Help computers understand images and videos
What is Computer Vision?
Computer vision is an interdisciplinary scientific field that deals with how computers can gain high-level understanding from digital images or videos. Giving computers the ability to understand and learn from these images and videos will allow us to automate many tasks. One such example of automation is self-driving cars.
What you will learn in the course?
This is a fun course; it is completely project-oriented. You will get to build 10+ projects in this course. We will start by learning some basics about images and then build some applications. We will learn different techniques for processing images and build some more applications. And then we will learn some more and build some more applications.
- Image basics
- Loading, displaying and saving images
- Haar Cascade
- Image Processing
- Smoothing & blurring
- Arithmetic Operations
- Edge detection and Contours
- Object Tracking
- Introduction to Machine Learning for Computer Vision
- Feature Extractions
- Optical Character Recognition (OCR)
- Face Detection
- Lane detection
- Playing games using hand gestures
- Invisible Cloak
- Document Alignment
- QR code scanner
- Hand-written digit recognition
- Sudoku Solver
- Extracting text from images
By the course end . . .
You will have 10+ applications that you build from scratch, all by yourself. In the process, you will develop an ability to take up any new project, identify the sub-modules involve, implement them and finally put them together to get a complete application, independently.