You've landed at the right place. oDesk is now Upwork. Learn about the new platform.

Ocr Tesseract Jobs

6 were found based on your criteria

show all
show all
only
only
only
show all
only
only
only
only
only
show all
only
only
only
Fixed-Price - Est. Budget: $ 50 Posted
My goal is tobe able to convert numbers from images ( See the file attached ) to know what kind of numbers will be used. These are just example but they are all similar but as you can notice some are really hard to see even for human eye. Bassically I want the program that you will make to be able to convert the number targetted and convert it in actual text then the result will be used. I will also need a coder to code the second part of this job wich is using the result(numbers in text ). If you can do both well thats great ill hire you for both.
Fixed-Price - Est. Budget: $ 250 Posted
Hi, We have 2 application running at client side. We need to integrate either 'tesseract' or any better OCR open source application which can convert 2 documents (PAN CARD and VOTER ID card) into text. We would like to have it as real time thing. In case of some 5-10% error in processing team will handle. Need suggestion plus integration so the person or team has handle such issue in past can revert. We do have some code with us, which gives a better idea. Our web platform is in Python and DB we are using MongoDB. Best
Fixed-Price - Est. Budget: $ 200 Posted
We want a script that will run on a Linux server and read a single long PDF document containing documents similar to those in link below and return a JSON with extracted data. Data to extract: - Violation Number - License Plate - Date - Amount / Toll Due Sample PDFs: http://104.236.66.8/buggy/pdf_tickets.zip The uploaded documents will be the same in the link but will have different data for Violation Number, License Plate etc. Script should preferably be in PHP and use Tesseract OCR engine. Here is PHP class for Tesseract: https://github.com/thiagoalessio/tesseract-ocr-for-php If this doesn't work well then another language would be fine. You would be provided root access to a Ubuntu server and be responsible for setting everything up.
Hourly - Est. Time: 1 to 3 months, 30+ hrs/week - Posted
I have a data set of about 15 000 annual reports in PDF formats. I Have get about 1200 new reports/week. I need to do three things with this data set. This may be solved by using existing open source software, licensed soft ware or build something new. 1. Build a process tool to convert PDF->Word+Excel. Find a way to automise this. 2. Build a tool to search through PDF and find all annual reports that contain a specific word or phrase 3. Find and extract KPI:s from income statement and balance sheet and extract to a database.
Hourly - Est. Time: More than 6 months, Less than 10 hrs/week - Posted
Looking for individual(s) that have an expert understanding/experience with OCR - and to be part of our existing team that helps to continually improve our existing OCR program/workflow Currently we have an application that is running successfully that utilizes: 1) tesseract 2) pdfbox 3) imagemagick 4) poppler-utils and a few more libraries/frameworks Additionally, the current iteration of the program is written in Java - but i am open for future development or enhancements to utilize python, c# or c++ Thank you