Comment on: "Extended Hough transform for linear feature detection"

作     者：Chung, Kuo-Liang Chang, Ting-Chin Huang, Yong-Huai 

作者机构：Department of Computer Science and Information Engineering National Taiwan University of Science and Technology No. 43 Section 4 Keelung Road Taipei 10672 Taiwan 

出 版 物：《Pattern Recognition》 (Pattern Recogn.)

年 卷 期：2009年第42卷第7期

页      面：1612-1614页

核心收录：

学科分类：08[工学] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Supported in part by the National Science Council of ROC under Contract NSC97-2221-E011-128 

主　　题：Hough transforms 

摘      要：The extended Hough transform (EHT) method for line detection with an ability to detect any line segment with desired length, formulated by Cha et al. was discussed. The method continued with the gray image with size hw is transferred into the edge map by using the edge detector. The voting process is performed in two 3D Hough spaces, each Hough space is consisted of a set of 2-D Hough planes, to detect line segments. The developed method is also capable of determining the starting point and ending point of each detected line segment. It has also been demonstrated by experiments, and the study aimed to show that after classifying all edge pixels into two types according to the orientations of edge pixels,the execution time required in the voting process of the EHT method can be reduced efficiently. Experimental results indicate that the average practical execution time improvement ratio is 16% and it is very close to the average theoretical execution time improvement ratio.