Spiders as Robust Point Descriptors
This paper introduces a new operator to characterize a point in an image in a distinctive and invariant way. The robust recognition of points is a key technique in computer vision: algorithms for stereo correspondence, motion tracking and object recognition rely heavily on this type of operator. The goal in this paper is to describe the salient point to be characterized by a constellation of surrounding anchor points. Salient points are the most reliably localized points extracted by an interest point operator. The anchor points are multiple interest points in a visually homogenous segment surrounding the salient point. Because of its appearance, this constellation is called a spider. With a prototype of the spider operator, results in this paper demonstrate how a point can be recognized in spite of significant image noise, inhomogeneous change in illumination and altered perspective. For an example that requires a high performance close to object / background boundaries, the prototype yields better results than David Lowe’s SIFT operator.
KeywordsObject Recognition Anchor Point Interest Point Salient Point Sift Descriptor
Unable to display preview. Download preview PDF.
- 1.Forsyth, D.A., Ponce, J.: Computer Vision – A Modern Approach (2003)Google Scholar
- 3.Lowe, D.: Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision 60 (2004)Google Scholar
- 4.Mikolajczyk, K., Schmid, C.: Scale & Affine Invariant Interest Point Detectors. International Journal of Computer Vision 60 (2004)Google Scholar
- 5.Mikolajczyk, K., Zisserman, A., Schmid, C.: Shape recognition with edge-based features. In: Proceedings of the British Machine Vision Conference, Norwich, U.K. (2003)Google Scholar
- 6.Scharstein, D., Szeliski, R.: A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms. International Journal of Computer Vision 47 (2002)Google Scholar
- 7.Strang, G.: Introduction to Linear Algebra, 3rd edn. (2003)Google Scholar
- 8.Tuytelaars, T., Gool, L.V.: Matching Widely Separated Views Based on Affine Invariant Regions. International Journal of Computer Vision 59 (2004)Google Scholar