Learn about the technology that’s revolutionising various business sectors

Have you ever found yourself in a situation where you spotted someone online wearing an article of clothing that you loved but had no way of finding out what brand it was or how you could get your hands on it? While most people would have resorted to contacting the said individual for details or Google up a storm, computer vision is one such technology that can help customers who find themselves in such a dilemma.

According to SAS, computer vision is a field of artificial intelligence (AI) that trains computers to interpret and understand the visual world. It requires a lot of data, and using digital images from cameras and videos and deep learning models, machines can now accurately identify and classify objects — and then react to what they “see.”

This technology enables computers to understand images or visual data, and allows it to take actions or make recommendations based on that information.

IBM notes that the technology is used in industries ranging from energy and utilities to manufacturing and automotive, and the market is continuing to grow and reach 48.6 billion US dollars by 2022.

“It runs analyses of data over and over until it discerns distinctions and ultimately recognise images. For example, to train a computer to recognise automobile tires, it needs to be fed vast quantities of tire images and tire-related items to learn the differences and recognise a tire, especially one with no defects,” it said.

Scientists and engineers have been trying to develop ways for machines to see and understand visual data for about 60 years. Today, we see the technology being used across a myriad of sectors.

It’s clear that computer vision is a spellbinding technology, not just for retailers but also for a suite of other sectors. And computer vision engineers are the brains who continue to develop this technology.

If you’re curious about it and are keen to understand how it works, there are many courses to give you the foundations.

Computer Vision Basics

This free course offered by the University at Buffalo and The State University of New York teaches learners the core concepts of computer vision and provides a rigorous introduction to human vision capabilities. All it will take is 13 hours for participants to fully understand how computers see and interpret the world as humans do.

The course covers crucial elements that enable computer vision: digital signal processing, neuroscience and artificial intelligence. Topics include colour, light and image formation; early, mid- and high-level vision; and mathematics. Learners will be able to apply mathematical techniques to complete computer vision tasks. 

Computer Vision Fundamentals with Watson and OpenCV

This intro-level course by IBM teaches how this dynamic technology is applied across many industries. To do so, learners will utilise Python, Watson AI, and OpenCV to process images and interact with image classification models. In just three weeks, they will also be able to build, train, and test their own custom image classifiers. 

What’s more, learners apply their newfound knowledge through several labs and exercises. The labs are performed in the Cloud, where participants will be provided access free of charge. Upon completion, learners will be able to innovate their own computer vision web app and deploy it to the Cloud.

AWS Computer Vision: Getting Started with GluonCV

In just six weeks, participants enrolled in this beginners course will be given an overview of computer vision, machine learning with Amazon Web Services, the basics of building and training a computer vision model using the Apache MXNet and GluonCV toolkit. 

To accomplish this, the course discusses artificial neural networks and other deep learning concepts.