Doc2Img: A New Approach to Vectorization of Documents.
ShreeRanjani SrirangamSridharanMudhakar SrivatsaRaghu K. GantiChristopher SimpkinPublished in: FUSION (2018)
Keyphrases
- information retrieval systems
- keywords
- legal documents
- document collections
- xml documents
- relevant documents
- information retrieval
- metadata
- document classification
- document retrieval
- web documents
- document clustering
- plagiarism detection
- free text
- vector space model
- document representation
- multi document summarization
- retrieval systems
- line segments
- machine learning
- text documents
- feature selection
- document structure
- digital documents
- relational databases