Title :
Corner Point Detection on Digital Curve through Rotate-Angle Accumulation
Author_Institution :
Sch. of Mech. Eng., Jimei Univ., Xiamen, China
Abstract :
A method based on rotate-angle accumulation is presented to detect the corner points on digital curve. By constructing a rotate-angle accumulation curve and its curvature waves, the intersections points are detected firstly, then the rotate-angle accumulation curve which doesn´t include intersection point is segmented to fit in straight line through the curvature waves, lastly the tangent points are determined according to the intersection point of every two adjacent fitted straight line. The method does not need in advance to give a threshold value and the detection accuracy was less affected by noise. Experiments show that the method is efficient for detection and localization.
Keywords :
curve fitting; image segmentation; corner point detection; digital curve; image segmentation; rotate-angle accumulation; Computed tomography; Equations; Fellows; Filters; Gaussian noise; Mechanical engineering; Pixel; Smoothing methods; Vectors;
Conference_Titel :
Image and Signal Processing, 2009. CISP '09. 2nd International Congress on
Conference_Location :
Tianjin
Print_ISBN :
978-1-4244-4129-7
Electronic_ISBN :
978-1-4244-4131-0
DOI :
10.1109/CISP.2009.5304759