Text and image area classification in mobile scanned digitised documents.
Anne-Sophie EttlArjan KuijperPublished in: Int. J. Appl. Pattern Recognit. (2014)
Keyphrases
- scanned documents
- document images
- scanned document images
- image classification
- text documents
- scanned images
- information retrieval
- document categorization
- image data
- document classification
- automatic categorization
- image features
- input image
- text clustering
- multiscale
- text lines
- text information
- textual information
- image content
- free text
- keywords
- text classification
- image retrieval
- document analysis
- web documents
- image segmentation
- automatic classification
- similarity measure
- text data
- image analysis
- bag of words
- text mining
- digital documents
- text detection
- printed text
- textual features
- information retrieval systems
- document content
- printed documents
- image representation
- document collections
- textual descriptions
- semantic information
- sentence level
- retrieval systems
- optical character recognition
- text retrieval