Keyword Matching in Historical Machine-Printed Documents Using Synthetic Data, Word Portions and Dynamic Time Warping.
Thomas KonidarisBasilios GatosStavros J. PerantonisAnastasios L. KesidisPublished in: Document Analysis Systems (2008)
Keyphrases
- synthetic data
- dynamic time warping
- printed documents
- elastic matching
- sequence matching
- document images
- word spotting
- keyword spotting
- character recognition
- optical character recognition
- keywords
- document analysis
- document processing
- distance measure
- language independent
- historical manuscripts
- euclidean distance
- matching algorithm
- document image analysis
- data sets
- similarity measure
- real world
- similarity search
- image matching
- real image data
- handwritten documents
- edit distance
- word level
- information extraction
- hidden markov models
- data analysis
- text lines
- pattern matching
- text processing