OpenCV with Python in 4 Hours

Notes and code used in my Python and OpenCV course on freeCodeCamp.org. You can find me on Twitter for more info on courses I'm working on currently.

Important Updates:

caer.train_val_split() is a deprecated feature in caer. Use sklearn.model_selection.train_test_split() instead. See #9 for more details.

Course Outline (with timestamps)

1. Installation

1. Using Poetry

Install poetry using your package manager or official guide.

The easiest way to install all required dependencies is as follows:

make install

2. Using pip

$ pip install -r requirements.txt

2. Basic Concepts:

• Reading Images and Video (0:04:12)
• Resizing and Rescaling Images and Video Frames (0:12:57)
• Drawing Shapes and Placing text on images (0:20:21)
• 5 Essential Methods in OpenCV (0:31:55)
• Image Transformations (0:44:13)
• Contour Detection (0:57:06)

3. Advanced Concepts:

• Switching between Colour Spaces (RGB, BGR, Grayscale, HSV and Lab) (1:12:53)
• Splitting and Merging Colour Channels (1:23:10)
• Blurring (1:31:03)
• BITWISE operations (1:44:27)
• Masking (1:53:06)
• Histogram Computation (2:01:43)
• Thresholding/Binarizing Images (2:15:22)
• Advanced Edge Detection (2:26:27)

4. Face Detection and Recognition

• Face Detection using Haar Cascades (2:35:25)
• Face Recognition using OpenCV's LBPHFaceRecognizer algorithm (2:49:05)

5. Capstone: Deep Computer Vision

• Building a Deep Computer Vision model to classify between the characters in the popular TV series The Simpsons (3:11:57)

Credits

The images in the Photos and Videos folders were downloaded from Unsplash and Pixabay, unless otherwise mentioned.

The images in the Faces folder were procurred from a repo on Kaggle.

Contributors

Please make sure you have dev dependencies installed and your PR code formatted using make format and linted using make lint