Image Mosaics Algorithm Based on SIFT Feature Point Matching and Transformation Parameters Automatically Recognizing

DOI

10.2991/iccsee.2013.392How to use a DOI?

Keywords

SIFT, Image mosaic, Feature point matching, Automatic recognize of transformation parameters

Abstract

A mosaic algorithm of different scale image registration and adaptive is proposed in this thesis, against to the large amount of calculation and poor robustness, as well as cannot well solve the problem of image mosaic of images who are in different scales in the traditional image mosaic method. The match and mosaic of different scale and rotated images is achieved through feature point matching and automatically recognizing of transform geometric parameters between images. First, using SIFT extraction algorithm to extract the feature points of the image to be mosaic. Second, achieving feature points matching according to the principal of mutual information maximum. Third, automatically recognize the relationship of transformation parameters between two images according to the geometric information of the matching pairs. Finally, the projective transformation matrix that reflected the image translation, rotation and scaling information can be obtained and the image stable mosaic can be achieved.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Pengrui Qiu
AU  - Ying Liang
AU  - Hui Rong
PY  - 2013/03
DA  - 2013/03
TI  - Image Mosaics Algorithm Based on SIFT Feature Point Matching and Transformation Parameters Automatically Recognizing
BT  - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
PB  - Atlantis Press
SP  - 1560
EP  - 1563
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccsee.2013.392
DO  - 10.2991/iccsee.2013.392
ID  - Qiu2013/03
ER  -