Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated: 1 00:00:00,870 --> 00:00:06,680 Write in the previews Statoil toil we detected the faces using the detect Montell scale method from 2 00:00:06,680 --> 00:00:13,650 our face cascade object and we gather the coordinates and the width and height of the detector rectangles 3 00:00:13,950 --> 00:00:20,420 in faces we iterated through the faces to draw the rectangles around them. 4 00:00:20,590 --> 00:00:26,250 And now now that we have those rectangles we can detect the eyes because we are actually going to take 5 00:00:26,250 --> 00:00:31,920 the eyes in the referential of the faces that is in the referentially of these rectangles. 6 00:00:31,920 --> 00:00:38,730 So the first thing we're going to do to detect the eyes is to get to region of interest inside the rectangles 7 00:00:39,060 --> 00:00:45,390 and y2 region of interest because we need one region of interest for the black and white image in which 8 00:00:45,390 --> 00:00:48,500 the cascade is going to be applied to detect the eyes. 9 00:00:48,690 --> 00:00:54,900 And of course one other region of interest for the original colored image because we will draw the rectangles 10 00:00:55,200 --> 00:00:57,600 in the original color image. 11 00:00:57,600 --> 00:00:59,780 So let's get these two regions of interest. 12 00:00:59,820 --> 00:01:03,390 So the first one for the black and white image. 13 00:01:03,390 --> 00:01:13,590 I'm going to call it our I underscore gray and I'm going to take my gray image that is the black and 14 00:01:13,590 --> 00:01:20,910 white image and I'm going to take the zone of the rectangles which corresponds to the first range y 15 00:01:21,330 --> 00:01:30,270 Collin y plus H H is the height and then Same for x which is the x coordinate of the upper left corner 16 00:01:30,270 --> 00:01:31,410 of the rectangle. 17 00:01:31,500 --> 00:01:35,100 And we're taking the range from x to x. 18 00:01:35,100 --> 00:01:37,460 Plus the width which is W.. 19 00:01:37,780 --> 00:01:45,270 Right now we have our zone of interest which corresponds exactly to the zone inside the detector rectangle. 20 00:01:45,900 --> 00:01:47,880 But remember we need to do that. 21 00:01:48,030 --> 00:01:55,310 We need to get a region of interest for both the gray images and the original color image. 22 00:01:55,350 --> 00:02:03,390 So I'm introducing a new variable here which is going to be our own eye color design for the original 23 00:02:03,390 --> 00:02:09,990 color image and therefore I need to here not gray but frame which is my original color image and the 24 00:02:09,990 --> 00:02:12,330 same zones of coordinates. 25 00:02:12,330 --> 00:02:18,420 All right so now we have two region of interest the zone inside the rectangle detecting the faces both 26 00:02:18,450 --> 00:02:21,550 in the black and white image and the colored image. 27 00:02:21,930 --> 00:02:25,590 And now now that we have this we can detect the eyes. 28 00:02:25,740 --> 00:02:29,280 And we're going to detect them in the region of interest. 29 00:02:29,370 --> 00:02:36,210 Of course the gray image because the Cascades are applied in black and white images. 30 00:02:36,210 --> 00:02:38,120 And so how are we going to detect the eyes. 31 00:02:38,160 --> 00:02:43,050 Well we're going to do exactly the same as what we did for the faces we're going to introduce a new 32 00:02:43,050 --> 00:02:49,770 variable which we're going to call ice then we're going to take our eye cascade object from the cascade 33 00:02:49,770 --> 00:02:57,000 classified class and we're going to apply to detect multihulls scale method to detect the ice that is 34 00:02:57,000 --> 00:03:03,060 to get the coordinates of the upper left corner of the rectangle detecting the eyes and the width and 35 00:03:03,060 --> 00:03:05,040 the height of these rectangles. 36 00:03:05,040 --> 00:03:17,610 So basically what we simply need to do is take this and here paste it replies here faces by eyes. 37 00:03:17,650 --> 00:03:22,270 That's a new variable to get these doubles of coordinates with and height for the eyes the rectangle 38 00:03:22,270 --> 00:03:23,590 detecting the eyes. 39 00:03:23,620 --> 00:03:31,090 And here we of course need to take not our face Cascada object but our eye Cascada objects and then 40 00:03:31,090 --> 00:03:36,510 same to detect multifocal method to detect Montell scale method as a method of the Cascade pass first 41 00:03:36,520 --> 00:03:43,690 class so we can use it for as many objects of the Cascade class for class as we want and then do we 42 00:03:43,690 --> 00:03:45,990 need to replace here Grey by something. 43 00:03:46,120 --> 00:03:52,750 Yes of course because we're detecting the eyes in the referential of the face there is a zone inside 44 00:03:52,750 --> 00:03:54,480 the rectangle detecting the face. 45 00:03:54,670 --> 00:03:57,740 That's just in order to save some computation time. 46 00:03:57,880 --> 00:04:05,080 So of course we need to replace Gray here by the region of interest in black and white and that is all 47 00:04:05,140 --> 00:04:06,790 I underscore. 48 00:04:06,790 --> 00:04:07,610 Gray. 49 00:04:07,840 --> 00:04:08,740 Perfect. 50 00:04:08,830 --> 00:04:12,160 And then are we going to change these numbers here. 51 00:04:12,190 --> 00:04:19,270 I remind that this first one here corresponds to descale factor by which we reduce the size of the images 52 00:04:19,480 --> 00:04:22,590 or equivalently by which we increase the size of the filters. 53 00:04:22,590 --> 00:04:23,690 That is the kernels. 54 00:04:23,890 --> 00:04:28,770 And yes we are going to replace it by 1 point 1 again. 55 00:04:28,870 --> 00:04:30,490 This is by experimenting. 56 00:04:30,550 --> 00:04:33,900 We get some good results with that some fast result. 57 00:04:33,970 --> 00:04:39,470 So 1.1 and then are we going to keep the same number of minimum neighbors. 58 00:04:39,580 --> 00:04:46,090 I remind this is the minimum number of zones around the accepted zone to be accepted and yes we are 59 00:04:46,090 --> 00:04:48,520 going to replace it by 3. 60 00:04:48,550 --> 00:04:50,580 That will give us some good results. 61 00:04:50,590 --> 00:04:51,590 All right. 62 00:04:51,590 --> 00:04:54,190 So we now have our eyes. 63 00:04:54,190 --> 00:04:57,580 That is a table of the coordinates of the upper left corner. 64 00:04:57,580 --> 00:05:00,530 The width and the height of the rectangle surrounding the eyes. 65 00:05:00,850 --> 00:05:05,970 And so now we are ready to start a new for loop in which. 66 00:05:06,010 --> 00:05:12,280 Well again we will draw the rectangles around the ice so we'll do that in the next to tutorial and until 67 00:05:12,280 --> 00:05:13,810 then enjoy computer vision. 7313