21 November 1995 Object recognition by multiresolutional template matching
Author Affiliations +
Proceedings Volume 2606, Digital Image Storage and Archiving Systems; (1995) https://doi.org/10.1117/12.227252
Event: Photonics East '95, 1995, Philadelphia, PA, United States
A novel and efficient pose-invariant guided template matching algorithm, for object recognition in images, is proposed. Template matching is performed in a rotation-scale- translation (pose) invariant fashion, thus greatly reducing the 4-d search space to a single point. The invariance is achieved by preprocessing the input image and associating certain geometric descriptors with the objects in the image. These descriptors completely characterize the affine parameters associated with the objects which must be applied to candidate templates, and the location in the image where the template is to be applied for a match. Preprocessing and matching are performed on a wavelet pyramidal decomposition of the image in a multiresolutional coarse-to-fine fashion for computational efficiency. An efficient search strategy is also proposed for selecting templates in the template database.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lakshman Prasad, Lakshman Prasad, Ramana L. Rao, Ramana L. Rao, } "Object recognition by multiresolutional template matching", Proc. SPIE 2606, Digital Image Storage and Archiving Systems, (21 November 1995); doi: 10.1117/12.227252; https://doi.org/10.1117/12.227252


Back to Top