Registration of Images With Outliers Using Joint Saliency Map

Mutual information (MI) is a popular similarity measure for image registration, whereby good registration can be achieved by maximizing the compactness of the clusters in the joint histogram. However, MI is sensitive to the ldquooutlierrdquo objects that appear in one image but not the other, and also suffers from local and biased maxima. We propose a novel joint saliency map (JSM) to highlight the corresponding salient structures in the two images, and emphatically group those salient structures into the smoothed compact clusters in the weighted joint histogram. This strategy could solve both the outlier and the local maxima problems. Experimental results show that the JSM-MI based algorithm is not only accurate but also robust for registration of challenging image pairs with outliers.

• Publication year

  2013

• Venue

  IEEE Signal Processing Letters

• Publication date

  2013-03-29

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/LSP.2009.2033728arXiv 1304.8052
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Distinctive Image Features from Scale-Invariant Keypoints Abstract by Matthijs Dorst Based on the paper by

  2011cited by this paper
• Registration of Cervical MRI Using Multifeature Mutual Information

  2009cited by this paper
• Accelerated Nonrigid Intensity-Based Image Registration Using Importance Sampling

  2009cited by this paper
• DRAMMS: Deformable Registration via Attribute Matching and Mutual-Saliency Weighting

  2009cited by this paper
• Maximum distance-gradient for robust image registration

  2008cited by this paper
• Multimodal image registration using floating regressors in the joint intensity scatter plot

  2008cited by this paper
• Multimodality image registration by maximization of quantitative-qualitative measure of mutual information

  2008cited by this paper
• Robust adaptive non-rigid image registration based on joint salient point sets in the presence of tumor-like gross outliers

  2007cited by this paper
• Multi-modal and Multi-temporal Image Registration in the Presence of Gross Outliers Using Feature Voxel-Weighted Normalized Mutual Information

  2006cited by this paper
• Region Enhanced Scale-Invariant Saliency Detection

  2006cited by this paper
• 3-D/2-D registration by integrating 2-D information in 3-D

  2006cited by this paper
• An automatic nonrigid registration for stained histological sections

  2005cited by this paper
• Phase mutual information as a similarity measure for registration

  2005influential reference
• Distinctive Image Features from Scale-Invariant Keypoints

  2004cited by this paper
• High-dimensional mutual information estimation for image registration

  2004influential reference
• Image Similarity Using Mutual Information of Regions

  2004influential reference
• Interpolation artifacts in multimodality image registration based on maximization of mutual information

  2003cited by this paper
• Spatial transformations of diffusion tensor magnetic resonance images

  2001cited by this paper
• A global optimisation method for robust affine registration of brain images

  2001cited by this paper
• A hierarchical approach to elastic registration based on mutual information

  2001cited by this paper
• Computational modelling of visual attention

  2001cited by this paper
• Saliency, Scale and Image Description

  2001cited by this paper
• Image registration by maximization of combined mutual information and gradient information

  2000influential reference
• An overlap invariant entropy measure of 3D medical image alignment

  1999cited by this paper
• Multimodality image registration by maximization of mutual information

  1997influential reference
• Alignment by Maximization of Mutual Information

  1995cited by this paper

• “A net for everyone”: fully personalized and unsupervised neural networks trained with longitudinal data from a single patient

  2022cites this paper
• Camera fusion for real-time temperature monitoring of neonates using deep learning

  2022cites this paper
• Extracting heterogeneous vessels in X-ray coronary angiography via machine learning

  2022cites this paper
• Salient video object detection using a virtual border and guided filter

  2020cites this paper
• Targeted Fusion Biopsy of the Prostate

  2019cites this paper
• Accurate vessel extraction via tensor completion of background layer in X-ray coronary angiograms

  2019cites this paper
• A saliency-weighted orthogonal regression-based similarity measure for entropic graphs

  2019cites this paper
• Joint-Saliency Structure Adaptive Kernel Regression with Adaptive-Scale Kernels for Deformable Registration of Challenging Images

  2018cites this paper
• Medical image registration in image guided surgery: Issues, challenges and research opportunities

  2017cites this paper
• Comparative Evaluation of Registration Algorithms in Different Brain Databases With Varying Difficulty: Results and Insights

  2014cites this paper
• A new similarity measure for intensity-based image registration

  2014cites this paper
• Structure matching driven by joint-saliency-structure adaptive kernel regression

  2013cites this paper
• Scale Selection of Adaptive Kernel Regression by Joint Saliency Map for Nonrigid Image Registration

  2013cites this paper
• Robust Multisensor Image Matching Using Bayesian Estimated Mutual Information

  2013cites this paper
• Volume sweeping and bodyline matching for automated prealignment in volumetric medical image registration

  2012cites this paper
• An Improved Hybrid Model for Automatic Salient Region Detection

  2012cites this paper
• Entropy-based image registration method using the curvelet transform

  2012cites this paper
• Image based representation for 3D content delivery.

  2012cites this paper
• Local Dominant Orientation Based Mutual Information for Multisensor Template Matching

  2011cites this paper
• Geometrical regularization of nonrigid registration using local anisotropic structure and joint saliency map

  2011cites this paper
• Application of Improved Genetic Algorithm in Practical Medical Image Registration

  2011cites this paper
• Nonrigid Registration of Brain Tumor Resection MR Images Based on Joint Saliency Map and Keypoint Clustering

  2009cites this paper