Image Matching Based on Chain Code of Image Edge Tangent Direction Angle

Abstract:

In order to solve problem that the image which is under different wavelength channels can’t match in the ice detection whit the near infrared, this paper describes a solution of image matching which based on the chain code of angle related to a tangential direction of image edge. By extracting the edge with Canny, calculating the chain code of angle and differences, computing the relative chain code of direction angle and comparing the relative chain code, the possible rotation angle between the images will be gained. After rotating the image and differencing the corresponding coordinates, the shift amount can be obtained. Ultimately image match can be achieved. Experimental results show that this method is accuracy and have certain inhibition of noise.

• Periodical: Applied Mechanics and Materials (Volumes 58-60)
• Pages: 2284-2289
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.58-60.2284
• Online since: June 2011
• Authors: Jian Shu Gao, Wen Qiao, Ren Yi Han
• Keywords: Canny, Chain Code of Angle Direction, Image Match

References

[1] Weng Jiangtao, Wang Boxiong, Luo Xiuzhi, etc. Research of image matching based on edge detection and gray level gradient distributing features. The 7th International Symposium on Test and Measurement, 1602-1604.

[2] J. F. Canny: A computational approach to edge detection. IEEE Trans. Pattern Analysis and Machine Intelligence, 8 (6), 1986, 679-698.

DOI: 10.1109/tpami.1986.4767851

[3] Xu Jianhua. Image processing and analysis[M]. Beijing: Science Press, 1992: 176-177.

[4] Lu Zong qi, Tong Tao. The Application of Chain Code Sum in the Edge form Analysis[J]. Journal of Image and Graphics, Vol. 7(A), No. 12 Dec. 2002: 1323-1328.