Only those candidates can apply who:
1. are available for the work from home job/internship
2. can start the work from home job/internship between 10th Jun'20 and 30th Jul'20
3. are available for duration of 6 months
4. have relevant skills and interests
1. You will need to use your own laptop and you can work from home or from campus once COVID situation improves
2. Any graduate or undergraduate from any stream can apply for this position who is comfortable to use the software on Windows/Linux
3. Must be self-motivated and work proactively to complete the tasks within the assigned time frame
4. Expertise in reading Indic (Sanskrit and Hindi) languages and English
5. knowledge of software installation on Windows and Ubuntu
6. knowledge of MS-Office
7. Hands-on experience in data labeling is an added bonus
8. Ability to handle and use custom made tools for annotations and spell-check efficiently
Demo video for our framework is at https://youtu.be/u9bqUDrGugc (MUST WATCH for applying candidates)
To install the software, you can go to https://github.com/rohitsaluja22/OpenOCRCorrect and follow the instructions given in https://youtu.be/0hcdlF-zn8E
This can be a remote internship or can be an in office internship & will start in June. There is an immediate demand to keep the softcopy of the Indian preserved texts. This is an in-office internship & will start in June. Candidates can work from home, till the lockdown is lifted up and it is safe to commute to the campus. 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 an 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. Demo video for our framework is in the first video. Currently, we are targeting Sanskrit. Even after a good accuracy in OCR, the detected text needs a lot of improvement. 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. Hence, the selected candidate’s task would be converting the generated OCR text in accordance with the scanned images of the 500 texts.
OR