Statistical Pattern and Image Analysis Area / ISTL / PARC

Extracting content from document images Model-directed recognition
Recognition, compression, & retrieval Formal probabilistic models
Page layout and printed text Automatic inference of models
 
Overview
People
Skills
Projects
Collaborations
Publications
Prof'l Activities
Computing
    This past year we have been focused on these projects:
  • DID training tools and benchmarks
  • DID search algorithms for language models (with Dan Greene of CSL/Theory)
  • Dataglyph decoding and segmentation
  • Data-driven character template estimation
  • Assist-channel coding & processing (with Dan Greene of CSL/Theory)
  • Layout-segmentation-assisted applications
  • Probabilistic document layout analysis
  • Extension of DID to grayscale and color
  • Compression of grayscale document images