2012 | OriginalPaper | Chapter
Improving the Efficiency and Accuracy of SIFT Image Matching
Authors : Daw-Tung Lin, Chin-Hui Hsu
Published in: Proceedings of the 2011 2nd International Congress on Computer Applications and Computational Science
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Developing an accurate mechanism of correspondence and increasing matching stability are crucial tasks in many computer vision applications. This work improves the accuracy and efficiency in image matching via a novel method. The Modifiable Area Harmony Dominating Rectification (MHDR) method is proposed to eliminate mismatched key-point couples automatically and protect matching couples. The matching performance of the proposed scheme was evaluated on a test image database and via the transformation of the shearing effect and thin-plate splines. Compared with other methods, including the Exhaustive Search, Best Bin Search, and Sliding Midpoint Splitting, the proposed method had promising results in improving the accuracy and efficiency of the SIFT image matching.