I have a set of 8 different documents in hebrew (total more than 500 docs)
from which i need to get 4 fields of data per document
I need an ocr (can be local or web based) that will run on a folder of all the scanned docs
per document i will need to get
a - Document number (always in the same place in each doc type)
b - ID number (always in the same place in each doc type)
c - doctor A name (always in the same place in each doc type)
d - doctor B name (always in the same place in each doc type)
e - doc type (which one of the 8 types is this doc)
In case you cant get any of the data (ussaly doctor name) i will need it in raster format if possible.
I dont need any design, this is not a final product
i just need it to run and get the data from the docs.
a - run on sample pdf we supply - 100% retrieve data
b - run on a 24 new samples - 100% retrieve data
c - run on all data with - at least 90% retrieve data
budget is 50$
time to finish 4 days.
50 freelancers are bidding on average $86 for this job
Dear Sir/Ma'am, I can get data from scanned doc by OCR (I have good OCR soft). If you have questions or doubts about anything, please feel free to ask me. Sincerely, Mir
Hello, Can I just check one or two sample pages so that I can estimate the time. Please contact me for discussion and I will send you sample data before we start. Thanks.
Hi there I can do it . I'm well trained on this type of works . You can see it on my profile. Let's start right away .. Looking forward to hearing from you. Thanks.