Robust unsupervised segmentation of degraded document images with topic models

Timothy J. Burns, Jason J. Corso

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Scopus citations

Abstract

Segmentation of document images remains a challenging vision problem. Although document images have a structured layout, capturing enough of it for segmentation can be difficult. Most current methods combine text extraction and heuristics for segmentation, but text extraction is prone to failure and measuring accuracy remains a difficult challenge. Furthermore, when presented with significant degradation many common heuristic methods fall apart. In this paper, we propose a Bayesian generative model for document images which seeks to overcome some of these drawbacks. Our model automatically discovers different regions present in a document image in a completely unsupervised fashion. We attempt no text extraction, but rather use discrete patch-based codebook learning to make our probabilistic representation feasible. Each latent region topic is a distribution over these patch indices. We capture rough document layout with an MRF Potts model. We take an analysis-by-synthesis approach to examine the model, and provide quantitative segmentation results on a manuallylabeled document image data set. We illustrate our model's robustness by providing results on a highly degraded version of our test set.

Original languageEnglish
Title of host publication2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
Pages1287-1294
Number of pages8
DOIs
StatePublished - 2009
Event2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 - Miami, FL, United States
Duration: 20 Jun 200925 Jun 2009

Publication series

Name2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

Conference

Conference2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
Country/TerritoryUnited States
CityMiami, FL
Period20/06/0925/06/09

Fingerprint

Dive into the research topics of 'Robust unsupervised segmentation of degraded document images with topic models'. Together they form a unique fingerprint.

Cite this