Graph Based Image Matching Using the Fusion of Several Kinds of Features

We exploit the image saliency, grayscale and RGB information to find feature correspondence based on a graph matching technique. We consider these saliency features, grayscale and average RGB values along with distance information for extracted image features by using a detector-descriptor combination of MSER detector and SIFT Descriptor. Three different affinity matrices are introduced by utilizing single pixel values collected by using the feature vector coordinates from three different forms of the same images. Considerable improvements in image matching performance are obtained while these affinity matrices are combined separately with the distance-based affinity matrix.

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

[2]  Hong Shen,et al.  Learning a hybrid similarity measure for image retrieval , 2013, Pattern Recognit..

[3]  Shi-Min Hu,et al.  Global contrast based salient region detection , 2011, CVPR 2011.

[4]  Andrea Torsello,et al.  Matching as a non-cooperative game , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[5]  Minsu Cho,et al.  Reweighted Random Walks for Graph Matching , 2010, ECCV.

[6]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[7]  Xiaoping Liu,et al.  Automatic Registration of Multisensor Images Using an Integrated Spatial and Mutual Information (SMI) Metric , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Yael Pritch,et al.  Saliency filters: Contrast based filtering for salient region detection , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Martial Hebert,et al.  A spectral technique for correspondence problems using pairwise constraints , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[10]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[11]  Yong Ma,et al.  Image Feature Matching via Progressive Vector Field Consensus , 2015, IEEE Signal Processing Letters.

[12]  Hwann-Tzong Chen,et al.  Multi-object tracking using dynamical graph matching , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[13]  King Ngi Ngan,et al.  Unsupervised Salient Object Segmentation Based on Kernel Density Estimation and Two-Phase Graph Cut , 2012, IEEE Transactions on Multimedia.

[14]  Weiqiang Wang,et al.  Retrieving images using saliency detection and graph matching , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[15]  Lihi Zelnik-Manor,et al.  Context-Aware Saliency Detection , 2012, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Chris H. Q. Ding,et al.  A Local Sparse Model for Matching Problem , 2015, AAAI.

[17]  Huchuan Lu,et al.  Hierarchical Cellular Automata for Visual Saliency , 2017, International Journal of Computer Vision.

[18]  Xiaochun Cao,et al.  Lagrangian relaxation graph matching , 2017, Pattern Recognit..

[19]  Nuno Vasconcelos,et al.  The discriminant center-surround hypothesis for bottom-up saliency , 2007, NIPS.

[20]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[21]  Jianbo Shi,et al.  Balanced Graph Matching , 2006, NIPS.

[22]  Ali Borji,et al.  Exploiting local and global patch rarities for saliency detection , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Jean Ponce,et al.  A graph-matching kernel for object categorization , 2011, 2011 International Conference on Computer Vision.

[24]  Jacqueline Le Moigne,et al.  An automated parallel image registration technique based on the correlation of wavelet features , 2013, IEEE Trans. Geosci. Remote. Sens..

[25]  Yao Lu,et al.  Salient Object Detection using concavity context , 2011, 2011 International Conference on Computer Vision.

[26]  Minsu Cho,et al.  Feature correspondence and deformable object matching via agglomerative correspondence clustering , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[27]  Jordi Inglada,et al.  Analysis of Artifacts in Subpixel Remote Sensing Image Registration , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[28]  Laurent Itti,et al.  An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[29]  S. Süsstrunk,et al.  Frequency-tuned salient region detection , 2009, CVPR 2009.

[30]  Shuicheng Yan,et al.  Common visual pattern discovery via spatially coherent correspondences , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[31]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

[32]  H. Barlow.  Vision Science: Photons to Phenomenology by Stephen E. Palmer , 2000, Trends in Cognitive Sciences.

[33]  Nanning Zheng,et al.  Learning to Detect a Salient Object , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Jitendra Malik,et al.  Shape matching and object recognition using low distortion correspondences , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[35]  Simone Frintrop,et al.  Center-surround divergence of feature statistics for salient object detection , 2011, 2011 International Conference on Computer Vision.

[36]  Nanning Zheng,et al.  Exploiting local linear geometric structure for identifying correct matches , 2014, Comput. Vis. Image Underst..