Computer Vision is an introductory course in the dynamic field of using computers to determine useful information from images. Applications range from image search, robotics, and drone automation to self driving cars and video information extraction.
Students will learn practical skills and applied techniques in computer vision. Each concept is introduced in plain English, avoiding confusing mathematical notation and jargon, and then demonstrated using Python code to experiment with and build upon. Every module comes along with extra practical exercises you can bring home to reinforce the learned concepts. They will all be real applications that you can actually showcase as project examples or even use them yourself. For the final project, students will work with a real application, using real data and giving a solution to a problem that can be readily used by the industry. At the end of the course you will have the sufficient knowledge to move into this hot career path.
Attendees should complete and submit the following exercises:
Modify at least two of the provided algorithms to perform a different task (Implement Changes)
Finish at least one of the individual coding exercises (Perform Coding Exercises)
Creating a final real object recognition application
Attend coding classes taught by true experts working in the industry. Get practical instructions and interact with these practitioners during the classes.