Convert images into editable and searchable text using Tesseract OCR and Python. This tool extracts text from images (like scanned documents, screenshots or handwritten notes) with high accuracy. Using CustomTkinter for graphical user interface.
Tkinter is Python’s standard GUI library used for building cross-platform desktop applications.
CustomTkinter extends Tkinter with:
Together, they ensure a smooth UI experience on Windows, macOS and Linux.
| Component | Description |
|---|---|
| Language | Python 3.x |
| GUI Framework | CustomTkinter |
| Core Libraries | Tkinter, CustomTkinter |
| Software Engine | Tesseract-OCR |
.jpg, .png, .bmp etc.)Download and install Tesseract-OCR:
After installation, find the installation path (for example): C:\Program Files\Tesseract-OCR\tesseract.exe
Add this path into your python script or system PATH.
git clone https://github.com/iamx-ariful-islam/Image-To-Text.git
cd Image-To-Text
The requirements.txt file, lists of all the Python libraries that “image to text” depends on and installs those packages from the file:
pip install -r requirements.txt
# or
sudo pip install -r requirements.txt
python main.py
Here’s the structure of the Image To Text project:
image-to-text/
│
├── screenshots/
├── example.png
├── main.py
├── notes.txt
│── LICENSE
├── README.md
└── requirments.txt
Here are some screenshots of the Image To Text project:
Main Window
Output Main Window
About Main Window

View full notes here: 👉 notes.txt
Contributions, suggestions, and feedback are always welcome! ❤️
To contribute:
feature/new-feature)💬 You can also open an issue if you’d like to discuss a feature or report a bug.
The MIT License (MIT)
“Good design is about making things simple yet significant”
— Md. Ariful Islam