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.