A sparse coding method for semi-supervised segmentation with multi-class histogram constraints

We present a semi-supervised segmentation method that uses a dictionary of multi-class foreground histograms to enhance the segmentation in the presence of incorrect or missing labels. Instead of requiring a target histogram, or a set of images with the same foreground, this method uses sparse coding to find the most relevant histogram for the foreground. An efficient strategy based on the ADMM algorithm is proposed to avoid the problems of non-submodularity and non-linearity, normally related to histogram-based segmentation. Experiments on the segmentation of natural images with incomplete or incorrect labels show our method to be more robust and accurate than other approaches for this task.

[1]  John W. Fisher,et al.  Submitted to Ieee Transactions on Image Processing a Nonparametric Statistical Method for Image Segmentation Using Information Theory and Curve Evolution , 2022 .

[2]  Shuo Li,et al.  Graph cut segmentation with a global constraint: Recovering region distribution via a bound of the Bhattacharyya measure , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Guillermo Sapiro,et al.  Discriminative learned dictionaries for local image analysis , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Eric P. Xing,et al.  On multiple foreground cosegmentation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Andrew Blake,et al.  Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[6]  Aaron D. Ward,et al.  Segmentation with Non-linear Regional Constraints via Line-Search Cuts , 2012, ECCV.

[7]  Jiebo Luo,et al.  iCoseg: Interactive co-segmentation with intelligent scribble guidance , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Shuicheng Yan,et al.  Multi-task low-rank affinity pursuit for image segmentation , 2011, 2011 International Conference on Computer Vision.

[9]  Michel Barlaud,et al.  Segmentation of Vectorial Image Features Using Shape Gradients and Information Measures , 2006, Journal of Mathematical Imaging and Vision.

[10]  Yogesh Rathi,et al.  Shape-Based Approach to Robust Image Segmentation using Kernel PCA , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[11]  Leo Grady,et al.  Random Walks for Image Segmentation , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Vladimir Kolmogorov,et al.  Joint optimization of segmentation and appearance models , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[13]  Leo Grady,et al.  Random walks based multi-image segmentation: Quasiconvexity results and GPU-based solutions , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Daniel Rueckert,et al.  Segmentation of MR images via discriminative dictionary learning and sparse coding: Application to hippocampus labeling , 2013, NeuroImage.

[15]  Huibin Li,et al.  A graph-cut approach to image segmentation using an affinity graph based on ℓ0-sparse representation of features , 2013, 2013 IEEE International Conference on Image Processing.

[16]  Junzhou Huang,et al.  Towards robust and effective shape modeling: Sparse shape composition , 2012, Medical Image Anal..

[17]  Jean Ponce,et al.  Multi-class cosegmentation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  B. S. Manjunath,et al.  Shape prior segmentation of multiple objects with graph cuts , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Daniel Cremers,et al.  Kernel Density Estimation and Intrinsic Alignment for Shape Priors in Level Set Segmentation , 2006, International Journal of Computer Vision.

[21]  A. Bruckstein,et al.  Sparse non-negative solution of a linear system of equations is unique , 2008, 2008 3rd International Symposium on Communications, Control and Signal Processing.