Share Email Print
cover

Proceedings Paper

Mesh based automatic image registration
Author(s): Dengfeng Chai; Qunsheng Peng
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents a novel method for automatic image registration. It represents image as triangular mesh and use triangle as feature primitive. First, it detects corner features and triangulates them into triangular mesh. Then, orrespondences of triangles from different images are established by evaluating the similarity of the triangular regions. Affine rectification is applied to establish pixel correspondences. Based on the triangle correspondences, the image transformation is estimated using RANSAC estimator. The proposed method is applied to various image pairs related by projective transformation, experimental results show that the method works successfully even under the case that there are large rotation or severe perspective deformation effect between the images.

Paper Details

Date Published: 4 November 2005
PDF: 6 pages
Proc. SPIE 6044, MIPPR 2005: Image Analysis Techniques, 604402 (4 November 2005); doi: 10.1117/12.652250
Show Author Affiliations
Dengfeng Chai, Zhejiang Univ. (China)
Qunsheng Peng, Zhejiang Univ. (China)


Published in SPIE Proceedings Vol. 6044:
MIPPR 2005: Image Analysis Techniques
Deren Li; Hongchao Ma, Editor(s)

© SPIE. Terms of Use
Back to Top