A very high accuracy handwritten character recognition system for Farsi/Arabic digits using Convolutional Neural Networks.
Sajjad S. AhranjanyFarbod RazzaziMohammad H. GhassemianPublished in: BIC-TA (2010)
Keyphrases
- handwritten characters
- character recognition
- convolutional neural networks
- ocr systems
- high accuracy
- optical character recognition
- writer independent
- hand written
- handwriting recognition
- arabic handwriting recognition
- handwritten character recognition
- machine vision
- handwritten documents
- printed documents
- convolutional network
- word spotting
- handwritten words
- character segmentation
- handwritten digits
- binary images
- word recognition
- alphanumeric characters
- chinese characters
- license plate
- document analysis
- high efficiency
- natural language processing
- highly accurate
- document images
- rapid convergence
- morphological analysis
- isolated word
- speech recognition
- feature extraction