Hello everyone
I have a project where we have to extract data using Abbyy Cloud OCR for 3 types of documents, Passports, ID cards and Drivers Licenses (DL)from 13 countries (there are approximately 50 different documents as there are more than one type of DL for some countries). We are required to process these documents as we receive them in perpetuity, i.e. this is not a one-time processing exercise but part of a larger solution where we will be required to process new documents daily. We therefore need someone to develop a program with the zonal ocr mapping that will extract the defined data from each document and export it into an agreed table format, which will then be read from another program of ours.
There is more to the project, including additional document formats from the same countries and additional countries, but before elaborating further, I would need to hear from people who have experience working with Abbyy Cloud OCR and who can show me what they have already accomplished in this field. If we are a good match for each other, then we can discuss this further.
Look forward to hearing from you all.
Thanks
Alexander
Hi there.
I am very interested in your proposal.
I can instantly help you with your starting project with a successful completion.
As a professional Image processor, I ensure for a perfect ongoing project.
You will never be disappointed in me for sure.
Looking forward to meeting you on chat.
Good luck. Thank you.
Hello Alexander
I have experience with ABBYY OCR with templates to extract information from mortgage documents. you can see this project here: https://www.freelancer.com/projects/mysql/OCR-PDF-Data-Extraction-for/details
Although I can work with ABBYY I suggest you to use free OCR such as tesseract which works great with zoned projects and gives results in hOCR format which is similar with ABBYYs XML result as it is based on XML too.
As you have multiple types of documents we need to split this project into parts:
1) Document recognition so that we can recognize which country, document type and revision is.(for example Georgian ID of 2010 type)
2) Document preprocessing (extracting document forms, deskewing, noise removing etc.)
3) Document zoning (based on some templates)
4) Extraction using ABBYY cloud OCR
5) Parsing and saving data to database of your choice.
I laid out estimated milestones that I see relevant to this project. Please discuss details over chat. Maximum response time is 12 hours, although mostly I respond in minutes.
Thanks for your attention
Archil
Hi there
I am proficient in OCR/ML/DL as a developer with 10+ years of experience.
You can check my review and portfolio for the my before work.
If you award me the project I'd be very happy to discuss this further and get started for you as soon as possible.
Thanks!
Vladimir.K
i have worked on OCRing PDF and images using tessract and abbyy tools. There we were reading legal documents of various counties. I can make a demo for you using abbyy tool, if you can give me some sample documents.