Write a script for OCR Conversion from scanned image and search for specific number
$25-50 USD
Paid on delivery
Lets chat. DO NOT push me to award job in a rush. Lets discuss, then when I am ready, I will ask to confirm price.
Do Not ask my budget. You quote me how much $$$ and time you want to do the work. Thank you!!!
I need a script to pull a number from a scanned image that was originally a text document.
The script can be written for windows or linux (ubuntu). I prefer ubuntu.
I will have a test machine to remote access with test files.
I will have a folder full of pdf documents. These documents are scanned images of text documents.
There is one 7 to 15 digit number I need to recover from each document.
(not all documents will have that 7 to 15 digit number. This number is on the first page of the document.
The sample of pdfs I will send in a zip file only contain first pages. Any document that says "Open-Ended" will not contain the number I am looking for )
This script/command will run specifying which pdf file to search. The script will only run search on one pdf at a time.
Example: **$run script [login to view URL] (output is [login to view URL])
When the 7 to 15 digit number is found, the number will be saved in with the same file name as the pdf [login to view URL]
If there is no string found, the file contents will = "null"
There are many slightly different format variations in the pdf file
We will have image type and/or specific text if found on first page, we will stop search and return null result from that document. example : "Open-Ended"
Project ID: #28084659
About the project
Awarded to:
Greetings I can design the script which will extract the required 7 to 15 digit movie from the pdf. I'll be using the state of the art OCR AI model like 'tesseract ocr'. I have past experience of more than 4 years. We More
