A novel and robust axis extraction method
Bei Cao, Caiwen Ma, ZhenTao Liu · 2010 3rd International Congress on Image and Signal Processing · 2010
This paper presents a novel and robust method for accurately extracting axis equation from axis symmetry objects. Our method combines Hough transform with centroid analysis technique to output sub-pixel axis equation. It is robust even in imperfect image qualities for fully use of regional grayscale pixel values while not relying on edges of objects. The whole process requires no information other than the input grayscale images. The results illustrate that our method is capable of extracting accurate axis while achieving near real-time performance.