Exploring the Use of Conditional Random Field Models and HMMs for Historical Handwritten Document Recognition.
Shaolei FengR. ManmathaAndrew McCallumPublished in: DIAL (2006)
Keyphrases
- random field models
- handwritten documents
- handwriting recognition
- hidden markov models
- word spotting
- random fields
- historical documents
- character recognition
- historical manuscripts
- object recognition
- speech recognition
- document image analysis
- document analysis
- pattern recognition
- text retrieval
- document images
- expectation maximization
- machine learning
- least squares
- probabilistic model
- feature extraction