Variable length and context-dependent HMM letter form models for Arabic handwritten word recognition.
Anne-Laure Bianne-BernardFarès MenasriLaurence Likforman-SulemChafic MokbelChristopher KermorvantPublished in: DRR (2012)
Keyphrases
- handwritten word recognition
- variable length
- context dependent
- hidden markov models
- fixed length
- statistical dependencies
- handwritten words
- word recognition
- computer vision
- probabilistic model
- n gram
- speech recognition
- image compression
- low level
- bayesian networks
- context free
- feature extraction
- high level
- machine learning