Fast document image comparison in multilingual corpus without OCR.
Yuping LinYingyu LiYonghong SongFang WangPublished in: Multim. Syst. (2017)
Keyphrases
- document images
- optical character recognition
- document image analysis
- document analysis
- printed documents
- scanned documents
- document processing
- ocr systems
- document image retrieval
- page layout
- indian languages
- language independent
- digital libraries
- language identification
- text lines
- page segmentation
- historical documents
- document image understanding
- character recognition
- line extraction
- input image
- word level
- image enhancement
- printed text
- metadata