The Use of Latent Semantic Indexing to Mitigate OCR Effects of Related Document Images.
Renato Bulcão NetoJosé Antonio Camacho GuerreroMárcio Branquinho DutraAlvaro BarreiroJavier ParaparAlessandra A. MacedoPublished in: J. Univers. Comput. Sci. (2011)
Keyphrases
- document images
- latent semantic indexing
- optical character recognition
- document image analysis
- document analysis
- text retrieval
- vector space
- scanned documents
- ocr systems
- document processing
- document image retrieval
- printed documents
- page segmentation
- singular value decomposition
- vector space model
- information retrieval
- page layout
- document representation
- scanned images
- least squares
- digital libraries
- printed text
- scanned document images
- low dimensional
- multiscale
- computer vision