A Hybrid Approach to Document Layout Analysis for Heterogeneous Document Images.
Zhuoyao ZhongJiawei WangHaiqing SunKai HuErhan ZhangLei SunQiang HuoPublished in: ICDAR (5) (2023)
Keyphrases
- document images
- document image analysis
- document analysis
- document processing
- document image understanding
- language identification
- page segmentation
- scanned documents
- document image retrieval
- historical documents
- word spotting
- scanned document images
- text lines
- web documents
- word level
- optical character recognition
- gray scale
- page layout
- printed text
- document layout
- metadata
- information retrieval