Separator and content based approach for table extraction in handwritten chemistry documents.
Nabil GhanmiAbdel BelaïdPublished in: ICDAR (2015)
Keyphrases
- web documents
- word spotting
- document analysis
- textual content
- metadata
- document content
- multimedia documents
- structured documents
- historical documents
- xml documents
- information retrieval
- content and structure
- text content
- character recognition
- semantic tags
- related documents
- document clustering
- text line segmentation
- information retrieval systems
- web information
- document collections
- handwritten documents
- semantic information
- semantic content
- relevant content
- document type
- handwritten text
- content similarity
- document structure
- semantic relevance
- logical structure
- electronic documents
- scientific papers
- arabic documents
- handwriting recognition
- semi structured documents
- text retrieval
- pdf files
- document retrieval
- user interests
- web content
- textual information
- digital objects
- information extraction