Learn how to harness the image-processing power of OpenCV to develop Python scripts that manipulate photos, create custom video streams, and even perform object and face tracking.
Overview
Syllabus
Introduction
- Image processing with OpenCV
- What you should know
- How to use the exercise files
- Python and OpenCV
- Using virtual environments
- Install on Mac OS
- Install on Windows
- Install on Linux: Prerequisites
- Install on Linux: Compile OpenCV
- Using OpenCV with Google Colab
- Test the install
- Get started with OpenCV and Python
- Get started with OpenCV and Python: Google Collab
- Access and understand pixel data
- Data types and structures
- Image types and color channels
- Pixel manipulations and filtering
- Blur, dilation, and erosion
- Scale and rotate images
- Use video inputs
- Create custom interfaces
- Challenge: Create a simple drawing app
- Solution: Create a simple drawing app
- Segmentation and binary images
- Simple thresholding
- Adaptive thresholding
- Skin detection
- Introduction to contours
- Contour object detection
- Area, perimeter, center, and curvature
- Canny edge detection
- Object detection overview
- Challenge: Assign object ID and attributes
- Solution: Assign object ID and attributes
- Overview of face and feature detection
- Introduction to template matching
- Application of template matching
- Haar cascading
- Face detection
- Challenge: Eye detection
- Solution: Eye detection
- Additional techniques
- Next steps
Taught by
Patrick W. Crawford
Related Courses
-
OpenCV Python Course - Learn Computer Vision and AI
5.0 -
OpenCV Course - Full Tutorial with Python
4.4 -
Python for Computer Vision with OpenCV and Deep Learning
-
OpenCV Tutorial - Develop Computer Vision Apps in the Cloud With Python
-
Computer Vision with OpenCV Python | Official OpenCV Course
-
Video Analytics using OpenCV and Python Shells
