Thank you!

Your message has been sent.
We'll get in touch with you ASAP!

Close
  • Recognizing Program Terms in PDF Documents

    The solution can definitions in PDF files and highlight their exact location in the text

    Project Overview

    The main challenge for our team was to develop a system that detects all terms with their definitions in PDF files. The program can recognize the font style (italic, bold or underline) and the boundaries of the term, separating it from the next sentence and indicating its exact location in the document. The most difficult part was to recognize the distribution of text in tables since standard algorithms cannot cope with this. Nevertheless, our team managed to find the optimal solution, and the customer received a useful tool that saves time searching for the necessary data in documents.

    Technologies

    What Was Done

    Our team has developed a system that discovers term definitions in Pdf files using artificial intelligence, machine learning and CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology. The most difficult task was to recognize the distribution of text in tables, as standard algorithms cannot cope with it. Nevertheless, our team managed to find the optimal solution, and the customer received a useful tool that saves time for searching the necessary data in the documents.

    In case of some specific request, or technology not listed here, you can discuss it with an expert at contact@innowise-group.com or Skype Innowise

    Get In Touch

    Need a technological solution?
    Contact us!

    Name *

    Phone

    E-mail *

    Subject *

    • Select the subject of your inquiry
      • Request for Quote
      • Partnership
      • Job Opportunities
      • Internship
      • Other

    Upload file

    Uploading…
    Done!
    Error! .

    Message

    Please be informed that when you click the Send button Innowise Group will process your personal data in accordance with our Privacy Policy for the purpose of providing you with appropriate information.