Post-Processing OCR Text using Web-Scale Corpora.
Jie MeiAminul IslamAbidalrahman Moh'dYajing WuEvangelos E. MiliosPublished in: DocEng (2017)
Keyphrases
- post processing
- web scale
- web images
- preprocessing
- image search
- text mining
- natural language processing
- filtering method
- information retrieval
- semi structured
- printed documents
- post processed
- database
- million images
- keywords
- image annotation
- structured data
- face recognition
- high level
- data mining process
- decision trees
- web pages
- databases