Optical character recognition (OCR) Snipping tool that copies text from screenshots to clipboard.
Built using front-end python (Tkinter, PyQt5 libraries) and Google’s Tesseract OCR engine API.
-
Download the
setup.exe
file -
Run the Installer:
-
Open the terminal (Command Prompt or PowerShell) and navigate to the directory where you downloaded
setup.exe
. -
Run the following command:
setup.exe
-
-
Follow the Installation Steps:
- Follow the on-screen instructions to complete the installation process.
-
Launch the Application:
- After installation, you can launch the application from the Start Menu, using the shortcut created on your desktop, or by pressing ctrl + shift + s.
The inspiration for this project largely came from my frustration while collecting data for Physics research. I had to manually input a lot of data from images and was unable to find easy-to-use OCR applications. Issues:
- A lot of available OCR products only work on the internet by scraping web links.
- While the applications that work on a system-wide level are either slow/cumbersome or very inaccurate.
So, I set out to resolve this by making a system-wide snipping tool that directly grabs screen data from the Operating System and processes that through Google's Tesseract Engine. It's also very quick and easy to use and the entire process can be completed in a single shortcut input and snip bound selection.