GRAY-SCALE HOUGH TRANSFORM FOR THICK LINE DETECTION IN GRAY-SCALE IMAGES

被引:2
作者
LOT, RC
TSAI, WH
机构
[1] NATL CHIAO TUNG UNIV,DEPT COMP & INFORMAT SCI,HSINCHU 300,TAIWAN
[2] NATL TAIWAN UNIV,DEPT ELECTR ENGN,TAIPEI 106,TAIWAN
关键词
GRAY-SCALE HOUGH TRANSFORM; GRAY-SCALE IMAGE; THICK LINES; BAND; THRESHOLDING; EDGE DETECTION; COMPLEXITY; RADON TRANSFORM;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A new extension of the Hough transform, called gray-scale Hough transform (GSHT), is proposed for detecting thick lines (called bands) in a gray-scale image. The use of the conventional Hough transform (CHT) usually requires the preprocessing steps of thresholding and edge detection (or thinning) before the transform can be performed on a gray-scale image containing bands. This causes loss of useful gray and position relationship existing among the pixels of a band, and requires certain postprocessing steps to recover the band in the original image. The proposed GSHT with a gray-scale image as the direct input removes this shortcoming, requiring neither preprocessing nor postprocessing step in detecting bands in a gray-scale image. Experimental results, showing the feasibility of the proposed approach, are also included.
引用
收藏
页码:647 / 661
页数:15
相关论文
empty
未找到相关数据