Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated: 1 00:00:00,490 --> 00:00:04,520 Hello and welcome to the homework of much of one face recognition. 2 00:00:04,750 --> 00:00:11,320 So this homework was about building a computer vision application that can detect smells which can be 3 00:00:11,320 --> 00:00:18,640 very useful today as indeed some businesses consist of building some computer vision tools to understand 4 00:00:18,640 --> 00:00:21,600 customers reactions when for example they're watching a movie. 5 00:00:21,600 --> 00:00:25,740 So it is widely used in the cinema industry in the movies industry. 6 00:00:25,840 --> 00:00:31,720 Some companies indeed use some computer vision tools to recognize customers expressions when they're 7 00:00:31,720 --> 00:00:35,670 watching a movie to understand what makes them smile what makes them sad. 8 00:00:35,860 --> 00:00:40,410 What makes them have strong emotions so that they can understand the customers. 9 00:00:40,540 --> 00:00:46,380 And then for example recommend some new movies which will boost their emotions. 10 00:00:46,390 --> 00:00:50,500 So today we're going to do exactly that but only with the small part. 11 00:00:50,500 --> 00:00:55,230 We're going to make a computer vision tool that will detect when a person is smiling. 12 00:00:55,450 --> 00:01:02,080 And now I get to say congratulations to the people who managed to make this smile detector but also 13 00:01:02,080 --> 00:01:05,330 I want to congratulate the people who tried to do this homework. 14 00:01:05,380 --> 00:01:09,300 Trying is also very important by trying always progress. 15 00:01:09,310 --> 00:01:12,520 We always learn some things even if we don't succeed. 16 00:01:12,640 --> 00:01:15,450 So what matters is to try hard. 17 00:01:15,500 --> 00:01:20,770 So on that note we're going to start the solution of this homework and the solution of this homework 18 00:01:20,770 --> 00:01:24,150 will include everything from the research phase. 19 00:01:24,250 --> 00:01:30,040 Because indeed when you are a computer vision scientist or even a machineries scientist or an AI engineer 20 00:01:30,280 --> 00:01:34,500 Well there is always the research phase to look for some solutions. 21 00:01:34,540 --> 00:01:40,750 So I included this research phase in the Statoil and this research phase consists of finding the hard 22 00:01:40,790 --> 00:01:47,560 cascade that will help us build this smell detector and then of course we'll proceed to the implementation 23 00:01:47,560 --> 00:01:54,190 phase and we'll of course use the previous code to be more efficient and then eventually we will watch 24 00:01:54,250 --> 00:02:00,880 the result in phase 3 we will notice that this is not optimal and therefore in Phase Four we will try 25 00:02:00,880 --> 00:02:07,820 to improve the code improve the computer vision application to make a much more accurate smell detector. 26 00:02:08,140 --> 00:02:10,600 So let's do this let's start with Phase 1. 27 00:02:10,720 --> 00:02:11,860 The research phase. 28 00:02:12,160 --> 00:02:14,500 So as you can see I'm on Google right now. 29 00:02:14,500 --> 00:02:19,750 We're going to do our research online to find the right cascade to detect this mouse. 30 00:02:19,750 --> 00:02:20,880 And so what I'm going to do. 31 00:02:21,040 --> 00:02:26,500 And actually we'll find a place where you have all the heart cascades in case some of you were wondering 32 00:02:26,500 --> 00:02:27,290 about that. 33 00:02:27,460 --> 00:02:34,330 So what I'm going to do I'm going to type here open see the heart cascade it's actually the first here 34 00:02:34,570 --> 00:02:36,370 open city the cascade. 35 00:02:36,760 --> 00:02:39,440 Let's do this and let's see what we get. 36 00:02:39,720 --> 00:02:40,020 OK. 37 00:02:40,030 --> 00:02:41,830 So we had a couple of links. 38 00:02:41,830 --> 00:02:46,670 The first one is some open city conditions on the open sea website. 39 00:02:46,720 --> 00:02:48,420 That's not what we're interested in. 40 00:02:48,700 --> 00:02:54,250 Then the second one is still in the open with the condition but that's still not what we're interested 41 00:02:54,250 --> 00:02:56,910 in because that's not where we'll find the heart cascade. 42 00:02:57,130 --> 00:03:01,060 However on the third link we might have something interesting. 43 00:03:01,240 --> 00:03:06,110 This third link is actually the good herb repository of open city. 44 00:03:06,160 --> 00:03:09,050 So if we click on the link What will we find. 45 00:03:09,100 --> 00:03:13,900 Well we will find all the different Ahar cascades that are allowed to detect features. 46 00:03:14,050 --> 00:03:21,390 Most of them are phase features not only human face features but also as you can see cat face features. 47 00:03:21,520 --> 00:03:25,590 This one for example can detect the frontal face of a cat. 48 00:03:25,630 --> 00:03:27,960 So if you have a cat you can play with it. 49 00:03:28,150 --> 00:03:34,420 And also it can detect some weird things like as you can see Russian plate number. 50 00:03:34,510 --> 00:03:36,390 So why not if you're in Russia. 51 00:03:36,550 --> 00:03:41,100 Well feel free to practice to make a tool to detect Russian plate numbers. 52 00:03:41,320 --> 00:03:44,550 And what do we see in all these Hargus games. 53 00:03:44,560 --> 00:03:52,700 We see the heart cascade smiled at X-amount and that's the one we'll use to build our smell detector. 54 00:03:52,840 --> 00:03:54,980 But you're going to see that it's not that easy. 55 00:03:55,030 --> 00:03:59,940 We will need to change some parameters in the implementation to make it work better. 56 00:04:00,190 --> 00:04:06,070 So that's the first step of this homework finding the Harker's get smothered ex-MIL Congratulations 57 00:04:06,430 --> 00:04:10,440 if you reached that step that's already exent. 58 00:04:10,500 --> 00:04:17,820 So now how do we extract this Hargus gate if some of you try to make Right-Click and then do something 59 00:04:17,820 --> 00:04:19,600 like Save Link as well. 60 00:04:19,610 --> 00:04:20,580 This will not work. 61 00:04:20,760 --> 00:04:24,180 The best way to extract that Hargus gate is to open it. 62 00:04:24,210 --> 00:04:26,400 I just clicked on it that should open right now. 63 00:04:26,400 --> 00:04:27,510 There we go. 64 00:04:27,510 --> 00:04:32,550 And inside you will find the whole heart cascade ex-MIL for the smell. 65 00:04:32,580 --> 00:04:40,080 And so what you can do then is copy all this texture and the Epogen way to do this is to scroll down 66 00:04:40,290 --> 00:04:46,180 all the way down and then press the shift key and then click again to select everything. 67 00:04:46,350 --> 00:04:54,780 Then you copy and paste it in a text editor and you save your file by giving the following name cascade. 68 00:04:54,840 --> 00:05:01,110 And of course now that ex-MIL this will work for sure you will make sure I have the right Hargus get 69 00:05:01,140 --> 00:05:02,650 X amount as smell. 70 00:05:02,820 --> 00:05:04,410 And so that's exactly what I did. 71 00:05:04,440 --> 00:05:09,710 I copied that pasted it in a text editor and saved it under this name. 72 00:05:09,750 --> 00:05:17,220 And so now what we're going to do is open an eye on that because again I really want to make sure you 73 00:05:17,220 --> 00:05:20,130 don't forget to connect to the virtual platform. 74 00:05:20,140 --> 00:05:20,670 So there we go. 75 00:05:20,670 --> 00:05:26,780 Let's do that right now so we don't forget virtual platform that I remind contains all the packages 76 00:05:26,790 --> 00:05:32,730 pre-install to to all the computer vision models that we will implement in this course and then we're 77 00:05:32,730 --> 00:05:39,990 going to launch spider and I'm going to show you what I prepared so I prepared actually a folder a homework 78 00:05:39,990 --> 00:05:46,780 folder and module one that contains this horrid cascade ex-MIL for the smile that we just made. 79 00:05:46,830 --> 00:05:49,580 And so now let's go to Val Explorer. 80 00:05:49,590 --> 00:05:52,240 Let's go to the folder that contains your computer vision. 81 00:05:52,260 --> 00:05:53,140 It is Zed. 82 00:05:53,190 --> 00:05:59,460 I'm taking this for that though because in module 1 I added a new folder a new subfolder that I called 83 00:05:59,460 --> 00:06:08,070 homework and that contains this new hard cascade underscores now that SML that I've created this homework 84 00:06:08,160 --> 00:06:13,740 folder will be provided in the next tutorial which will have the form of an article and you will get 85 00:06:13,740 --> 00:06:18,010 this homework folder that contains the four files here. 86 00:06:18,090 --> 00:06:23,610 The first two files you recognize them are X-amount for the eye and the face because we will still be 87 00:06:23,610 --> 00:06:28,560 detecting the eye and the face but then it contains just new Hargus gate x. 88 00:06:28,610 --> 00:06:34,890 For the smile and the homework solution that is open right now and inside which we will implement the 89 00:06:34,890 --> 00:06:36,000 solution. 90 00:06:36,000 --> 00:06:36,680 All right. 91 00:06:36,810 --> 00:06:41,870 So if you're ready let's proceed to face to the implementation. 92 00:06:41,880 --> 00:06:42,200 All right. 93 00:06:42,210 --> 00:06:47,940 So as I said in the beginning of this oil we're going to do that efficiently and to do that efficiently 94 00:06:47,940 --> 00:06:54,810 we're going to take our face recognition code that we implemented through all the module one where we 95 00:06:54,810 --> 00:06:56,920 detected the face and the eye. 96 00:06:57,150 --> 00:07:00,200 And we're going to simply copy paste the whole code. 97 00:07:00,210 --> 00:07:07,470 I'm copying it right now and I'm going to close this because we don't we won't need it anymore and I'm 98 00:07:07,470 --> 00:07:11,190 going to paste this code inside the homework solution. 99 00:07:11,190 --> 00:07:12,000 So good news. 100 00:07:12,000 --> 00:07:19,220 Now we simply need to add something that will detect a smile in my face and your faces of course. 101 00:07:19,230 --> 00:07:21,670 So according to you what do we need to do now. 102 00:07:21,930 --> 00:07:26,360 Well as you can see in the first code section we load the Cascades. 103 00:07:26,490 --> 00:07:31,440 So as you might guess we need to load the cascade for the smell and that's exactly what we're going 104 00:07:31,440 --> 00:07:31,890 to do. 105 00:07:32,130 --> 00:07:37,620 But before we do that let's not forget to go back to the homework folder because that's the working 106 00:07:37,620 --> 00:07:42,610 directory folder we need to be in that folder because it contains this Melkus Kate. 107 00:07:43,050 --> 00:07:51,460 So what I'm going to do now I'm going to copy this line pasted below and replace. 108 00:07:51,540 --> 00:07:56,040 I cascade by a new object that will represent the small cascade itself. 109 00:07:56,040 --> 00:07:57,390 And so I'm going to rename it. 110 00:07:57,450 --> 00:07:59,290 Smile cascade. 111 00:07:59,550 --> 00:08:01,100 And of course what do I need to do. 112 00:08:01,260 --> 00:08:07,270 I need to change the input here by the right input and the right input is no longer Hargus good. 113 00:08:07,290 --> 00:08:12,620 I SML it is hard cascade smal SML. 114 00:08:12,900 --> 00:08:13,320 Perfect. 115 00:08:13,320 --> 00:08:15,380 Now we have this Marcus Gade. 116 00:08:15,390 --> 00:08:19,770 We not only have the SML we also have to smoggiest get great. 117 00:08:19,890 --> 00:08:25,860 The next step let's move on to the second code section here where we define that function that will 118 00:08:25,860 --> 00:08:27,020 do the detections. 119 00:08:27,210 --> 00:08:34,260 And so inside this function we need to add the code that will detect a smell in the face or multiple 120 00:08:34,260 --> 00:08:39,430 smells if there are multiple faces and draw the rectangles around the smell. 121 00:08:39,510 --> 00:08:40,050 So there we go. 122 00:08:40,050 --> 00:08:45,320 Let's do this according to you do we need to do that in the reverential of the face like we did with 123 00:08:45,320 --> 00:08:45,920 the eyes. 124 00:08:46,080 --> 00:08:51,260 Well the answer is of course yes because we cannot have a smell if we don't have a face. 125 00:08:51,300 --> 00:08:54,030 So I'm going to copy the three lines here. 126 00:08:54,030 --> 00:08:57,430 That corresponds to the detection of the eyes. 127 00:08:57,630 --> 00:09:00,680 And I'm going to paste that here right. 128 00:09:00,690 --> 00:09:03,530 So these are the same that correspond to the direction of the eyes. 129 00:09:03,660 --> 00:09:08,550 And then we're going to make the right replacement to make the detection of this mouse. 130 00:09:08,580 --> 00:09:17,520 So the first thing that we need to do is replace this object here by smells smells it will contain. 131 00:09:17,560 --> 00:09:22,610 I remind the coordinates of the upper left corner of the rectangle that will detect this mouse. 132 00:09:22,650 --> 00:09:28,080 If there are several smells in the videos that is if there are several faces and so this object contains 133 00:09:28,080 --> 00:09:33,870 the coordinates of the upper left corner of the rectangles detecting this mouse and also the width and 134 00:09:33,870 --> 00:09:36,110 the height of each of these rectangles. 135 00:09:36,280 --> 00:09:37,120 OK. 136 00:09:37,330 --> 00:09:41,890 So smells this is not an object of I cascade. 137 00:09:41,900 --> 00:09:45,320 But this time smile cascade. 138 00:09:45,450 --> 00:09:53,370 And from Smout cascade we used to detect multi-skilled method that will apply on the gray region of 139 00:09:53,370 --> 00:09:59,460 interest which is the region of interest of the face with a skin factor on 1.1 and a minimum number 140 00:09:59,460 --> 00:10:00,980 of neighbors of three. 141 00:10:01,010 --> 00:10:01,790 So that's fine. 142 00:10:01,860 --> 00:10:04,740 Let's keep that for now and we'll see what happens. 143 00:10:04,740 --> 00:10:13,440 All right then we start this new loop that will iterate through the different eyes but smiles that are 144 00:10:13,500 --> 00:10:14,180 in the video. 145 00:10:14,310 --> 00:10:16,400 So I'm replacing ice by Smaltz. 146 00:10:16,410 --> 00:10:16,700 All right. 147 00:10:16,710 --> 00:10:21,110 Good but then we will replace the names of these variables here. 148 00:10:21,150 --> 00:10:25,470 We chose x y z w an H for the eyes. 149 00:10:25,490 --> 00:10:33,990 Now since we're dealing with a mouse we're going to replace x by a sex e y y s y either will Y S W and 150 00:10:34,380 --> 00:10:35,830 H by s h. 151 00:10:35,830 --> 00:10:37,360 That's safer. 152 00:10:37,410 --> 00:10:38,030 OK. 153 00:10:38,190 --> 00:10:44,380 And then therefore for each Smout detector we are going to draw the rectangle around this mouse. 154 00:10:44,460 --> 00:10:47,170 So we do that still in the region of interest. 155 00:10:47,250 --> 00:10:53,270 This time the colored region of interest because we want to have the original footage with the colors. 156 00:10:53,370 --> 00:11:03,240 Then of course we need to replace the X and e y by x x and x y and same here X plus E.W. is replaced 157 00:11:03,240 --> 00:11:12,210 by as 6 plus s w and E.W. PCH we replaced by S-W plus S H. 158 00:11:12,330 --> 00:11:13,050 Perfect. 159 00:11:13,060 --> 00:11:16,670 And now let's choose a different color for this mouse. 160 00:11:16,890 --> 00:11:27,960 So let's see we have 2 5 5 0 0 0 2 5 5 and 0 and so now that shows 0 0 and 2.5 that will give us a different 161 00:11:27,960 --> 00:11:28,490 color. 162 00:11:28,500 --> 00:11:33,880 Perfect We will have three different colors to detect the face that will be in blue. 163 00:11:33,990 --> 00:11:38,860 Then the eyes in green and now the smell will be detected in red. 164 00:11:38,880 --> 00:11:40,220 Perfect. 165 00:11:40,230 --> 00:11:47,880 All right so that's it that's actually done for phase 2 we implemented the code to detect a smile. 166 00:11:47,880 --> 00:11:49,410 So now let's have a look at the results. 167 00:11:49,410 --> 00:11:55,650 I'm going to execute this code and let's see if it manages to detect correctly some smells. 168 00:11:55,890 --> 00:12:01,950 So I'm going to select everything here and press command control plus enter to execute. 169 00:12:01,950 --> 00:12:02,930 There we go. 170 00:12:04,250 --> 00:12:05,090 Here I am. 171 00:12:05,360 --> 00:12:11,210 Hello again happy to see you again and congratulations by the way for those of you who reached this 172 00:12:11,210 --> 00:12:14,900 step with all the red rectangles in your face. 173 00:12:14,900 --> 00:12:15,850 Don't worry about this. 174 00:12:15,860 --> 00:12:17,510 This is not our final answer. 175 00:12:17,510 --> 00:12:18,580 We will improve this. 176 00:12:18,710 --> 00:12:26,020 Of course we don't have a good smell detector here so we have to do something to improve this indeed. 177 00:12:26,030 --> 00:12:32,840 So the face is correct correctly detected that either correctly detected but we see some red rectangles 178 00:12:32,900 --> 00:12:34,250 all around my face. 179 00:12:34,280 --> 00:12:35,230 That's not good. 180 00:12:35,360 --> 00:12:38,090 So according to you what do we have to do. 181 00:12:38,300 --> 00:12:46,530 Well the answer is to choose some different parameters some different parameters in our detect ask methods. 182 00:12:46,710 --> 00:12:48,250 So that's exactly what we're going to do. 183 00:12:48,480 --> 00:12:55,860 And in the end we should have only one red rectangle around my ear around my mouth and only when I'm 184 00:12:55,860 --> 00:12:58,740 smiling of course we're making smell detector. 185 00:12:58,740 --> 00:12:59,400 So let's do this. 186 00:12:59,400 --> 00:13:02,070 I'm going to press Q to quit. 187 00:13:02,190 --> 00:13:03,190 I just quit. 188 00:13:03,390 --> 00:13:11,010 And now let's proceed to phase four because phase 3 was about watching the result. 189 00:13:11,040 --> 00:13:14,130 Let's proceed to face forward to improve the code. 190 00:13:14,220 --> 00:13:21,130 So as I said we have to change the parameters and the detect multitasking method. 191 00:13:21,270 --> 00:13:21,890 All right. 192 00:13:22,080 --> 00:13:23,670 So let's look at them one by one. 193 00:13:23,700 --> 00:13:30,780 The first one is air or gray which is a region where we apply the detection according to you. 194 00:13:30,900 --> 00:13:32,310 Do we need to change that. 195 00:13:32,490 --> 00:13:34,170 Well not really. 196 00:13:34,320 --> 00:13:41,360 We're not going to replace it by Gray because then we will see some red rectangles all around my place. 197 00:13:41,400 --> 00:13:47,910 You know if I have any shape of object in my place that look like a man will see a red rectangle around 198 00:13:47,910 --> 00:13:48,140 it. 199 00:13:48,180 --> 00:13:49,360 That will be that good. 200 00:13:49,560 --> 00:13:54,040 And believe it or not that will be even worse than what we just got. 201 00:13:54,040 --> 00:14:01,530 So no we keep our eye Crais because we want to make the detection and the referential of the face for 202 00:14:01,530 --> 00:14:04,450 the simple reason that a smile is in the face. 203 00:14:04,560 --> 00:14:09,350 Then second parameter 1.1 during what this is about. 204 00:14:09,540 --> 00:14:12,270 This is about the scaling factor. 205 00:14:12,270 --> 00:14:15,440 And in fact we're going to replace it by a new number. 206 00:14:15,540 --> 00:14:22,230 We're going to choose a larger scaling factor and we're going to increase it to 1.7. 207 00:14:22,230 --> 00:14:22,970 All right. 208 00:14:23,040 --> 00:14:29,640 This is not what will help the most improve the solution but still it will help a little but the parameter 209 00:14:29,830 --> 00:14:35,640 that will definitely make a difference is the number of neighbors we really want to increase the number 210 00:14:35,640 --> 00:14:39,400 of neighbors because in some way that the direction has to be much more thorough. 211 00:14:39,510 --> 00:14:46,230 If we have a low number of minimal neighbors well anything that looks approximately like a smell will 212 00:14:46,230 --> 00:14:49,110 be detected as a smell and that will be not good. 213 00:14:49,110 --> 00:14:53,310 And that's why we obtained many rectangles in the previous detection. 214 00:14:53,310 --> 00:14:57,740 So we're going to considerably increase this minimum number of neighbors. 215 00:14:57,960 --> 00:15:02,330 Now the right number is obtained with experimentation. 216 00:15:02,340 --> 00:15:08,130 That's another thing very common when doing some computer vision or machine learning or you always have 217 00:15:08,130 --> 00:15:09,260 to experiment. 218 00:15:09,330 --> 00:15:11,630 Well this actually goes with research. 219 00:15:11,760 --> 00:15:14,440 But here we have to replace this number. 220 00:15:14,610 --> 00:15:16,930 And I'm going to give you the right number now. 221 00:15:16,950 --> 00:15:18,840 I mean the a number that works very well. 222 00:15:18,870 --> 00:15:23,770 That will get us a new one rectangle detecting when I'm smiling when you're smiling. 223 00:15:23,910 --> 00:15:25,960 And this number is 22. 224 00:15:26,250 --> 00:15:33,800 We increased the number of minimum neighbors from 3 to 22 and that's all we need to do to improve this 225 00:15:33,810 --> 00:15:35,230 computer vision solution. 226 00:15:35,490 --> 00:15:37,260 And now let's look at the results. 227 00:15:37,290 --> 00:15:40,230 I'm going to execute that again. 228 00:15:40,230 --> 00:15:41,290 There we go. 229 00:15:41,310 --> 00:15:42,350 Executed. 230 00:15:42,360 --> 00:15:44,680 Now let's see. 231 00:15:44,680 --> 00:15:44,950 All right. 232 00:15:44,950 --> 00:15:46,150 So hello again. 233 00:15:46,360 --> 00:15:52,130 Well now as you can see I'm not smelling I'm neutral and nothing happens. 234 00:15:52,210 --> 00:15:57,350 What does happen when I smile. 235 00:15:57,350 --> 00:15:58,330 There we go. 236 00:15:58,370 --> 00:16:04,340 We can see a red rectangle detecting detecting when I'm smelling. 237 00:16:04,340 --> 00:16:12,890 I'm sorry for the non natural smell but I'm trying to make this work all right here it works very well. 238 00:16:15,370 --> 00:16:17,500 We can we can try to still improve this. 239 00:16:17,500 --> 00:16:24,550 So I'm going to press Q And I'm even going to increase the minimum number of neighbors of the eyes and 240 00:16:24,550 --> 00:16:28,830 I'm also going to remove my mike because I think it's interfering with the detection. 241 00:16:29,080 --> 00:16:30,030 So let's see. 242 00:16:30,040 --> 00:16:37,860 I'm going to increase the minimum number of neighbors of the eyes to also 22 and we'll see what happens. 243 00:16:37,900 --> 00:16:38,380 So there we go. 244 00:16:38,380 --> 00:16:44,040 Now we have for the eye a scaling factor of 1.1 and 22 minimum neighbors. 245 00:16:44,080 --> 00:16:51,830 And for this now we have a scaling factor of 1.7 and 22 minimum neighbors. 246 00:16:51,850 --> 00:16:58,960 Now I'm going to put my mike a little bit away from me but not the force that you can still hear me. 247 00:16:58,990 --> 00:17:01,970 I'm going to say like that again. 248 00:17:02,080 --> 00:17:02,740 Execute. 249 00:17:02,770 --> 00:17:04,190 And now let's see what happens. 250 00:17:06,050 --> 00:17:07,510 And here are the results. 251 00:17:07,580 --> 00:17:07,780 OK. 252 00:17:07,790 --> 00:17:12,390 So first of all we see that the eye detection works much better. 253 00:17:12,400 --> 00:17:20,690 I'm trying not to smile so we can indeed see two red red to green rectangles around the eyes and not 254 00:17:20,780 --> 00:17:24,380 any around my nose as we could observe before. 255 00:17:24,630 --> 00:17:28,270 And right now I'm having a neutral smell and not smelling. 256 00:17:28,430 --> 00:17:30,230 And what does happen when I smell 257 00:17:33,930 --> 00:17:35,990 we see the red rectangle. 258 00:17:36,000 --> 00:17:36,720 Cool. 259 00:17:36,840 --> 00:17:38,860 And now what has happened when I don't smile. 260 00:17:39,890 --> 00:17:41,280 Know smile it's not 261 00:17:44,600 --> 00:17:48,850 smile no smile now no smile. 262 00:17:49,070 --> 00:17:51,190 Ok it seems to be working very well. 263 00:17:51,230 --> 00:17:53,780 I work much better than before. 264 00:17:53,780 --> 00:17:58,350 I'm glad we proved this and the smile is really working well. 265 00:17:58,520 --> 00:18:05,440 Not only we see only one rectangle when I'm smiling but also it only appears when I smell. 266 00:18:05,490 --> 00:18:08,190 All right perfect so that's done for the homework. 267 00:18:08,280 --> 00:18:10,530 Congratulations if you reached that phase. 268 00:18:10,530 --> 00:18:16,120 That is if you manage to make this mounded takes you by changing the parameters to make it work. 269 00:18:16,170 --> 00:18:21,510 That was not an easy homework we had several things to do several phases to go through. 270 00:18:21,600 --> 00:18:28,940 But if you managed to get this no phase detector detector and smell detector well really congratulations. 271 00:18:29,130 --> 00:18:34,890 And again for those of you who didn't obtain this but still try it and spend some time trying to get 272 00:18:34,890 --> 00:18:36,630 a good smell detector. 273 00:18:36,720 --> 00:18:39,630 Well congratulations to you to be relieved. 274 00:18:39,630 --> 00:18:42,510 That also made you progress definitely. 275 00:18:42,930 --> 00:18:46,480 So now it's actually the end of Mudgal one face recognition. 276 00:18:46,530 --> 00:18:49,020 I was very happy to do this for us Mudgal with you. 277 00:18:49,050 --> 00:18:52,680 Now we're going to take things at the next level with object detection. 278 00:18:52,680 --> 00:18:58,260 We're going to build a state of the art computer vision more all that beats any other model for object 279 00:18:58,260 --> 00:18:59,030 detection. 280 00:18:59,190 --> 00:19:03,300 It's as is the model single shot multi-book detection. 281 00:19:03,480 --> 00:19:05,700 So I look forward to starting Munjal too with you. 282 00:19:05,700 --> 00:19:07,570 And until then enjoy computer vision. 28727