Word-Level Multi-Script Indic Document Image Dataset and Baseline Results on Script Identification.
Sk Md ObaidullahK. C. SantoshChayan HalderNibaran DasKaushik RoyPublished in: Int. J. Comput. Vis. Image Process. (2017)
Keyphrases
- word level
- image dataset
- document images
- word recognition
- document analysis
- language independent
- machine translation
- image database
- image annotation
- character recognition
- automatic classification
- image collections
- n gram
- word segmentation
- viterbi algorithm
- information retrieval
- sentence level
- semantic roles
- semi supervised learning
- multi modal
- feature extraction
- image segmentation
- feature selection