Learning to Detect Scene Text Using a Higher-Order MRF with Belief Propagation

Authors:
Dong-Qing Zhang;Shih-Fu Chang
Affiliations:
Columbia University, New York, NY;Columbia University, New York, NY
Venue:
CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 6 - Volume 06
Year:
2004

Citing 0
Cited 8

Gaussian mixture modeling and learning of neighboring characters for multilingual text extraction in images

Pattern Recognition
Graphical Models for Structured Classification, with an Application to Interpreting Images of Protein Subcellular Location Patterns

The Journal of Machine Learning Research
Figure-ground segmentation using factor graphs

Image and Vision Computing
Grouping using factor graphs: an approach for finding text with a camera phone

GbRPR'07 Proceedings of the 6th IAPR-TC-15 international conference on Graph-based representations in pattern recognition
Distributed inference for network localization using radio interferometric ranging

EWSN'08 Proceedings of the 5th European conference on Wireless sensor networks
Higher order MRF for foreground-background separation in multi-spectral images of historical manuscripts

DAS '10 Proceedings of the 9th IAPR International Workshop on Document Analysis Systems
Maximum-minimum similarity training for text extraction

ICONIP'06 Proceedings of the 13th international conference on Neural information processing - Volume Part III
Integrating multiple character proposals for robust scene text extraction

Image and Vision Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Detecting text in natural 3D scenes is a challenging problem due to background clutter and photometric/gemetric variations of scene text. Most prior systems adopt approaches based on deterministic rules, lacking a systematic and scalable framework. In this paper, we present a parts-based approach for 3D scene text detection using a higher-order MRF model. The higher-order structure is used to capture the spatial-feature relations among multiple parts in scene text. The use of higher-order structure and the feature-dependent potential function represents significant departure from the conventional pairwise MRF, which has been successfully applied in several low-level applications. We further develop a variational approximation method, in the form of belief propagation, for inference in the higher-order model. Our experiments using the ICDAR'03 benchmark showed promising results in detecting scene text with significant geometric variations, background clutter on planar surfaces or non-planar surfaces with limited angles.