Doc Scanner is a small OCR app using the Tesseract library to extract written content from a photo.
The simple GUI loads the photo (jpg or png) into the screen for verification and allows the user to scan the image, modify the resulting text and save it anywhere in the hard drive. The prototype only works for English.
This app was designed completely in Python, using Tkinter for the GUI and PyTesseract for the OCR Engine. PyInstaller was used for compiling the distributable version.
To use Doc Scanner, simply download and extract the zip file, then execute file doc.exe inside the directory.
Skills Used: Python Tkinter Tesseract OCR End-product compiling