OCR Tesseract Jobs

15 were found based on your criteria

  • Fixed-Price – Est. Budget: $1,200.00 Posted
    Using HTML5, Node.JS and a RESTful API I want to have an implementation of object detection that can guide a user from a web page (with no plugins) to present their credit card and drivers license, capture the corresponding image, send it to the server where OCR recognition will be done, information extracted and returned to the web page for user correction. At this point I am looking for an implementation that works well with a few specific document ...
  • Fixed-Price – Est. Budget: $389.00 Posted
    Summary: Command line Ruby application that uses OCR to convert a PDF bill from Google's billing dept. to specifically formatted Excel document. Required Skills: Ruby, OCR (tesseract), command line applications, Sinatra, Unit testing This is the first in a series of four (4) or more 'scripts' that need to be written. This Job's scope is only for the first script. The remaining scripts will be awarded based on the quality, speed, and communication level perceived during the development ...
  • Hourly – Less than 1 month – Less than 10 hrs/week – Posted
    Do you know how to archive a the very best OCR result. We use Abbyy right now, but would like a better result. We run a web application, where we use OCR to recognize documents. We need to minimize mistakes, in other words we need to make OCR of our documents the very best.
  • Hourly – Less than 1 month – Less than 10 hrs/week – Posted
    We need a developer to write a PHP or Python script / module that will use Tesseract to provide text indexing on a number of images. The script will: - Connect to a DB (Parse) to obtain image locations - Return images from S3 - Use Tesseract to perform an OCR scan of the image - Transform output into a list of unique words (removing common words such as 'and', 'the' etc) - Save output list back in the DB Input images could be .gif, .jpg ...
  • Fixed-Price – Est. Budget: $30.00 Posted
    53 pages long document in PDF format (scanned) need to be converted into editable Microsoft word format. The layout (tables, graphs, diagrams, margins, spacing, font, etc.) of the output document MUST be the SAME as the original. Since the job needs to be delivered today, I'm looking for a freelancer who can effectively use OCR programs and is able to check and edit (where necessary) the output document to match the original. Deadline: ASAP
  • Fixed-Price – Est. Budget: $75.00 Posted
    I need to build an OCR solution for a customer in a Form based VB.NET Framework 4.0 application build in Visual Studio 2012. What is does is getting invoices (JPG, PNG, PDF) and puts it in the right flow by determine certain text in the image. The deliverable for this project is : A step by step tutorial how to make a workable application that you can feed an image and retrieve the text on that image. Used technology ...
  • Hourly – Less than 1 month – Less than 10 hrs/week – Posted
    I need a desktop app for Windows 8.1 that can detect a polygon defined by black and white dots moving up and down along a grid of 5 stationary vertical lines. The .jpeg image is relatively large (400 x 1000 pixels) and the dots very easy to detect. The math is pretty easy. I can send you a PDF explaining my requirement if you are available and interested. One programmer has already given this a try using AForge, but ...
  • Fixed-Price – Est. Budget: $800.00 Posted
    We are looking for a developer to create a php script to process images of product keys and convert to text using Tesseract or similar open-source OCR engine. The image processing element will be required to detect and remove all elements of the image bar the code including any background and other unwanted elements to provide the cleanest possible image to be used with Tesseract and as a backup in the event that the OCR result is not 100% accurate ...
  • Hourly – 1 to 3 months – 30+ hrs/week – Posted
    Hello, CCTV reviewing program: We need a software programmer to make us a Windows application in .net, Java or similar language to watch a bunch of video files on two screens at the same time, in sync. One play, pause, rewind and fast forward button will control all video files. This needs to be compatible with all types of video files that VLC support, if possible. The user will need to be able to click 1 button and it record ...
  • Fixed-Price – Est. Budget: $25.00 Posted
    continue develop an existing app for android: this job refer only to step 1&2 down The app needs to take a picture of a license plate and translate it into text. the app include up to 4 different screen pages . simple app with nice and friendly design. the data is past to server data base, and also have to be the option to save data on the phone memory sd card. Working with sql server data base Java language ...
loading