Title :
Asymmetric region-to-image matching for comparing images with generic object categories
Author :
Kim, Jaechul ; Grauman, Kristen
Author_Institution :
Univ. of Texas at Austin, Austin, TX, USA
Abstract :
We present a feature matching algorithm that leverages bottom-up segmentation. Unlike conventional image-to-image or region-to-region matching algorithms, our method finds corresponding points in an “asymmetric” manner, matching features within each region of a segmented image to a second unsegmented image. We develop a dynamic programming solution to efficiently identify corresponding points for each region, so as to maximize both geometric consistency and appearance similarity. The final matching score between two images is determined by the union of corresponding points obtained from each region-to-image match. Our encoding for the geometric constraints makes the algorithm flexible when matching objects exhibiting non-rigid deformations or intra-class appearance variation. We demonstrate our image matching approach applied to object category recognition, and show on the Caltech-256 and 101 datasets that it outperforms existing image matching measures by 10~20% in nearest-neighbor recognition tests.
Keywords :
dynamic programming; feature extraction; image matching; image segmentation; object recognition; Caltech 101 dataset; Caltech-256 dataset; appearance similarity; asymmetric region-to-image matching; bottom-up segmentation; comparing images; dynamic programming solution; feature matching algorithm; generic object category; geometric consistency; geometric constraints; image matching approach; image matching measures; image-to-image matching algoritms; intraclass appearance variation; nearest-neighbor recognition tests; nonrigid deformations; object category recognition; region-to-region matching algorithms; unsegmented image; Computer vision; Distortion measurement; Dynamic programming; Encoding; Image matching; Image recognition; Image retrieval; Image segmentation; Object recognition; Testing;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
978-1-4244-6984-0
DOI :
10.1109/CVPR.2010.5539923