Linear feature detection based on the multi-scale, multi-structuring element, grey-level hit-or-miss transform. (August 2015)

• Record Type: Journal Article
• Authors: Bai, Xiangzhi; Wang, Tao; Zhou, Fugen
• Is Part Of: Computers & electrical engineering. Volume 46(2015)
• Page Start: 487
• Page End: 499
• Publication Date: 2015-08
• Subjects: Multi-scale -- Hit-or-miss transform -- Linear feature detection -- Mathematical morphology; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2015.05.014
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Multi-scale extension of multi-structuring elements for hit-or-miss transform. Utilizing the grey-level hit-or-miss transform for linear feature detection. Performing linear feature detection without thresholding. Abstract: Detecting the linear features in an image is a key technology for different applications. In this paper, a simple and effective algorithm based on the hit-or-miss transform is proposed. To detect linear features with different directions, multi-structuring elements corresponding to different directions are constructed. To detect linear features with different widths, a multi-scale extension of the constructed multi-structuring elements is used. Then, the grey-level hit-or-miss transform that utilizes the constructed multi-scales of multi-structuring elements could effectively extract all of the possible linear features without thresholding. Therefore, after refining the extracted linear feature regions using three simple steps, the final linear features could be effectively detected. Experimental results on different images from different applications show that the proposed algorithm performs well for detecting linear features with different widths, different grey distributions and noises.