Be part of the next generation of consumer and enterprise applications
What if you could learn and master some of the same techniques used in:
- Self-driving cars
- Microsoft Kinect
- Google image search
- Snapchat and Instagram filters
In this 7-hour course you will learn computer vision using Python and develop skills in topics such as image filtering and processing, pattern recognition, machine learning and face detection.
These technologies are powering the next generation of consumer and enterprise applications.
From the Internet of Things, to advertising and gaming. We want you to get on board and be part of this revolution.
The course includes theory, lots of live coding and examples, and challenges for you to build your portfolio. Students can download the source code, projects and challenge solutions. Challenges include:
- Receipt Segmenter – Find text in an image
- Currency Counter – Count coins and dollar bills in an image
- Multi-object Matching – Find Legend of Zelda rupees using a patter matching algorithm
- Face Swap – App to swap the faces of two people
Complementing the application is the theory. We’ll discuss some of the mathematics and processes that happen under the hood to give you a better understanding of the concepts.
- Colorspace conversions
- Edge Detection
- Machine Learning
- Face detection
At the end of the course, students will learn the fundamental computer vision techniques and be able to apply computer vision and image processing to their own images for a variety of cool tasks like building their own image filters, segmenting images, and even detecting faces in images!
How is machine learning covered in the course?
In this course, we will discuss some very elementary supervised machine learning topics such as support vector machines, decision trees, and Adaboost. These are just some elementary topics that lead to face detection using cascade classifiers, which use Adaboost and decision trees to determine if faces or eyes are present in an image. But to understand how cascade classifiers work, we first need to understand how Adaboost and decision trees work. However, both are techniques used in supervised learning. To understand supervised learning, we will use support vector machines.
Mohit Deshpande is a software developer author of several ZENVA courses in iOS and Android development (including Advanced Android App Development – From Padawan to Jedi).
But first and foremost, Mohit is a computer scientist. His field of research and main areas of expertise are Computer Vision and Artificial Intelligence.