Zhu, Y and Cheng, Samuel and Stankovic, Vladimir and Stankovic, Lina (2013) Image registration using BP-SIFT. Journal of Visual Communication and Image Representation, 24 (4). pp. 448-457. ISSN 1047-3203Full text not available in this repository. (Request a copy from the Strathclyde author)
Scale Invariant Feature Transform (SIFT) is a powerful technique for image registration. Although SIFT descriptors accurately extract invariant image characteristics around keypoints, the commonly used matching approaches of registration loosely represent the geometric information among descriptors. In this paper, we propose an image registration algorithm named BP-SIFT, where we formulate keypoint matching of SIFT descriptors as a global optimization problem and provide a suboptimum solution using belief propagation (BP). Experimental results show significant improvement over conventional SIFT-based matching with reasonable computation complexity.
|Keywords:||image registration, belief propagation, min-sum algorithm, keypoint matching, descriptors matching, image processing, Electrical engineering. Electronics Nuclear engineering, Media Technology, Signal Processing, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering|
|Subjects:||Technology > Electrical engineering. Electronics Nuclear engineering|
|Department:||Faculty of Engineering > Electronic and Electrical Engineering|
|Depositing user:||Pure Administrator|
|Date Deposited:||30 Apr 2014 13:09|
|Last modified:||24 Mar 2017 08:46|