Experiences of integration and performance testing of multilingual OCR for printed Indian scripts
Citations
81 citations
64 citations
Cites background or methods from "Experiences of integration and perf..."
...Keywords: BLSTM, Word recognition, Devanagari, OCR...
[...]
...In this section, we quantitatively compare our method against a state-of-the-art Indian language OCR [1]....
[...]
...It results in more than 20% improvement in word accuracy while comparing traditional OCR system....
[...]
40 citations
Cites background from "Experiences of integration and perf..."
...Though there have been many attempts in developing OCRs for Indian scripts from the 1970s to the beginning of this decade [2, 3, 4], methods that can scale across languages and yield reasonable results over a wide variety of documents are not yet devised....
[...]
40 citations
Cites background from "Experiences of integration and perf..."
...The major contributions of our work are: • A novel re-posing of the OCR problem to one of recognizing character n-grams....
[...]
24 citations
Cites background from "Experiences of integration and perf..."
...There has been significant progress in the recent past on developing robust solutions [1], [2], [3]....
[...]
...Traditionally this module has been formulated as an adhoc composition of a set of isolated character (or symbol) classifiers [1], [9]....
[...]
...OCR [1] Tesseract [17] Our Method Char....
[...]
...Word to symbol/character separation, is required for classifiers that recognize isolated characters [1]....
[...]
References
592 citations
381 citations
"Experiences of integration and perf..." refers background in this paper
...There have been many attempts in development of OCRs for Indian Scripts like Devanagari, Malayalam[10], Telugu, Tamil[7], Bangla[14], Gurumukhi[15] and Kannada[8]....
[...]
...There have been many attempts in development of OCRs for Indian Scripts like Devanagari, Malayalam[10], Telugu, Tamil[7], Bangla[14], Gurumukhi[15] and Kannada[8]....
[...]
...Bangla and Devanagari are among the most symbol-rich since originally about 2000 shapes need to be recognized for a complete OCR system[14]....
[...]
68 citations
46 citations
46 citations
"Experiences of integration and perf..." refers background in this paper
...There have been many attempts in development of OCRs for Indian Scripts like Devanagari, Malayalam[10], Telugu, Tamil[7], Bangla[14], Gurumukhi[15] and Kannada[8]....
[...]
...There have been many attempts in development of OCRs for Indian Scripts like Devanagari, Malayalam[10], Telugu, Tamil[7], Bangla[14], Gurumukhi[15] and Kannada[8]....
[...]
...Tamil has 18 consonants and 12 vowels[7]....
[...]