simple_OCR_copying_from_image

Image_OCR_Text (OpenCV)

Using PyTessaract to create OCR (Optical Character Recognition) to extract text from an image file in Python

Packages used in the Project

1. TKinter
2. PyTessaract
3. OpenCV

Initial Setup

1. tkinter package

for taking Input of an image from the user

pip install tk

2. PyTessaract package

to recognize text from the image

pip install pytesseract

2. OpenCV package

to read an image and perform certain image-processing techniques

pip install opencv-python

3. Save an image you want to extract text from

Important

1. If that didn't work then you can try these commands
2. If there is still a problem then you can install through a .whl file for that particular package

Test Drive

1. Run the file "main.py" in the initial directory
2. Enter the path for the image.
3. Open the "extracted_text.txt" file created after running the program.

Note

1. Remember to perform the initial setup before test-driving
2. You can also directly run "test2.py" or "test3.py" files they have different preprocessing applied to them.