Skip to content

An image of handwritten text is given as input and output of recognized text is shown as a result.

License

Notifications You must be signed in to change notification settings

thejaswin123/Handwritten_Text_Recognition

Repository files navigation

HandWritten Text Recognition

Introduction

This project aims to Extract Handwritten text from an image of any format(png,jpg,jpeg) and project is done using tesseract-OCR, OpenCV and tkinter. Optical Character Recognition (OCR) Systems aim to recognize text and bring it to editable form from the given document image, where the input text can be in machine printed, hand written or hand printed form.

Dependencies

If you dont have Python installed in your PC ,it can be installed from here python.

How to run the code

  1. Clone the Repository and extract the files
  2. Make sure the teserract-ocr file set in path C:\Program Files\Tesseract-OCR\tesseract.exe
  3. Run the code in jupyter to have better experience

Outcome:

The outcome the project is :

  • To extract the text from the given input image file .
  • To display the extracted text from that image with accuracy of 0.7-0.8 .

Exceptions considered:

  • The accuracy considered is around 0.75 - 0.80 so more than that is model cant predict
  • The language considered for the text extraction is english other than that we cant use any other language.
  • The image should be captured properly without any disturbances.

You can also try run the code in Colab and link to the notebook is given below https://colab.research.google.com/drive/1JOufSBv20vgO3j6FJN6FnhcSzmkBNXn7?usp=sharing

Output

image

About

An image of handwritten text is given as input and output of recognized text is shown as a result.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published