Image Mosaic Algorithm and Its Application to the Microimage of Grass Seeds

DOI

10.2991/isca-13.2013.31How to use a DOI?

Keywords

image mosaic, SIFT, RANSAC, adaptive Gamma correction

Abstract

This paper presents an image mosaic algorithm and its application to the microimage of grass seeds. The following main steps are involved, firstly in the registration stage, the scale invariant feature transform (SIFT) is employed to obtain initial matches. Then the Random Sample Consensus (RANSAC) is used to remove incorrect matches effectively. Finally in the fusion stage, fade-in and fade-out method is applied to smooth seams which exist in the stitched image. Since the effect is not obvious, the adaptive Gamma correction method is used to weaken illumination effect on image quality to obtain a stitched image, which contains more information than each of the original images. Experimental results demonstrate that the proposed approach achieves good performance for grass seeds microimage mosaic in both subjective and objective evaluations.

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  - Lina Ning
AU  - Xin Pan
AU  - Lin Zhai
AU  - Fan Han
PY  - 2013/10
DA  - 2013/10
TI  - Image Mosaic Algorithm and Its Application to the Microimage of Grass Seeds
BT  - Proceedings of 2013 International Conference on Information Science and Computer Applications
PB  - Atlantis Press
SP  - 179
EP  - 184
SN  - 1951-6851
UR  - https://doi.org/10.2991/isca-13.2013.31
DO  - 10.2991/isca-13.2013.31
ID  - Ning2013/10
ER  -