Patch Alignment Manifold Matting

Image matting is generally modeled as a space transform from the color space to the alpha space. By estimating the alpha factor of the model, the foreground of an image can be extracted. However, there is some dimensional information redundancy in the alpha space. It usually leads to the misjudgments of some pixels near the boundary between the foreground and the background. In this paper, a manifold matting framework named Patch Alignment Manifold Matting is proposed for image matting. In particular, we first propose a part modeling of color space in the local image patch. We then perform whole alignment optimization for approximating the alpha results using subspace reconstructing error. Furthermore, we utilize Nesterov’s algorithm to solve the optimization problem. Finally, we apply some manifold learning methods in the framework, and obtain several image matting methods, such as named ISOMAP matting and its derived Cascade ISOMAP matting. The experimental results reveal that the manifold matting framework and its two examples are effective when compared with several representative matting methods.

[1]  Xuelong Li,et al.  Patch Alignment for Dimensionality Reduction , 2009, IEEE Transactions on Knowledge and Data Engineering.

[2]  Kilian Q. Weinberger,et al.  Unsupervised Learning of Image Manifolds by Semidefinite Programming , 2004, CVPR.

[3]  Ling Shao,et al.  Targeting Accurate Object Extraction From an Image: A Comprehensive Study of Natural Image Matting , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Ying Wu,et al.  Locality Versus Globality: Query-Driven Localized Linear Models for Facial Image Computing , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[5]  Xuelong Li,et al.  A survey of graph edit distance , 2010, Pattern Analysis and Applications.

[6]  Jian Sun,et al.  Fast matting using large kernel matting Laplacian matrices , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  Michael F. Cohen,et al.  Image and Video Matting: A Survey , 2007, Found. Trends Comput. Graph. Vis..

[8]  David Salesin,et al.  A Bayesian approach to digital matting , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[9]  Richard Szeliski,et al.  Light field layer matting , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Hui Zhou,et al.  Automatic defocus spectral matting , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[11]  Aykut Erdem,et al.  Image Matting with KL-Divergence Based Sparse Sampling , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[12]  Carlo Tomasi,et al.  Alpha estimation in natural images , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[13]  Jianzhong Wang Maximum Variance Unfolding , 2012 .

[14]  Xuelong Li,et al.  Superpixel fats for fast foreground extraction , 2015, 2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP).

[15]  Kaizhu Huang,et al.  MTC: A Fast and Robust Graph-Based Transductive Learning Method , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[16]  Jiaya Jia,et al.  Deep Automatic Portrait Matting , 2016, ECCV.

[17]  Ying Zhang,et al.  Learning a Probabilistic Topology Discovering Model for Scene Categorization , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[18]  Xuelong Li,et al.  Lazy Random Walks for Superpixel Segmentation , 2014, IEEE Transactions on Image Processing.

[19]  Yide Ma,et al.  Region-Based Object Recognition by Color Segmentation Using a Simplified PCNN , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[20]  Rüdiger Westermann,et al.  RANDOM WALKS FOR INTERACTIVE ALPHA-MATTING , 2005 .

[21]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[22]  Pascal Fua,et al.  What Players do with the Ball: A Physically Constrained Interaction Modeling , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Xiao Liu,et al.  Random Geometric Prior Forest for Multiclass Object Segmentation , 2015, IEEE Transactions on Image Processing.

[24]  Marc Teboulle,et al.  A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems , 2009, SIAM J. Imaging Sci..

[25]  Y. Nesterov Gradient methods for minimizing composite objective function , 2007 .

[26]  Bo Du,et al.  Ensemble manifold regularized sparse low-rank approximation for multiview feature embedding , 2015, Pattern Recognit..

[27]  Bo Du,et al.  Target detection based on a dynamic subspace , 2014, Pattern Recognit..

[28]  Meng Wang,et al.  Adaptive Hypergraph Learning and its Application in Image Classification , 2012, IEEE Transactions on Image Processing.

[29]  Dani Lischinski,et al.  Spectral Matting , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Xiaofei He,et al.  Locality Preserving Projections , 2003, NIPS.

[31]  Michael F. Cohen,et al.  Optimized Color Sampling for Robust Matting , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.

[33]  Dani Lischinski,et al.  A Closed-Form Solution to Natural Image Matting , 2008 .

[34]  Manoranjan Paul,et al.  The Image Matting Method with Regularized Matte , 2012, 2012 IEEE International Conference on Multimedia and Expo.

[35]  Manuel Menezes de Oliveira Neto,et al.  Shared Sampling for Real‐Time Alpha Matting , 2010, Comput. Graph. Forum.

[36]  Xiaogang Wang,et al.  Video Matting via Sparse and Low-Rank Representation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[37]  Jianfei Cai,et al.  Compressive environment matting , 2014, The Visual Computer.

[38]  Xuelong Li,et al.  A Nonlinear Adaptive Level Set for Image Segmentation , 2014, IEEE Transactions on Cybernetics.

[39]  Dacheng Tao,et al.  Subspaces Indexing Model on Grassmann Manifold for Image Search , 2011, IEEE Transactions on Image Processing.

[40]  Deepu Rajan,et al.  Improving Image Matting Using Comprehensive Sampling Sets , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[41]  Liangpei Zhang,et al.  Tensor Discriminative Locality Alignment for Hyperspectral Image Spectral–Spatial Feature Extraction , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[42]  Junbin Gao,et al.  Image Matting via Local Tangent Space Alignment , 2011, 2011 International Conference on Digital Image Computing: Techniques and Applications.

[43]  Jiaya Jia,et al.  Poisson matting , 2004, SIGGRAPH 2004.

[44]  Pascal Fua,et al.  Tracking Interacting Objects Optimally Using Integer Programming , 2014, ECCV.

[45]  Kilian Q. Weinberger,et al.  Unsupervised Learning of Image Manifolds by Semidefinite Programming , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[46]  Xuelong Li,et al.  Geometric Mean for Subspace Selection , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[47]  Michael F. Cohen,et al.  An iterative optimization approach for unified image segmentation and matting , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[48]  Linda G. Shapiro,et al.  Robust interactive image segmentation with automatic boundary refinement , 2010, 2010 IEEE International Conference on Image Processing.

[49]  Deepu Rajan,et al.  Sparse Coding for Alpha Matting , 2016, IEEE Transactions on Image Processing.

[50]  Aggelos K. Katsaggelos,et al.  Locally adaptive subspace and similarity metric learning for visual data clustering and retrieval , 2008, Comput. Vis. Image Underst..

[51]  Junbin Gao,et al.  Natural Image Matting with Total Variation Regularisation , 2012, 2012 International Conference on Digital Image Computing Techniques and Applications (DICTA).

[52]  Y. Nesterov A method for solving the convex programming problem with convergence rate O(1/k^2) , 1983 .

[53]  Ery Arias-Castro,et al.  On the convergence of maximum variance unfolding , 2012, J. Mach. Learn. Res..

[54]  Ling Shao,et al.  What's the Role of Image Matting in Image Segmentation? , 2013, 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[55]  Minglun Gong,et al.  Integrated foreground segmentation and boundary matting for live videos. , 2015, IEEE transactions on image processing : a publication of the IEEE Signal Processing Society.

[56]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[57]  Xuelong Li,et al.  Image Categorization by Learning a Propagated Graphlet Path , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[58]  Pascal Fua,et al.  Tracking Interacting Objects Using Intertwined Flows , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[59]  Deepu Rajan,et al.  Weighted color and texture sample selection for image matting , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[60]  Wei Chen,et al.  Easy Matting ‐ A Stroke Based Approach for Continuous Image Matting , 2006, Comput. Graph. Forum.

[61]  Jianfei Cai,et al.  Real-Time and Temporal-Coherent Foreground Extraction With Commodity RGBD Camera , 2015, IEEE Journal of Selected Topics in Signal Processing.

[62]  Ming Shao,et al.  Deep Robust Encoder Through Locality Preserving Low-Rank Dictionary , 2016, ECCV.

[63]  Hongyuan Zha,et al.  Principal Manifolds and Nonlinear Dimension Reduction via Local Tangent Space Alignment , 2002, ArXiv.

[64]  Guillermo Sapiro,et al.  A Geodesic Framework for Fast Interactive Image and Video Segmentation and Matting , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[65]  Deepu Rajan,et al.  Weighted color and texture sample selection for image matting , 2012, CVPR.

[66]  Junbin Gao,et al.  Image Matting via LLE/iLLE Manifold Learning , 2013 .

[67]  Xuelong Li,et al.  Group sparse reconstruction for image segmentation , 2014, Neurocomputing.

[68]  Xuelong Li,et al.  Interactive Segmentation Using Constrained Laplacian Optimization , 2014, IEEE Transactions on Circuits and Systems for Video Technology.

[69]  Xuelong Li,et al.  An Efficient MRF Embedded Level Set Method for Image Segmentation , 2015, IEEE Transactions on Image Processing.

[70]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.