Machine Learning vs Deterministic Rule-Based System for Document Stream Segmentation.
Ahmed HamdiJoris VoermanMickaël CoustatyAurélie JosephVincent Poulain D'AndecyJean-Marc OgierPublished in: WML@ICDAR (2017)
Keyphrases
- machine learning
- page segmentation
- web documents
- data streams
- fully automatic
- level set
- information retrieval
- computer vision
- segmentation accuracy
- image segmentation
- segmentation method
- information extraction
- energy function
- machine learning algorithms
- segmentation algorithm
- real time
- document images
- machine learning methods
- pattern recognition
- document classification
- medical imaging
- text documents
- text classification
- medical images
- image analysis
- data analysis
- document collections
- label assignment
- text mining
- active learning
- region growing
- multiscale
- streaming data
- clustering algorithm
- artificial intelligence