Vision Based Scratch Inspection Quality Tool

Inspects surfaces to find scratches.

Data

• Data is arranged as images in a folder with unique names
• Output will be json/csv file
• Setting file defines which test are run and parameters

Supported Platforms and Compute Environments

• Windows

Installation on Windows

1. Creating environment

PowerShell: C:\Users\udubin\AppData\Local\Programs\Python\Python310\python.exe -m venv C:\Users\udubin\Documents\Envs\pyqt5g

2. Activating

Cmd: C:\Users\udubin\Documents\Envs\pyqt5g\Scripts\activate.bat

3. OpenCV

pip install opencv-contrib-python

4. PyQt

pip install PyQt5

5. Matplotlib

pip install matplotlib

6. PyInstaller

pip install pyinstaller

7. Install realsense driver fpor image capture

pip install pyrealsense2

8. skimage :

pip install scikit-image

9. Sklearn

pip install scikit-learn

Compiling the App

In the lens_tool environment swicth to the lens_quality folder and run:

'''py pyinstaller --onefile inspection_tool_main.py '''

If this error occures: '''py _get_const_info argval = const_list[const_index] IndexError: tuple index out of range '''

Change in "C:\Users\udubin\AppData\Local\Programs\Python\Python310\Lib\dis.py":

'''py def _unpack_opargs(code): extended_arg = 0 for i in range(0, len(code), 2): op = code[i] if op >= HAVE_ARGUMENT: arg = code[i+1] | extended_arg extended_arg = (arg << 8) if op == EXTENDED_ARG else 0 else: arg = None extended_arg = 0 # Add this line yield (i, op, arg) '''