Share Email Print

Proceedings Paper

An improved SIFT algorithm based on KFDA in image registration
Author(s): Peng Chen; Lijuan Yang; Jinfeng Huo
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

As a kind of stable feature matching algorithm, SIFT has been widely used in many fields. In order to further improve the robustness of the SIFT algorithm, an improved SIFT algorithm with Kernel Discriminant Analysis (KFDA-SIFT) is presented for image registration. The algorithm uses KFDA to SIFT descriptors for feature extraction matrix, and uses the new descriptors to conduct the feature matching, finally chooses RANSAC to deal with the matches for further purification. The experiments show that the presented algorithm is robust to image changes in scale, illumination, perspective, expression and tiny pose with higher matching accuracy.

Paper Details

Date Published: 2 March 2016
PDF: 10 pages
Proc. SPIE 9901, 2nd ISPRS International Conference on Computer Vision in Remote Sensing (CVRS 2015), 99010G (2 March 2016); doi: 10.1117/12.2234856
Show Author Affiliations
Peng Chen, Hubei Key Lab. of Intelligent Vision-based Monitoring for Hydroelectric Engineering (China)
China Three Gorges Univ. (China)
Lijuan Yang, China Three Gorges Univ. (China)
Jinfeng Huo, China Three Gorges Univ. (China)

Published in SPIE Proceedings Vol. 9901:
2nd ISPRS International Conference on Computer Vision in Remote Sensing (CVRS 2015)
Cheng Wang; Rongrong Ji; Chenglu Wen, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?