Mutual Information Optimization Based Dynamic Log-Polar Image Registration

doi:10.1007/s12204-015-1589-8

Abstract

Abstract: Log-polar transformation (LPT) is widely used in image registration due to its scale and rotation invariant properties. Through LPT, rotation and scale transformation can be made into translation displacement in log-polar coordinates, and phase correlation technique can be used to get the displacement. In LPT based image registration, constant samples in digitalization processing produce less precise and effective results. Thus, dynamic log-polar transformation (DLPT) is used in this paper. DLPT is a method that generates several sample sets in axes to produce several results and only the effective results are used to get the final results by using statistical approach. Therefore, DLPT can get more precise and effective transformation results than the conventional LPT. Mutual information (MI) is a similarity measure to align two images and has been used in image registration for a long time. An optimal transform for image registration can be obtained by maximizing MI between the two images. Image registration based on MI is robust in noisy, occlusion and illumination changing circumstance. In this paper, we study image registration using MI and DLPT. Experiments with digitalizing images and with real image datasets are performed, and the experimental results show that the combination of MI with DLPT is an effective and precise method for image registration.

Key words: image registration| mutual information (MI)| log-polar transformation (LPT)| phase correlation technique

摘要： Log-polar transformation (LPT) is widely used in image registration due to its scale and rotation invariant properties. Through LPT, rotation and scale transformation can be made into translation displacement in log-polar coordinates, and phase correlation technique can be used to get the displacement. In LPT based image registration, constant samples in digitalization processing produce less precise and effective results. Thus, dynamic log-polar transformation (DLPT) is used in this paper. DLPT is a method that generates several sample sets in axes to produce several results and only the effective results are used to get the final results by using statistical approach. Therefore, DLPT can get more precise and effective transformation results than the conventional LPT. Mutual information (MI) is a similarity measure to align two images and has been used in image registration for a long time. An optimal transform for image registration can be obtained by maximizing MI between the two images. Image registration based on MI is robust in noisy, occlusion and illumination changing circumstance. In this paper, we study image registration using MI and DLPT. Experiments with digitalizing images and with real image datasets are performed, and the experimental results show that the combination of MI with DLPT is an effective and precise method for image registration.

关键词: image registration| mutual information (MI)| log-polar transformation (LPT)| phase correlation technique

CLC Number:

TP 391.4

ZHANG Kui* (张葵), ZHANG Xiao-long (张晓龙), XU Xin (徐新), FU Xiao-wei (付晓薇). Mutual Information Optimization Based Dynamic Log-Polar Image Registration[J]. Journal of shanghai Jiaotong University (Science), 2015, 20(1): 61-67.

References 18

[1]	Zitov′a B, Flusser J. Image registration methods: A survey [J]. Image and Vision Computing, 2003, 21(11):977-1000.
[2]	Dame A, Marchand E. Second order optimization of mutual information for real-time image registration [J].IEEE Transactions on Image Processing, 2012, 21(9):4190-4203.
[3]	Tzimiropoulos G, Argyriou V, Zafeiriou S, et al.Robust FFT-based scale-invariant image registration with image gradients [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(10):1899-1906.
[4]	Mohod N P, Ladhake S A. Polar transform in image registration [J]. International Journal of Advanced Research in Computer Science and Software Engineering,2013, 3(3): 603-606.
[5]	Baker S, Matthews I. Lucas-kanade 20 years on: A unifying framework [J]. International Journal of Computer Vision, 2004, 56(3): 221-255.
[6]	Reddy B S, Chatterji B N. An FFT-based technique for translation, rotation, and scale-invariant image registration [J]. IEEE Transactions on Image Processing,1996, 5(8): 1266-1271.
[7]	Stone H S, Orchard M T. Chang E C, et al. A fast direct Fourier-based algorithm for subpixel registration of images [J]. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(10): 2235-2243.
[8]	Vandewalle P, Susstrunk S, Vetterli M. A frequency domain approach to registration of aliased images with application to super-resolution [J].EURASIP Journal on Applied Signal Processing, 2006,1: 071459.
[9]	Zokai S, Wolberg G. Image registration using logpolar mappings for recovery of large-scale similarity and projective transformations [J]. IEEE Transactions on Image Processing, 2005, 14(10): 1422-1434.
[10]	Matungka R, Zheng Y F, Ewing R L. 2D invariant object recognition using log-polar transform [C]//7th World Congress on Intelligent Control and Automatio.Chongqing China: IEEE, 2008: 223-228.
[11]	Liu H, Guo B, Feng Z. Pseudo-log-polar fourier transform for image registration [J]. IEEE Signal Processing Letters, 2006, 13(1): 17-20.
[12]	Sarvaiya J N, Patnaik S, Kothari K. Image registration using log polar transform and phase correlation to recover higher scale [J]. Journal of Pattern Recognition Research, 2012, 7: 90-105.
[13]	Stone H, Orchard M, Chang E C. Subpixel registration of images [C]//Conference Record of 33rd Asilomar Conferenc on Signals, Systems, and Computers:Volume 2. Pacific Grove, CA, USA: IEEE, 1999: 1446-1452.
[14]	Zhang K, Zhang X L, Chen L, et al. Image registration using dynamic log-polar transformation [C]//2010 6th International Conference on Wireless Communications Networking and Mobile Computing. Chengdu China: IEEE, 2010: 1-4.
[15]	Shannon C. A mathematical theory of communication [J]. ACM SIGMOBILE Mobile Computing and Communications Review, 2001, 5(1): 3-55.
[16]	Pluim J P W, Maintz J B A, Viergever M A.Mutual-information-based registration of medical images:A survey [J]. IEEE Transactions on Medical Imaging, 2003, 22(8): 986-1004.
[17]	Ritter N, Owens O R, Cooper J, et al. Registration of stereo and temporal images of the retina [J]. IEEE Transactions on Medical Imaging, 1999, 18(5): 404-418.
[18]	Mikolajczyk K. Image database/feature detector evaluation sequences [EB/OL]. (2014-04-04).http://lear.inrialpes.fr/people/mikolajczyk.