Elimination of junk document surrogate candidates through pattern recognition.
Eunyee KohDaniel CarusoAndruid KerneRicardo Gutierrez-OsunaPublished in: ACM Symposium on Document Engineering (2007)
Keyphrases
- pattern recognition
- neural network
- document images
- signal processing
- information retrieval systems
- document retrieval
- document collections
- image processing
- document classification
- feature extraction
- computer vision
- image analysis
- document representation
- keywords
- textual content
- structured documents
- web documents
- text documents
- machine learning
- similarity measure
- face recognition
- document clustering
- information retrieval
- candidate set
- database
- multimedia documents
- graph matching
- speech recognition
- fuzzy sets
- dimensionality reduction
- decision trees
- knowledge base