ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction.
Zheng HuangKai ChenJianhua HeXiang BaiDimosthenis KaratzasShijian LuC. V. JawaharPublished in: ICDAR (2019)
Keyphrases
- auction protocol
- scanned documents
- information extraction
- document images
- text detection
- optical character recognition
- text lines
- natural language processing
- scanned images
- text mining
- precision and recall
- information retrieval
- machine learning
- open domain
- structured data
- free text
- noise removal
- web documents
- named entity recognition
- scanned document images
- semi structured
- web mining
- natural language
- character recognition
- ontology based information extraction
- text recognition
- conditional random fields
- textual data
- data extraction
- printed documents
- post processing
- relational learning
- international competition
- machine translation
- text documents
- relation extraction
- document processing
- knowledge discovery
- preprocessing
- extracting meaningful
- text summarization
- object recognition