Structural Feature Extraction From Regular-Shaped Rigid Objects(1)—Based on Gradient Direction Constraint Randomized Hough Transform

摘要：

The structural feature extraction from regular shaped rigid objects b studied. First, some specific measures Tor facilitating the conventional Randomized Hough Transform (abbr. RHT) in our application ire introduced. Then, a gradient direction constraint RHT is proposed for improving the poor performance of the conventional RHT that too much false response happens in noisy real images. Tht basic idea of tbe new method is that the edge points of the true straight edges have more consistent distribution of the gradient direction than the noise has. Last, experiments including subjective observations and quantitative statistics validate that the new approach has much more robust performance than the conventional RHT.

关键词： failure extraction Randomized Hough Transform corner detection straight tine extraction

作者: Lei Zhang Qingshaa Fu Xingguo Zhang Guoran Hua Longbiao Zhu

作者单位: School of the Mechanical Engineering, Nantong University, Nanlong, China School of the Mechanical Engineering, Southeast University, Nanjing, China

会议类型: 国际会议

会议名称: 2010 International Symposium on Computational Intelligence and Edsign(第三届计算智能与设计国际学术研讨会 ISCID 2010)

会议地点: 杭州

会议语种:英文

页码: 209-214

在线出版日期: 2010-10-29（万方平台首次上网日期，不代表论文的发表时间）