New mapping scheme of Hough Transform for line detection

作者：Chen Hongbo^*; Wang Qiang; Xu Xiaorong; Chen Zhencheng; Tang Jingtian

来源：Journal of Computational Information Systems, 2009, 5(1): 407-415.

• Line detection
• Many-to-one
• Mapping scheme
• Parameter spaces
• Peak diffusion
• Running time
• Storage requirements

In terms of mapping scheme, the existing algorithms of Hough Transform for line detection can be classified two categories: one-to-many and many-to-one. Each of them has its drawbacks such as peak diffusion in parameter space, heavy burden of computational complexity, and massive storage requirement. To overcome these drawbacks, an adaptive many-to-many mapping scheme is proposed in this paper, which has an effective strip-shaped detection region. With the new mapping scheme, the peak corresponding to a line does not spread around in parameter space and is insensitive to parameter quantization, so the threshold can be selected conveniently. These characteristics are very helpful to accurately detect the parameter of line in image. Although the computational complexity of many-to-many mapping schemes is slightly higher than that of many-to-one-θ mapping schemes, experimental results reveal that the proposed method is more efficient for line detection at the cost of an acceptable running time.

• 出版日期2009