Technical Management For Machine Learning & Backend Development On OCR Internship

We are working on detecting the layout of the OCRed text, preserve it, and reflect it in the to automate the annotation task. Optical character recognition (OCR) is the process of converting the document images into an editable electronic format. This has many advantages like data compression, enabling search or edit options in the images/text, and creating the database for other applications like machine translation, speech recognition, and enhancing dictionaries and language models. OCR in Indian languages is quite challenging due to richness in inflections. Using open-source and commercial OCR systems, we have observed the word error rates (WER) of around 20-50% on printed documents in four different Indic languages. Moreover, developing a highly accurate OCR system with accuracy as high as 90% is not useful unless aided by the mechanism to identify errors. So, we started with the problem of developing "OpenOCRCorrect", an end-to-end framework for error detection and corrections in Indic-OCR. Our models outperform state-of-the-art results in 'Error Detection in Indic-OCR' for six Indic languages with varied inflections and we have solved the out of vocabulary problem for “Error Correction in Indic-OCR” in our ICDAR-2017 conference paper. We further improve the results with the help of sub-word embeddings in our ICDAR-2019 conference paper.

The demo video for our framework is https://www.youtube.com/watch?v=u9bqUDrGugc.
To install the software, you can go to https://github.com/rohitsaluja22/OpenOCRCorrect and follow the instructions given in https://www.youtube.com/watch?v=0hcdlF-zn8E. There is an immediate demand to keep the softcopy of the Indian preserved texts. Currently, we are targeting Sanskrit. Although the OCR tools available online do a decent job on English texts, they are not optimized for Indic languages. Thus, we developed an in-house OCR model for the same. The model can detect text with maximum level accuracy and can draw bounding boxes on each line of the text. Further, in the digitization process of such texts, the second step would be spelling correction and formatting of the text detected by the OCR models.

'ICDAR 2019 Post-OCR competition': Our team "CLAM" secured 2nd position in the multilingual PostOCR competition at ICDAR'19. Our model achieved the highest corrections of 44% in Finnish, which is significantly higher than the overall topper (8% in Finnish).
Our final report for the same - (https://drive.google.com/file/d/15mxNOM9PiXBnffi7MOa8wUw33nj1xBp/view?usp=drive_open) and poster available (https://drive.google.com/file/d/1uuBWu1LQ1QZ49SCgLBoB1er4HpWSzmcx/view).

'ICDAR2019': You can read the paper here -https://www.cse.iitb.ac.in/~rohitsaluja/PID6011473.pdf
'ICDAR2017': You can read the paper here - https://ieeexplore.ieee.org/document/8269944

'ICDAR-OST 2017':
a. OpenOCRCorrect, you can read the paper here - https://ieeexplore.ieee.org/abstract/document/8270254
b. The source code for our framework is available here - https://github.com/rohitsaluja22/OpenOCRCorrect

Candidates need to understand that this is a technical management role required to lead a backend team working in C++/Python and also lead the ML Team. Technical Guidance will be provided by industry experts or professors but the candidate needs to execute the work with the team and manage efficiently.