KTP-OCR ID Card text Extraction using pytesseract/Tesseract

Поделиться
HTML-код
  • Опубликовано: 23 авг 2024
  • KTP-OCR is a open source python package that attempts to create a production grade KTP extractor. The aim of the package is to extract as much information as possible yet retain the integrity of the information. For example, we will upload the photo first. And after u upload the photo the system will read the image.
    The main part of OCR (optical character recognition) was python-tesseract, python-tesseract is an optical character recognition (OCR) tool for python. That is, it will recognize and “read” the text embedded in images. lets go to the code:
    here's the blog post: about.lovia.li...
    if u want the code just open this link(don't forget to copy in drive if u want to edit it) : colab.research...
    Interested on working at Lovia? Check us out at about.lovia.life !
    #artificialintelligence #ai #extraction #photo #datascience #engineer #engineering
    #lovia #internship #intern #meeting

Комментарии • 15

  • @neeraj.kumar.1
    @neeraj.kumar.1 Год назад +2

    Thanks for uploading the video in 4K

  • @rockygultom
    @rockygultom 4 года назад +1

    Mantab Bang, Terima Kasih... 👍👍

  • @haroonrehman8156
    @haroonrehman8156 Год назад

    Waliikum Assalam

  • @jeprirasmanaginting3726
    @jeprirasmanaginting3726 3 года назад

    thank bang , sangat mebantu.
    mohon pencerahanya bang , bagaimana cara menambahkan ind.traineddata?
    terimakasih

  • @chaitanyachowdary5029
    @chaitanyachowdary5029 4 года назад

    can u add confusion matrix to it

  • @ayasheriflotfymohamed5925
    @ayasheriflotfymohamed5925 Год назад

    ظهرت عندي مشكله وأنا بكتب detect

  • @romihadi9338
    @romihadi9338 3 года назад

    bang buat tutor kalau nerapkan di java netbens dong

  • @AnuRadha-fg8ry
    @AnuRadha-fg8ry 4 года назад

    hi..can u please upload a video for text extraction for arabic numbers and dates using tesseract please...I am using the latest version of tesseract alpha 4.00

    • @firhanmaulanarusli2209
      @firhanmaulanarusli2209 4 года назад

      hy.. maybe u can change the language on the parameter pytesseract, and maybe this link might help u stackoverflow.com/questions/54763731/tesseract-returns-nothing-for-arabic-words-letters

    • @neeraj.kumar.1
      @neeraj.kumar.1 Год назад

      Hello Anu, did you get the solution ?

  • @msecureit6018
    @msecureit6018 3 года назад

    Why don't you just take the ID and get the rest info from government API to prevent false info and getting the updated data. You know everybody can print fake KTP/ID Card easily

    • @siddhivinayakzaveri7637
      @siddhivinayakzaveri7637 3 года назад

      Correct
      Usually the extracted information from the document(in this case id card) will be verified against the government database/api to decide its authenticity

  • @riololiestiono
    @riololiestiono 3 года назад

    bro asli mana bisa ketemuan gak bro

  • @aaroldaaroldson708
    @aaroldaaroldson708 3 года назад

    man, work on your pronunciation