Title :
A fast method for image mosaic based on SURF
Author :
Fei Lei ; Wenxue Wang
Author_Institution :
Electron. Inf. & Control Eng. Coll., Beijing Univ. of Technol., Beijing, China
Abstract :
This article presents a fast method for image mosaic based on SURF. The method includes three principal steps: Firstly, the feature points are extracted using SURF operator and the feature points are matched using BBF algorithm; Secondly, image registration is completed by estimating the converting relationship between images with the RANSAC and least squares method; Finally, seamless image fusion is obtained by using Gradating in-and-out amalgamation algorithm, which can reduce the effects of seams and illumination variations. The experimental results demonstrate that this method has superior quality of stitching.
Keywords :
feature extraction; image fusion; image matching; image registration; image segmentation; least squares approximations; BBF algorithm; RANSAC; SURF operator; feature point extraction; gradating in-and-out amalgamation algorithm; image mosaic; image registration; least squares method; seamless image fusion; stitching quality; Convolution; Educational institutions; Feature extraction; Image fusion; Image registration; Robustness; Vectors; BBF; Gradating in-and-out; RANSAC; SURF; image mosaic;
Conference_Titel :
Industrial Electronics and Applications (ICIEA), 2014 IEEE 9th Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-4799-4316-6
DOI :
10.1109/ICIEA.2014.6931135
