Towards Building A Robust Large-Scale Bangla Text Recognition Solution Using A Unique Multiple-Domain Character-Based Document Recognition Approach.
A. K. M. Shahariar Azad RabbyMd. Majedul IslamZahidul IslamNazmul HasanFuad RahmanPublished in: ICMLA (2021)
Keyphrases
- text recognition
- optical character recognition
- character segmentation
- document images
- text lines
- printed documents
- handwritten documents
- viterbi algorithm
- handwriting recognition
- character recognition
- document analysis
- hidden markov models
- dynamic programming
- partial occlusion
- information retrieval
- scene images
- handwritten numerals
- complex scenes
- object recognition