Classical Mongolian Words Recognition in Historical Document.
Guanglai GaoXiangdong SuHongxi WeiYeyun GongPublished in: ICDAR (2011)
Keyphrases
- historical documents
- handwritten document images
- word recognition
- handwriting recognition
- printed documents
- document analysis
- document images
- text documents
- word spotting
- continuous speech recognition
- historical manuscripts
- handwritten documents
- recognition rate
- keywords
- related words
- topic hierarchy
- spoken words
- document representation
- text lines
- information retrieval
- document content
- text recognition
- feature extraction
- word segmentation
- word co occurrence
- character recognition
- keyword extraction
- object recognition
- latent topics
- noun phrases
- document clustering
- historical data
- word level
- document level
- text corpus
- index terms
- information retrieval systems
- multiword
- tf idf
- document retrieval
- statistical topic models
- related documents
- automatic text classification
- n gram
- automatic transcription
- endpoint detection
- user queries
- word sense
- handwritten text
- handwritten words
- training documents