Title :
An automatic method for image mosaic based on feature matching
Author_Institution :
Dept. of Control Eng., Acad. of Armored Forces Eng., Beijing, China
Abstract :
In this paper, an automatic image mosaic algorithm based on feature matching is presented. In the algorithm, a scale invariant feature transform (SIFT) is used to extract feature points. The initial matches are divided into inliers and outliers by robust RANSAC algorithm. Then LM algorithm is used to estimate the point transformation matrix between two images accurately. In the end, weighted average method is used to blend images. Experimental results show the image mosaic effect is wonderful and the algorithm is adaptive very much. It is high valuable in practice.
Keywords :
feature extraction; image matching; image segmentation; automatic image mosaic algorithm; blend images; feature extraction; feature matching; point transformation matrix; robust RANSAC algorithm; scale invariant feature transform; weighted average method; Electrical engineering; Feature extraction; Frequency modulation; Pattern recognition; Robustness; System-on-a-chip; Transforms; feature extraction; feature matching; image mosaic; optimal estimating;
Conference_Titel :
Electric Information and Control Engineering (ICEICE), 2011 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-8036-4
DOI :
10.1109/ICEICE.2011.5777315
