Automatic Page Segmentation Without Decompressing the Run-Length Compressed Text Documents.
Mohammed JavedP. NagabhushanPublished in: CoRR (2020)
Keyphrases
- run length
- page segmentation
- gray level
- compressed text
- comparative evaluation
- information retrieval systems
- document collections
- pattern matching
- xml documents
- document classification
- document images
- relevant documents
- sample size
- information retrieval
- natural language text
- inverted index
- retrieval systems
- texture information
- optical character recognition
- text lines
- face recognition
- binary images
- upper bound
- image processing
- web pages