A fast eliminating translational deviation method in template matching. (30th July 2014)

• Record Type: Journal Article
• Authors: Chen, Fang; Zhang, Cunji; Shi, Jinfei; Chen, Ping
• Is Part Of: International journal of computer applications technology. Volume 50:Number 1/2(2014)
• Page Start: 131
• Page End: 136
• Publication Date: 2014-07-30
• Subjects: machine vision -- image sequences -- image matching -- straight profile -- template; Technology -- Data processing -- Periodicals; 620.00285
• Languages: English
• ISSNs: 0952-8091

Abstract

To achieve accurate measurements of large scale machine parts with machine vision techniques, a new image matching method for image sequences is selected. And the matching method is one of the most critical influences on measuring speed and measuring precision. This paper aims at improving measuring speed. The proposed method bases on a straight profile. It mainly consists of two stages: One is adjusting image sequences to the same direction of coordinate axis to eliminate rotating deviation. It is realised by searching the straight profile with chain code. The other is sequences matching to eliminate translational deviation. The new algorithm focuses on eliminating translational deviation. It makes good use of differences of nearest neighbour grey values. Two templates are taken separately from two neighbour sequences. Those templates complete matching by the minimum value of the sum of adjacent-pixel-difference. In experiments, the new method is contrasted with the classical algorithm of the normalised cross correlation method. Experimental result demonstrates that the proposed algorithm is more effective than the NCC for image matching.