4 - Line Segment Detector with Demo - Duration 03:20

Loading...

來自 Duke University 的課程

Image and Video Processing: From Mars to Hollywood with a Stop at the Hospital

418 個評分

Duke University

Image and Video Processing: From Mars to Hollywood with a Stop at the Hospital

418 個評分

In this course, you will learn the science behind how digital images and video are made, altered, stored, and used. We will look at the vast world of digital imaging, from how computers and digital cameras form images to how digital special effects are used in Hollywood movies to how the Mars Rover was able to send photographs across millions of miles of space. The course starts by looking at how the human visual system works and then teaches you about the engineering, mathematics, and computer science that makes digital images work. You will learn the basic algorithms used for adjusting images, explore JPEG and MPEG standards for encoding and compressing video images, and go on to learn about image segmentation, noise removal and filtering. Finally, we will end with image processing techniques used in medicine. This course consists of 7 basic modules and 2 bonus (non-graded) modules. There are optional MATLAB exercises; learners will have access to MATLAB Online for the course duration. Each module is independent, so you can follow your interests.

從本節課中

Image segmentation

Not all parts of the image are the same, and students will learn the basic techniques to partition an image, from simple threshold to more advanced graph cuts and active contours. This is the first unit where student will learn about image analysis and image interpretation, and will learn why this is important, e.g., in medical imaging and object recognition.

1 - Introduction to Segmentation - Duration 04:174:17

2 - On Edges and Regions - Duration 05:175:17

3 - Hough Transform with Matlab Demo - Duration 20:5920:59

4 - Line Segment Detector with Demo - Duration 03:203:20

5 - Otsu's Segmentation with Demo - Duration 14:2514:25

6 - Congratulations - Duration 00:170:17

7 - Interactive Image Segmentation - Duration 21:1321:13

8 - Graph Cuts and Ms Office - Duration 09:349:34

9 - Mumford-Shah - Duration 05:505:50

10 - Active Contours - Introduction with ipol.im and Photoshop Demos - Duration 05:585:58

11 - Behind the Scenes of Adobe's Roto Brush - Duration 31:29 - Optional breaks at 20:30 and 27:2631:29

12 - End of the Week - Duration 00:210:21

與講師見面

Guillermo Sapiro
Professor
Electrical and Computer Engineering

Hello, and welcome back. We just discussed the half transform as

one of the ways to integrate local computation of edges.

I want to illustrate a second one. And for that, I want to use what we have

seen past, the image processing online facilities.

The basic idea is here. We are once again in the image processing

online website, and we're going to be discussing a line

segment detector that was described by the authors.

And, once again, it's an old technique to produce coherent segments, coherent

curves in the image, instead of just relying on local edge

detectors like the gradient. Let's, first of all, illustrate this by

showing one of the videos that they provide in their website.

And, it's going to be very clear already from the video what's happening.

So, let's just open this video, and see how nice it is.

So, you're now seeing edges. You're basically seeing edges all around

the image. That's really, really nice.

You're seeing the video and there're very, very coherent curves here in the

video. We don't see gradiants jumping from frame

to frame, and we can actually understand what's

happening. There is a person here, handing letters.

We can actually read the letters. Look how nice this is.

A very clear picture of what's happening in the scene, because we have these

coherent curves going around. So, this is really, really nice.

And what we are going to do now is give a couple of additional examples,

really as we have done in the past. Let's just run this demo on real time.

So, we'll click on demo. And we're going to pick an image. We see

here is an image of some chairs. And, I'm going to just, ask the algorithm

to run it, and here is the result. So, I'm going to shift, scroll this down,

and then we see the output and the input. And once again, the output is a very

clear illustration of what's happening in this scene, and we can basically see very

clear curves that describe the objects in this scene.

Let's see one more example, I think this is really fun. So, let's just illustrate

with one additional example, what's going on.

Let's pick this image, and run it.

And, once again, let me scroll down. And then, we can see the output and the

input. The output, and the input.

And from the output, basically from the coherent lines, that this algorithm has

found, basically we can see the buildings, we can understand the basic

objects in the scene. And that's because there's kind of an

integrations of what are important curves in the scene.

And what we're going to see in some of the future videos is other techniques

based on what's called active controls that also provide basically integrations

of the local behavior to give us coherent curves in the image.

Thank you very much. See you in the next video.

探索我們的目錄

免費加入並獲得個性化推薦、更新和優惠。

Coursera 致力於普及全世界最好的教育，它與全球一流大學和機構合作提供在線課程。

© 2018 Coursera Inc. 保留所有權利。

通過 App Store 下載

通過 Google Play 獲取