对Freeman链码分析的角点检测算法

摘要

针对传统的基于轮廓曲线的角点检测算法需要计算曲率和选取阈值的不足, 提出一种对Freeman链码分析的角点检测算法, 首先通过图像边缘检测, 轮廓提取得到轮廓的Freeman链码, 当链码发生变化时分析其连续前后多个点的链码是否符合一定的规则来判定角点, 无需经过传统的角点阈值选取, 曲率计算等步骤. 实验通过与He&Yung、CPDA、Fast-CPDA和ARCSS角点检测器比较, 结果表明本文算法在角点检测时准确率(ACU)最高;在变换实验中, 本算法的平均重复率(AR)最高, 由此可以得出本算法具有良好的角点检测性能.%In view of the traditional need to calculate the curvature and the insufficient threshold selection of detection algorithm angular profile curve, this study proposes an angle detection analytic algorithm based on Freeman code by first edge detection, contour extraction to give Freeman code profile. When the chain code changes, it analyzes whether the chain code of a number of points before and after it is consistent with certain rules to determine the corner point, without the need of traditional corner threshold selection, curvature calculation and other steps. Compared with He & Yung, CPDA, Fast-CPDA, and ARCSS corner detector, the experimental results show that the proposed algorithm has the highest accuracy (ACU) in detecting the corner. The transformation experiments show that the average repetition (AR) is the highest, which shows that the proposed algorithm has good corner detection performance.