Document Data Extraction System Based on Visual Words Codebook.
Vasily LoginovAleksandr ValiukovStanislav SemenovIvan ZagaynovPublished in: DAS (2020)
Keyphrases
- visual words
- data extraction
- bag of words
- image classification
- semi structured
- bag of visual words
- image representation
- vector quantized
- co occurrence
- image retrieval
- scene classification
- visual phrases
- visual vocabulary
- spatial information
- image features
- bag of features
- web documents
- data integration
- web pages
- keypoints
- information retrieval systems
- information retrieval
- object retrieval
- visual codebook
- information extraction
- keywords
- action recognition
- database
- document collections
- gaussian mixture model
- soft assignment
- text classification
- query interface
- user queries
- relevant documents
- visual features
- pairwise
- feature space
- vector quantization
- web databases
- document retrieval
- object recognition
- multiscale
- similarity measure
- data sets