Image registration based on SIFT features and adaptive RANSAC transform

Scale invariant feature transform (SIFT) is one of the most applicable algorithms used in the image registration problem for extracting and matching of the features. One of the efficient methods in reducing mismatches in this algorithm is the RANdom SAmple Consensus (RANSAC) method. Besides the applicability of RANSAC, its threshold value is fixed, and it is empirically chosen. In this paper, a new method is proposed where the threshold value is calculated based on the variance between the correct matches' and of mismatches classes. Simulation results confirm the superiority of the chosen threshold in different situations in comparison with classic RANSAC algorithms in terms of CMR and FMR.

[1]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[2]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[3]  Yuanxin Ye,et al.  A local descriptor based registration method for multispectral remote sensing images with non-linear intensity differences , 2014 .

[4]  Ye Zhao,et al.  Visual summarization of image collections by fast RANSAC , 2016, Neurocomputing.

[5]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[6]  Chiou-Ting Hsu,et al.  Multiresolution feature-based image registration , 2000, Visual Communications and Image Processing.

[7]  Feng Wang,et al.  Adapted Anisotropic Gaussian SIFT Matching Strategy for SAR Registration , 2015, IEEE Geoscience and Remote Sensing Letters.

[8]  Bin Li,et al.  Image Matching Based on Two-Column Histogram Hashing and Improved RANSAC , 2014, IEEE Geoscience and Remote Sensing Letters.

[9]  Chia-Ling Tsai,et al.  The Edge-Driven Dual-Bootstrap Iterative Closest Point Algorithm for Registration of Multimodal Fluorescein Angiogram Sequence , 2010, IEEE Transactions on Medical Imaging.

[10]  Badrinath Roysam,et al.  Image change detection algorithms: a systematic survey , 2005, IEEE Transactions on Image Processing.

[11]  Long Wang,et al.  Registration of images with affine geometric distortion based on Maximally Stable Extremal Regions and phase congruency , 2015, Image Vis. Comput..

[12]  Jianghai Hu,et al.  A Multistage Approach for Image Registration , 2016, IEEE Transactions on Cybernetics.

[13]  Hongjian You,et al.  BFSIFT: A Novel Method to Find Feature Matches for SAR Image Registration , 2012, IEEE Geoscience and Remote Sensing Letters.

[14]  M. Garreau,et al.  Medical image registration using Edgeworth-based approximation of Mutual Information , 2014 .

[15]  Xiangyang Xu,et al.  SIFT Feature Point Matching Based on Improved RANSAC Algorithm , 2013, 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics.

[16]  Long Wang,et al.  Similarity-based multimodality image fusion with shiftable complex directional pyramid , 2011, Pattern Recognit. Lett..

[17]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[18]  Arturo Espinosa-Romero,et al.  A robust Graph Transformation Matching for non-rigid registration , 2009, Image Vis. Comput..