17 August 1994 Object recognition by cost minimization
Author Affiliations +
Proceedings Volume 2357, ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision; (1994) https://doi.org/10.1117/12.182904
Event: Spatial Information from Digital Photogrammetry and Computer Vision: ISPRS Commission III Symposium, 1994, Munich, Germany
Abstract
Since the analogy between images and statistical mechanics systems was made, numerous research projects have been done to solve problems of image processing by the use of iterative methods. In this paper, we investigate cost functions in image processing and present a general expression and common requirements for cost functions. Meanwhile, we construct cost functions for object recognition. Although the cost functions are defined with geometric errors or radiometric errors, they measure errors in the two domains and their minimum corresponds to the same prediction without any errors in both domains. An optimization procedure is performed to reach the expected result with the minimum cost. The most noticeable characteristic of the method is that it is not sensitive to noise and works remarkably well in the presence of high noise level.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Liu Lu, Liu Lu, Fang Luo, Fang Luo, Nanno J. Mulder, Nanno J. Mulder, } "Object recognition by cost minimization", Proc. SPIE 2357, ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision, (17 August 1994); doi: 10.1117/12.182904; https://doi.org/10.1117/12.182904
PROCEEDINGS
6 PAGES


SHARE
Back to Top