Image Labeling Model Based on Conditional Random Fields

Abstract:

We present conditional random fields (CRFs), a framework for building probabilistic models to segment and label sequence data, and use CRFs to label pixels in an image. CRFs provide a discriminative framework to incorporate spatial dependencies in an image, which is more appropriate for classification tasks as opposed to a generative framework. In this paper we apply CRF to an image classification tasks: an image labeling problem (manmade vs. natural regions in the MSRC 21-object class datasets). Parameter learning is performed using contrastive divergence (CD) algorithm to maximize an approximation to the conditional likelihood. We focus on two aspects of the classification task: feature extraction and classifiers design. We present classification results on sample images from MSRC 21-object class datasets.

• Periodical: Advanced Materials Research (Volumes 756-759)
• Pages: 3869-3873
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.756-759.3869
• Online since: September 2013
• Authors: Yang Yan, Wen Bo Huang, Yun Ji Wang, Na Li
• Keywords: Classifier, CRFs, Feature Extraction, Image Labeling, Label Features, Parameter Estimation

References

[1] John Lafferty, Andrew McCallum. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. ICML. (2001).

DOI: 10.1145/1015330.1015422

[2] An introduction to hidden Markov models. ASSP Magazine, IEEE, (1986) 3: 4-16.

[3] S.Z. Li. Markov Random Field Modeling in Image Analysis. Springer. (2001).

[4] Charles Sutton, Andrew McCallum. An Introduction to Conditional Random Fields. (2006).

[5] Geoffrey E. Hinton. Training products of experts by minimizing contrastive divergence. Neural Computation. (2002)14: 1771–1800.

DOI: 10.1162/089976602760128018

[6] Xuming He. Learning Structured Prediction Models for Image Labeling. University of Toronto. (2008): 11-12.

[7] Xuming He. Multiscale Conditional Random Fields for Image Labeling. Proceedings of the IEEE (2004) 2: 695-702.

[8] Hanna M. Wallach. Conditional Random Fields: An Introduction. Technical Reports (CIS), (2004): 2-7.

[9] D Parikh, D Batra. CRFs for Image Classification. Carnegie Mellon University. (2006).