Passive Classification of Source Printer using Text-line-level Geometric Distortion Signatures from Scanned Images of Printed Documents.
Hardik JainGaurav GuptaSharad JoshiNitin KhannaPublished in: CoRR (2017)
Keyphrases
- printed documents
- document images
- text lines
- optical character recognition
- character recognition
- document analysis
- feature selection
- feature extraction
- document image analysis
- handwritten documents
- image classification
- text classification
- connected components
- language independent
- machine vision
- feature set
- feature space
- metadata