¹College of Computer and Information Science, Chongqing Normal University, Chongqing, 400047, China
²Department education administration, Guizhou University of Finance and Economics, Guiyang, 550004, China

---

Abstract—This paper proposes a method for line matching based on invariance of feature points. Firstly, feature points are roughly matched by Normalized Cross Correlation (NNC) and Average of Square Difference (ASD). Additionally, feature points obtained from the two views are grouped into matched point pairs. Finally, curve segments between matched point pairs are matched by dynamic programming algorithm with edge potential functions (EPF) taken as the measure. The proposed method makes full use of feature points, the relationship between feature points and the curve, and space information of the gray image.

Index Terms—Feature Point; Dynamic Programming; Edge Potential Functions; Curve Potential Function; line matching.

[PDF]

Cite: Yanxia Wang, Yan Ma, and Qixin Chen, "A Method of Line Matching Based on Feature Points," Journal of Software vol. 7, no. 7, pp. 1539-1545, 2012.