Learning a classification model for segmentation

We propose a two-class classification model for grouping. Human segmented natural images are used as positive examples. Negative examples of grouping are constructed by randomly matching human segmentations and images. In a preprocessing stage an image is over-segmented into super-pixels. We define a variety of features derived from the classical Gestalt cues, including contour, texture, brightness and good continuation. Information-theoretic analysis is applied to evaluate the power of these grouping cues. We train a linear classifier to combine these features. To demonstrate the power of the classification model, a simple algorithm is used to randomly search for good segmentations. Results are shown on a wide range of images.

[1]  M. Wertheimer Laws of organization in perceptual forms. , 1938 .

[2]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Robyn A. Owens,et al.  Feature detection from local energy , 1987, Pattern Recognit. Lett..

[4]  C. Chen,et al.  Dose-response relation between arsenic concentration in well water and mortality from cancers and vascular diseases. , 1989, American journal of epidemiology.

[5]  Steven W. Zucker,et al.  Radial Projection: An Efficient Update Rule for Relaxation Labeling , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  B. Hoque,et al.  Tubewell water consumption and its determinants in a rural area of Bangladesh. , 1989, The Journal of tropical medicine and hygiene.

[7]  Steven W. Zucker,et al.  Trace Inference, Curvature Consistency, and Curve Detection , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  D. Mumford,et al.  Optimal approximations by piecewise smooth functions and associated variational problems , 1989 .

[9]  J. Potash,et al.  Effects of improved water supply and sanitation on ascariasis, diarrhoea, dracunculiasis, hookworm infection, schistosomiasis, and trachoma. , 1991, Bulletin of the World Health Organization.

[10]  A. Smith,et al.  Cancer risks from arsenic in drinking water. , 1992, Environmental health perspectives.

[11]  Carl-Fredrik Westin,et al.  Normalized and differential convolution , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Carl-Fredrik Westin,et al.  Normalized Convolution : Technique for Filtering Incomplete and Uncertain Data , 1993 .

[13]  M. Lai,et al.  Ingested inorganic arsenic and prevalence of diabetes mellitus. , 1994, American journal of epidemiology.

[14]  Lance R. Williams,et al.  Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience , 1995, Neural Computation.

[15]  Alan L. Yuille,et al.  Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Joachim M. Buhmann,et al.  Non-parametric similarity measures for unsupervised texture segmentation and image retrieval , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Yoram Singer,et al.  Improved Boosting Algorithms Using Confidence-rated Predictions , 1998, COLT' 98.

[19]  Pietro Perona,et al.  A Factorization Approach to Grouping , 1998, ECCV.

[20]  Kim L. Boyer,et al.  Quantitative Measures of Change Based on Feature Organization: Eigenvalues and Eigenvectors , 1998, Comput. Vis. Image Underst..

[21]  Jitendra Malik,et al.  Contour Continuity in Region Based Image Segmentation , 1998, ECCV.

[22]  S. Palmer Vision Science : Photons to Phenomenology , 1999 .

[23]  M. Rahman,et al.  Hypertension and arsenic exposure in Bangladesh. , 1999, Hypertension.

[24]  Ian H. Jermyn,et al.  Globally optimal regions and boundaries , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[25]  Y. Ko,et al.  Mortality for certain diseases in areas with high levels of arsenic in drinking water. , 1999, Archives of environmental health.

[26]  Jianbo Shi,et al.  Learning Segmentation by Random Walks , 2000, NIPS.

[27]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[28]  Shimon Ullman,et al.  Class-Specific, Top-Down Segmentation , 2002, ECCV.

[29]  Jitendra Malik,et al.  A Probabilistic Multi-scale Model for Contour Completion Based on Image Statistics , 2002, ECCV.

[30]  Jitendra Malik,et al.  Learning to Detect Natural Image Boundaries Using Brightness and Texture , 2002, NIPS.

[31]  P. Smedley,et al.  A review of the source, behaviour and distribution of arsenic in natural waters , 2002 .

[32]  Zhuowen Tu,et al.  Image Segmentation by Data-Driven Markov Chain Monte Carlo , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  A. Prüss,et al.  Estimating the burden of disease from water, sanitation, and hygiene at a global level. , 2002, Environmental health perspectives.

[34]  Stella X. Yu,et al.  Object Segmentation by Graph Partitioning ∗ , 2002 .

[35]  Jitendra Malik,et al.  Learning affinity functions for image segmentation: combining patch-based and gradient-based approaches , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[36]  Y. Hsueh,et al.  Long-term arsenic exposure and ischemic heart disease in arseniasis-hyperendemic villages in Taiwan. , 2003, Toxicology letters.

[37]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[38]  Jitendra Malik,et al.  Contour and Texture Analysis for Image Segmentation , 2001, International Journal of Computer Vision.

[39]  A. Smith,et al.  Arsenic drinking water regulations in developing countries with extensive exposure. , 2004, Toxicology.

[40]  T. Clasen,et al.  Household water management: refining the dominant paradigm. , 2004, Tropical medicine & international health : TM & IH.

[41]  K. Lokuge,et al.  The Effect of Arsenic Mitigation Interventions on Disease Burden in Bangladesh , 2004, Environmental health perspectives.