A New Method for Feature Point Matching: Inner and Exterior Product

Abstract:

In this paper, a novel feature descriptor called gradient correlation descriptor (GCD) is proposed. The GCD descriptor uses the gradient correlation measure defined by the inner and exterior product to characterize the gradient distributions in neighborhoods of feature points, and it has the following advantages: Its construction is very simple because of only the inner and exterior product operations are used; Its distinctive performance is better than the region-based SIFT descriptors since the gradient correlation measure can effectively characterize the gradient distributions in neighborhoods of feature points; In the gradient correlation measure the use of gradient mean makes it is not sensitive to the estimate precision of main orientation of feature point, and thus can provide a better stabilization to image rotation; The gradient correlation measure makes it also has very good adaptability to image affine transform, image blur, JPEG compression as well as illumination change.

• Periodical: Applied Mechanics and Materials (Volumes 48-49)
• Pages: 79-83
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.48-49.79
• Online since: February 2011
• Authors: Xu Guang Wang, Li Jun Lin, Hai Yan Cheng
• Keywords: Exterior Product, Feature Matching, GCD Descriptor, Inner Product, SIFT

References

[1] Moravec H, in: Rover visual obstacle avoidance [J]. International Joint Conference on Artificial Intelligence. (1981).

[2] Freeman W and Adelson E, in: The design and use of steerable filters [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(9): 891–906, (1991).

DOI: 10.1109/34.93808

[3] Pal N R and Pal S K, in: A review on image segmentation techniques [J]. Pattern Recognition, 26(9): 1277–1294, (1993).

DOI: 10.1016/0031-3203(93)90135-j

[4] Lowe D G, in: Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 60(2): 91–110, (2004).

DOI: 10.1023/b:visi.0000029664.99615.94

[5] Belongie S, Malik J, and Puzicha J, in: Shape matching and object recognition using shape contexts [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(4): 509–522, (2002).

DOI: 10.1109/34.993558