A comprehensive survey of mostly textual document segmentation algorithms since 2008.
Sébastien EskenaziPetra Gomez-KrämerJean-Marc OgierPublished in: Pattern Recognit. (2017)
Keyphrases
- page segmentation
- optimization problems
- computationally efficient
- segmentation algorithm
- multimedia
- interactive segmentation
- evolutionary algorithm
- ground truth data
- computational cost
- information retrieval systems
- document retrieval
- problems in image processing
- information retrieval
- shape prior
- document clustering
- document collections
- significant improvement
- data structure
- image segmentation
- learning algorithm