You are viewing the course site for a past offering of this course. The current offering may be found here.
Lecture 20: Image Processing (23)
rwang0110

One of the most well known edge detection algorithms Hough Edge detection which uses the Hough transform in order to extract features from an image.

AadithSrinivasan

It was interesting to read about the different types of edge detection algorithms and how each one differs in how crisp/smooth the final edges are. I've had the most experience with Canny edge detection, but it was interesting to learn about Sobel detection in this lecture

o0WeiyuFeng0o

In computer vision, a common technic is to use Canny edge detection followed by using Hough transform for line detection. Canny is used to detect Edges, increase contrast, and remove noises in images. Then the Hough transform is used to detect if there is a line.

Dezhang1999

I searched about different Edge Detection algorithms, especially the one that interests me(Canny Edge Detection), https://towardsdatascience.com/canny-edge-detection-step-by-step-in-python-computer-vision-b49c3a2d8123 But I feel like it does need some ML background to understand it.

somaniarushi

I've seen this technique in an indie video game, some years ago. Back then, I didn't know what the science behind it was, but thought the aesthetic was extremely pleasing! I went back to look for it, but couldn't find the name of what I'm referring to. If anyone else knows what I'm talking about, I'd love to be able to revisit it!

stephen422

I've also seen similar effects in games as well, wonder if in practice these edge detectors are implemented in shaders (as we did using GLSL in the assignments) to achieve those visual effects.

You must be enrolled in the course to comment