Using Sequential Context for Image Analysis

This paper proposes the sequential context inference (SCI) algorithm for Markov random field (MRF) image analysis. This algorithm is designed primarily for fast inference on an MRF model, but its application requires also a specific modeling architecture. The architecture is composed of a sequence of stages, each modeling the conditional probability of the labels, conditioned on a neighborhood of the input image and output of the previous stage. By learning the model at each stage sequentially with regards to the true output labels, the stages learn different models which can cope with errors in the previous stage.

[1]  J. Besag.  On the Statistical Analysis of Dirty Pictures , 1986 .

[2]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[3]  Zhuowen Tu,et al.  Auto-context and its application to high-level vision tasks , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[5]  Stan Z. Li,et al.  Markov Random Field Modeling in Image Analysis , 2001, Computer Science Workbench.

[6]  Han Wang,et al.  Minimization of MRF Energy with Relaxation Labeling , 2004, Journal of Mathematical Imaging and Vision.

[7]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[8]  Vladimir Kolmogorov,et al.  What energy functions can be minimized via graph cuts? , 2002, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Michael I. Jordan,et al.  Loopy Belief Propagation for Approximate Inference: An Empirical Study , 1999, UAI.

[10]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[11]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[12]  Shimon Ullman,et al.  Combining Top-Down and Bottom-Up Segmentation , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[13]  William W. Cohen,et al.  Stacked Graphical Models for Efficient Inference in Markov Random Fields , 2007, SDM.