An improved Hough transform for line detection

• Published in: 2010 International Conference on Computer Application and System Modeling (ICCASM 2010) Vol. 2; pp. V2-354 - V2-357
• Main Authors: Dagao Duan, Meng Xie, Qian Mo, Zhongming Han, Yueliang Wan
• Format: Conference Proceeding
• Language: English; Japanese
• Published: IEEE 01.10.2010
• Subjects: Hough transform; Line detection; Local sliding window neighborhood; Many-to-one mapping; Pixel
• ISBN: 9781424472352; 1424472350
• ISSN: 2161-9069
• DOI: 10.1109/ICCASM.2010.5620827

The Hough transform is a popular robust method for detecting lines in an image. However, the computational complexity and storage requirements are the main bottlenecks of the standard Hough transform (SHT) applied on real-time detection. Therefore, many variations on Hough's original transform have been proposed to alleviate the computational and storage burden. In this paper, an improved Hough transform for line detection is proposed, which shares the similar characteristic of the modified Hough transform (MHT) and the Windowed random Hough transform (RHT). The proposed method employs the "many-to-one" mapping and sliding window neighborhood technique to alleviate the computational and storage load. Extensive experiments indicate that the proposed method has achieved a much better performance than the previous variations of Hough transform.