This course focuses on the detection of features and boundaries in images. Feature and boundary detection is a critical preprocessing step for a variety of vision tasks including object detection, object recognition and metrology – the measurement of the physical dimensions and other properties of objects. The course presents a variety of methods for detecting features and boundaries and shows how features extracted from an image can be used to solve important vision tasks. We begin with the detection of simple but important features such as edges and corners. We show that such features can be reliably detected using operators that are based on the first and second derivatives of images. Next, we explore the concept of an “interest point” – a unique and hence useful local appearance in an image. We describe how interest points can be robustly detected using the SIFT detector. Using this detector, we describe an end-to-end solution to the problem of stitching overlapping images of a scene to obtain a wide-angle panorama. Finally, we describe the important problem of finding faces in images and show several applications of face detection.
TF
A little bit advanced, but the quality of the slides and presentations is superb.
KJ
Amazing course , Well explained and interesting assignments!!!
GP
Great overview for various topics. The highlight is the simple explanation for the SIFT algorithm operational concept imo.
GS
Another excellent course on first principles of comuter vision.
Showing: 9 of 9
Course materials are very high quality. Quizes reinforce the material from video lecture. Professor Nayar presents topics in an easy to understand manner and builds on concepts taught in previous lectures.
Great overview for various topics. The highlight is the simple explanation for the SIFT algorithm operational concept imo.
A little bit advanced, but the quality of the slides and presentations is superb.
Another excellent course on first principles of comuter vision.
Amazing course , Well explained and interesting assignments!!!
very clear
5
Very interesting course with clear and concise lectures. If you only want to sit and listen to the explanations, this is a five star course. Unfortunately, I mark it down a little because a number of quiz questions aren't very good, and those are the only place to practice/recall the material.
I feel like I have a good manager's level understanding of the subject now, but not quite up to the level of a junior engineer.
There great potential for this course to be 5 stars. However, I find the lack of practical programming assignments a big negative. The topis are interesting and well presented, but without practical assignments you just forget everything very quickly.