一种基于Hough变换的直角角点检测算法

直角角点检测在广泛的图像处理与机器视觉应用领域中具有重要性.提出了一个新的直角角点检测方法.原始图像经边缘检测后得到二值化边缘,将直角角点检测问题分解为一系列的模板匹配问题.应用了Hough变换来高效地解决模板匹配的问题,并在Hough变换中结合了边缘方向信息以减少检测出的虚假直角角点数量.在一个实际的图像数据库上进行了提出的方法与其他数种角点检测算法的对比实验.实验结果表明,与其他方法相比,提出的方法具有最高的直角角点检出率,而其整体性能(包括运行时间、检出率、虚假角点检测率)也具有优势.

Right Angled Corner Detection Method Based on Hough Transform

Right angled comer detection is important for wide range of image processing and machine vision applications, e. g. , automatic analysis of engineering charts. A novel method for right angled comer detection is proposed. Edge detection is applied to the original image to get the binary contours. The problem of right angled comer detection is then decomposed into a series of template matching problems. Hough transform is used to solve the matching problems efficiently. Besides, edge direction information is also integrated into the Hough transform procedure to reduce the number of false positive instances of right angles. The proposed method was applied to a practical image database and compared with other comer detection algorithms. Experiment results show that the proposed algorithm has the highest right angle detection rate, and the overall performance of the method, including running time, detection rate, and false positive rate, is also oreferable comoared with other methods.