Object recognition by belief propagation

Tongwei Lu; Nong Sang; Jizhong Liu; Xiaoying Gao

doi:10.1117/1.2957950

Translator Disclaimer

1 July 2008 Object recognition by belief propagation

Tongwei Lu, Nong Sang, Jizhong Liu, Xiaoying Gao

Author Affiliations +

Optical Engineering, 47(7), 077205 (2008). https://doi.org/10.1117/1.2957950

Abstract

We try to incorporate a graphical model to solve the problem of object recognition, which is a fundamental problem in computer vision. Adopting the multiscale feature keypoint technique, we present an object recognition algorithm that establishes the center, scale factor, and rotation angle of the object in the images. First, the local invariant features are detected in template and scene images. Second, the belief propagation algorithm is used to compute the correspondence considering the spatial constraints. Third, each correspondence point records a vote to the object's center, scale factor, and rotation angle. Finally, we keep the densest point on the vote map as the recognition result. Experimental results demonstrate the robustness of the algorithm on real images.

©(2008) Society of Photo-Optical Instrumentation Engineers (SPIE)

Citation Download Citation

Tongwei Lu, Nong Sang, Jizhong Liu, and Xiaoying Gao "Object recognition by belief propagation," Optical Engineering 47(7), 077205 (1 July 2008). https://doi.org/10.1117/1.2957950

Published: 1 July 2008

ACCESS THE FULL ARTICLE