Intensity based image registration by minimizing the complexity of weighted subtraction under illumination changes

Abstract One crucial part of an image registration algorithm is utilization of an appropriate similarity metric. For common similarity metrics such as CC or MI, it is assumed that the intensities of image pixels are independent from each other and stationary. Accepting these assumptions, one will have difficulty doing image registration in the presence of spatially varying intensity distortion. In Myronenko et al. [5] a solution based on minimization of residual complexity is introduced to solve this problem. In this work, the weakness of RC method is investigated for more complex spatially varying intensity distortions and a modification of this method is presented to improve its performance in such conditions. The proposed method reduces the error respect to the other methods. Experimental results on synthetic and real-world data sets demonstrate the effectiveness of the proposed method for image registration tasks.

[1]  Alexander Wong,et al.  Robust Multimodal Registration Using Local Phase-Coherence Representations , 2009, J. Signal Process. Syst..

[2]  Nicholas Ayache,et al.  The Correlation Ratio as a New Similarity Measure for Multimodal Image Registration , 1998, MICCAI.

[3]  Michael Brady,et al.  MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration , 2012, Medical Image Anal..

[4]  Prem Kumar Kalra,et al.  An automatic image registration scheme using Tsallis entropy , 2010, Biomed. Signal Process. Control..

[5]  Olivier D. Faugeras,et al.  Dense image matching with global and local statistical criteria: a variational approach , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[6]  Mohamed M. Fouad,et al.  Geometric image registration under arbitrarily-shaped locally variant illuminations , 2012, Signal Image Video Process..

[7]  Jing Tian,et al.  Retinal image registration using topological vascular tree segmentation and bifurcation structures , 2015, Biomed. Signal Process. Control..

[8]  Jacqueline Le Moigne,et al.  Image Registration for Remote Sensing: Similarity Metrics for Image Registration , 2011 .

[9]  A. Ardeshir Goshtasby.  Image Registration: Principles, Tools and Methods , 2012 .

[10]  Wei Liu,et al.  A survey on image-based continuum-body motion estimation , 2011, Image Vis. Comput..

[11]  Leo Joskowicz,et al.  A curvelet-based patient-specific prior for accurate multi-modal brain image rigid registration , 2011, Medical Image Anal..

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

[13]  Emad Fatemizadeh,et al.  Robust Huber similarity measure for image registration in the presence of spatially-varying intensity distortion , 2015, Signal Process..

[14]  Mohsen Shirpour,et al.  A new similarity measure for intensity-based image registration , 2014, 2014 4th International Conference on Computer and Knowledge Engineering (ICCKE).

[15]  Maria Petrou,et al.  Image registration using the Walsh transform , 2006, IEEE Transactions on Image Processing.

[16]  Nassir Navab,et al.  Entropy and Laplacian images: Structural representations for multi-modal registration , 2012, Medical Image Anal..

[17]  Jan Modersitzki,et al.  Combining Homogenization and Registration , 2006, WBIR.

[18]  Stefano Soatto,et al.  Nonrigid registration combining global and local statistics , 2009, CVPR.

[19]  Qianjin Feng,et al.  Intensity based image registration by minimizing exponential function weighted residual complexity , 2013, Comput. Biol. Medicine.

[20]  Andriy Myronenko,et al.  Intensity-Based Image Registration by Minimizing Residual Complexity , 2010, IEEE Transactions on Medical Imaging.