Author : Dakshayani N 1
Date of Publication :7th May 2016
Abstract: Recognition of objects in a scene containing multiple objects is a primary challenge that has only in recent times been broadly undertaken by computer vision systems. This paper proposes a new technique how to identify a particular object in jumbled scenes, given a reference image of the object. This paper represents an algorithm for recognizing a particular object based on finding feature points correspondences between the reference and the target image. It can detect objects in spite of a scale change or orientation. It is also robust to small amount of occlusion.
Reference :
-
[1] A. R. Ahmadyfard and J. Kittler, “A multiple classifier system approach to affine invariant object recognition,” in Computer Vision Systems, Springer, 2003, pp. 438–447.
[2] D. G. Lowe, “Object recognition from local scaleinvariant features,” in Computer vision, 1999. The proceedings of the seventh IEEE international conference on, 1999, vol. 2, pp. 1150–1157.
[3] D. L. Waltz, “Generating semantic description from drawings of scenes with shadows,” 1972.
[4] S. U. R. F. (SURF),“Herbet bay, andreas ess, tinne tuytelaars, luc van gool”, Elsevier preprint, 2008.
[5] University of Koblenz-Landau, Tech. Rep., 2009.
[6]Jacob Toft Pedersen,"Study group SURF: Feature detection & description".