Multiscale document segmentation using wavelet-domain hidden Markov models

Hyeokho Choi, Richard Baraniuk

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Scopus citations


We introduce a new document image segmentation algorithm, HMTseg, based on wavelets and the hidden Markov tree (HMT) model. The HMT is a tree-structured probabilistic graph that captures the statistical properties of the coefficients of the wavelet transform. Since the HMT is particularly well suited to images containing singularities (edges and ridges), it provides a good classifier for distinguishing between different document textures. Utilizing the inherent tree structure of the wavelet HMT and its fast training and likelihood computation algorithms, we perform multiscale texture classification at a range of different scales. We then fuse these multiscale classifications using a Bayesian probabilistic graph to obtain reliable final segmentations. Since HMTseg works on the wavelet transform of the image, it can directly segment wavelet-compressed images, without the need for decompression into the space domain. We demonstrate HMTseg's performance with both synthetic and real imagery.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
PublisherSociety of Photo-Optical Instrumentation Engineers
Number of pages14
StatePublished - 2000
EventProceedings of the 2000 Document Recognition and Retrieval VII - San Jose, CA, USA
Duration: Jan 26 2000Jan 27 2000


OtherProceedings of the 2000 Document Recognition and Retrieval VII
CitySan Jose, CA, USA

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics


Dive into the research topics of 'Multiscale document segmentation using wavelet-domain hidden Markov models'. Together they form a unique fingerprint.

Cite this