Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
527308 | Image and Vision Computing | 2008 | 14 Pages |
Abstract
A mathematical model of blob matching is developed in this paper. Based on the model, the matching performance of Bhattacharyya coefficient is analyzed and evaluated. The numerical critical conditions of biased matching and mistaken matching for Bhattacharyya coefficient are given. According to the model analysis, a modified version of Bhattacharyya coefficient is proposed, which improves the matching performance relative to the original one. The numerical analysis based on the new model and visual experiments both demonstrate the superior performance of the modified Bhattacharyya coefficient.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Na Lu, Zuren Feng,