Digit-Recognition-Using-Tesseract

This project uses Tesseract, an open-source OCR engine, to recognize digits from an image. Tesseract is trained on a dataset of images containing digits and used to extract the digits from a given image. The output is a set of recognized digits that can be used for further processing or analysis.

Digit-Recognition-Using-Deep-Learning

How to run?

Step Zero: Clone the repo

git clone https://github.com/BitterOcean/Digit-Recognition-Using-Tesseract.git

Step One: Cd to the folder

cd Digit-Recognition-Using-Tesseract

Step Two: Create a virtual enviroment and activate it

python3 -m venv env
source ./env/bin/activate

Step Three: Install the PIP packages/dependencies

(env)$ pip install -r requirements.txt

Step Four: Installing Tesseract on Ubuntu

$ sudo apt install tesseract-ocr -y

Step Five: Installing Fonts

In order to make the app's gui look good, you will have to install the Montserrat font. From the assets folder, install all three fonts (with .ttf format) by double clicking them.

Step Six: It's done 🎉 | Run the app

(env)$ python main.py

Demo 🎥