbols. Finally we find the best alignment of two complete strings and compute the optimal cost of similarity. The algorithm has been tested on a large set of shape databases and real images (MPEG-7, natural silhouette database).
Abstract (translated)
本文提出了一种基于动态规划的形状识别方法。首先,每个形状的轮廓由一组点表示。两个形状对齐匹配后,将形状轮廓按n个角和m个半径划分为多个部分,每个部分包含轮廓的一部分;该部分在拐点处划分为凸形和凹形部分,并提取有关部分的信息,以提供一个语义。将内容转换为轮廓形状,然后将这些信息编码并转换为一系列符号。最后,我们找到两个完整字符串的最佳对齐方式,并计算出最佳相似成本。该算法已经在大量的形状数据库和真实图像(MPEG-7,自然轮廓数据库)上进行了测试。
URL
https://arxiv.org/abs/1904.08501