Font clustering and cluster identification in document images.
Serdar ÖztürkBülent SankurA. Toygar AbakPublished in: J. Electronic Imaging (2001)
Keyphrases
- document images
- document image understanding
- clustering algorithm
- optical character recognition
- data clustering
- hierarchical clustering
- ocr systems
- document image analysis
- cluster analysis
- clustering approaches
- data points
- clustering method
- document analysis
- disjoint clusters
- k means
- scanned documents
- cluster centers
- character recognition
- document processing
- printed documents
- page segmentation
- language identification
- clustering quality
- text regions
- intra cluster
- document image retrieval
- page layout
- image analysis
- line extraction
- indian languages
- machine vision
- structural features