An Extraction Approach to Building Straight Lines Based on Hough Transform
Detecting lines in a digital image is a crucial step in many applications, such as visual navigation, feature recognition. In this paper, an algorithm which is based on part Hough transform is proposed for extracting straight lines from building image. Firstly, edges are detected based on Canny detector. Secondly, An algorithm that follows image boundary categorizes edges. Thirdly, Hough transformation extracts straight lines to each classification of image. Experiment results shows that the proposed algorithm is better than Hough transform. It can detect lines correctly in building images with high accuracy, low false detection and low missing detection.
KeywordsImage Space Peak Detection Edge Point Hough Transform Collinear Point
Unable to display preview. Download preview PDF.
- 3.Deng, B., Gao, Y., Yang, B., Wu, L.: A New Algorithm for Linear Features Extraction and Orientation. Computer Engineering 32, 198–202 (2006)Google Scholar
- 4.Liu, X., Xiang, J., Yang, B.: A Labeling Algorithm Based on 8-Connected Boundary Tracking. Computer Engineering and Application 37, 126–127 (2001)Google Scholar
- 5.Teng, J.-Z., Qiu, J.: Fast and Precise Detection of Straight Line with Hough Transform. Journal of Image and Graphics 13, 234–237 (2008)Google Scholar
- 6.Zhang, C.: Auto-Position Detection of Spatial Points Based on Hough Transformation. Computer Engineering 32, 200–202 (2006)Google Scholar