An Impact of OCR Errors on Automated Classification of OCR Japanese Texts with Parts-of-Speech Analysis.
Akihiro KokawaLazaro S. P. BusagalaWataru OhyamaTetsushi WakabayashiFumitaka KimuraPublished in: ICDAR (2011)
Keyphrases
- recognition errors
- optical character recognition
- text recognition
- automated classification
- preprocessing
- post processing
- statistical analysis
- speech recognition
- document images
- error correction
- real world
- image analysis
- character recognition
- document processing
- text to speech
- end to end
- text localization and recognition
- handwriting recognition
- natural language generation
- data sets
- hidden markov models
- information retrieval
- neural network