DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documents.
Eun-Soo JungHyeongGwan SonKyusam OhYongkeun YunSoonhwan KwonMin Soo KimPublished in: ICPR (2020)
Keyphrases
- text documents
- document images
- information retrieval
- text lines
- web documents
- digital documents
- free text
- text analysis
- textual documents
- scanned images
- keywords
- document analysis
- automatic categorization
- text data
- scanned document images
- document processing
- text retrieval
- text collections
- document content
- latent semantic analysis
- printed documents
- textual content
- plagiarism detection
- text clustering
- document categorization
- document collections
- scanned documents
- page layout
- newspaper articles
- document retrieval
- natural language text
- text content
- line extraction
- text categorization
- structured documents
- retrieval engine
- linguistic analysis
- topic segmentation
- text corpus
- text mining
- information retrieval systems
- document level
- electronic documents
- textual data
- journal articles
- multimedia documents
- vector space model
- metadata
- sentence level
- xml documents
- textual information
- document structure
- scientific documents
- document set
- text classification
- image enhancement
- semantic information
- relevant documents
- digital libraries
- information extraction
- retrieval systems
- document clustering
- semantic content
- optical character recognition
- text corpora
- scientific literature