PLEASE REPLY Very good Video, Thank you for your effort. Make next video on how to stop spoofing so model should not detect faces on images or in videos but only real faces. I have another important question. Can I use Haar Cascade instead of MTCNN for face detection in PART 1? Will it reduce accuracy or have any disadvantages, despite potentially offering better speed than MTCNN? If accuracy will drop if I use Haar Cascade than tell me what should I do as I want to build real world robust face recognition attendance system application for schools, and I don't want to get complaints that software is either not detecting faces or its not recognizing students correctly. In my scenario camera will be on the top of the class's white board and should be able to detect all students of the class from above of the board, class lights may be dimmed or turned of if teacher is teaching using projector.
Dear @abdulrafey, The Haar Cascade accuracy is lower than the MTCNN. Definetely, you can change from MTCNN to Haar Cascade. I believe there are more robust solutions in the github. Check out BlazeFace or Mediapipe library. Use data augmentation before training, or move the input images to normalized space. In fact, it is a bit challenging to make 1 to 10. I hope my response helped you. Have a good day!
My SVM is trying to classify the input face into the trained faces. If you want to add unknown, I suggest you to use “softmax” activation function which return the probability of given face to the trained face. If you give mode the new face, it will return like taylor swift: 0.3 , person B: 0.5. Then you can create conditions that if probability is lower than 0.7 (as example) then it is “unknown”
I tried this code but what should I do when the person who are not trained, their faces are being recognized forcefully. instead it should be shown "UNKNOWN". so can you please help me out how to avoid that false detection.
My SVM is trying to classify the input face into the trained faces. If you want to add unknown, I suggest you to use “softmax” activation function which return the probability of given face to the trained face. If you give mode the new face, it will return like taylor swift: 0.3 , person B: 0.5. Then you can create conditions that if probability is lower than 0.7 (as example) then it is “unknown”
Another common issue: Solution: My SVM is trying to classify the input face into the trained faces. If you want to add unknown, I suggest you to use “softmax” activation function which return the probability of given face to the trained face. If you give mode the new face, it will return like taylor swift: 0.3 , person B: 0.5. Then you can create conditions that if probability is lower than 0.7 (as example) then it is “unknown”
Thank you for your video, it's really helpful. I have a question, I trained a model to recognize 2 persons, ex: A and B, and if another appears in front of the webcam, how can my model return "unknown" in this? I look forward to your reply. Thank you so much ^^.
My SVM is trying to classify the input face into the trained faces. If you want to add unknown, I suggest you to use “softmax” activation function which return the probability of given face to the trained face. If you give mode the new face, it will return like taylor swift: 0.3 , person B: 0.5. Then you can create conditions that if probability is lower than 0.7 (as example) then it is “unknown”
getting errors like this please help me WARNING:tensorflow:From C:\Users\AppData\Roaming\JetBrains\PyCharmCE2023.3\light-edit\.venv\Lib\site-packages\keras\src\backend\tensorflow\core.py:174: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead. [ERROR:0@14.564] global obsensor_uvc_stream_channel.cpp:159 cv::obsensor::getStreamChannelGroup Camera index out of range
Bruh I tried executing your method it went really well , but at last i got an error like " global obsensor_uvc_stream_channel.cpp:156 cv::obsensor::getStreamChannelGroup Camera index out of range " how to fix this and bro how to PASS a image as input
PLEASE REPLY
Very good Video, Thank you for your effort. Make next video on how to stop spoofing so model should not detect faces on images or in videos but only real faces. I have another important question.
Can I use Haar Cascade instead of MTCNN for face detection in PART 1? Will it reduce accuracy or have any disadvantages, despite potentially offering better speed than MTCNN?
If accuracy will drop if I use Haar Cascade than tell me what should I do as I want to build real world robust face recognition attendance system application for schools, and I don't want to get complaints that software is either not detecting faces or its not recognizing students correctly.
In my scenario camera will be on the top of the class's white board and should be able to detect all students of the class from above of the board, class lights may be dimmed or turned of if teacher is teaching using projector.
Dear @abdulrafey,
The Haar Cascade accuracy is lower than the MTCNN. Definetely, you can change from MTCNN to Haar Cascade. I believe there are more robust solutions in the github. Check out BlazeFace or Mediapipe library. Use data augmentation before training, or move the input images to normalized space. In fact, it is a bit challenging to make 1 to 10. I hope my response helped you. Have a good day!
hi, where is "svm_model_160x160.pkl" file come from? because i didn't see you create it from part I video
thx for this tuto plz i have a question : what if there is a total unkown and we want to classify that person is unkown?
My SVM is trying to classify the input face into the trained faces. If you want to add unknown, I suggest you to use “softmax” activation function which return the probability of given face to the trained face. If you give mode the new face, it will return like taylor swift: 0.3 , person B: 0.5. Then you can create conditions that if probability is lower than 0.7 (as example) then it is “unknown”
I tried this code but what should I do when the person who are not trained, their faces are being recognized forcefully. instead it should be shown "UNKNOWN". so can you please help me out how to avoid that false detection.
same brother
My SVM is trying to classify the input face into the trained faces. If you want to add unknown, I suggest you to use “softmax” activation function which return the probability of given face to the trained face. If you give mode the new face, it will return like taylor swift: 0.3 , person B: 0.5. Then you can create conditions that if probability is lower than 0.7 (as example) then it is “unknown”
Thank you for the help. Love from India🇮🇳❣️
sir ,what is the result for if we give the new face on a webcam, is it give unknown person or what ? could please explain this
how to make a file in the format .npz
good ex2planation bro
thanx for explaining , it helped me
when it identifies a face which is not included in model the code recognize that person as known how to fix this issue.
Another common issue:
Solution: My SVM is trying to classify the input face into the trained faces. If you want to add unknown, I suggest you to use “softmax” activation function which return the probability of given face to the trained face. If you give mode the new face, it will return like taylor swift: 0.3 , person B: 0.5. Then you can create conditions that if probability is lower than 0.7 (as example) then it is “unknown”
@@sardorabdirayimov thank you brother
Thank you for your video, it's really helpful. I have a question, I trained a model to recognize 2 persons, ex: A and B, and if another appears in front of the webcam, how can my model return "unknown" in this? I look forward to your reply. Thank you so much ^^.
My SVM is trying to classify the input face into the trained faces. If you want to add unknown, I suggest you to use “softmax” activation function which return the probability of given face to the trained face. If you give mode the new face, it will return like taylor swift: 0.3 , person B: 0.5. Then you can create conditions that if probability is lower than 0.7 (as example) then it is “unknown”
Juda zo'r ma'lumot oldim rahmat kattakon
getting errors like this please help me
WARNING:tensorflow:From C:\Users\AppData\Roaming\JetBrains\PyCharmCE2023.3\light-edit\.venv\Lib\site-packages\keras\src\backend\tensorflow\core.py:174: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.
[ERROR:0@14.564] global obsensor_uvc_stream_channel.cpp:159 cv::obsensor::getStreamChannelGroup Camera index out of range
Hi can you please make a video on liveness (spoof) detection
Replay and image attack
I will consider it! Thanks for suggesting it
Im getting an error : Error during unpickling: invalid load key, '\x02' when loading the pkl file. Im using joblib to generate the pkl file
Check for Memory Leaks, tensorflow has a leak in it
Please help
Can this program implemented attendance record ?...
Indeed, it can be implemented as attendance systems.
You're great, thanks man
Thank you for this well-explained tutorial. Can you make a video on voice recognition? Thanks in advance.
Hii Sardor I wanted to detect face shapes but I am not able to understand where to start
Thank you Sardor, The tutorials were amazing and it helped me alot!! Thanks alot for sharing the codes and the datasets as well!!
0
Thank you a lot! Your tutorial is the best ) I'm looking forward your next video and if it will be about emotions recognition it will be great!
Glad to he helpful ))
hello@@sardorabdirayimov have you found any better version of it. like using any other model that gives more accuracy
is mtcnn used in this for face detection in real time ?
Thanks
hi, can i know how can i show the accuracy of the face recognition?
sir , please respond quickly
I like the way how you are explaining the concepts of the process but still should work on the quality of the content 👌🙌🙌
what about Unknown face?
🧠💪
Where did you make this file (haarcascade_frontalface_default.xml) ?
You used it out of nowhere that's why I am asking.
I downloaded it from github repo of hasrcascade.
Check the video description! It has google drive link for that file)
Helpful video
Thank you for your efforts. Do you know how to increase accuracy of svm? Thanks in advance
I suggest you to do fine-tuning of hyperparams. I hope it helps you
hello @sardorabdirayimov its a great work.
have you found any better version of it. like using any other model that gives more accuracy
May I ask how to train a SVM model and save to pki?
Thank you for question. Please refer to: ruclips.net/video/bG2tNYs7gw8/видео.html
I wish I had seen you sooner ❤❤❤❤❤❤
Appreciated! I will be back soon
Course code please
Refer to the video description
Bruh I tried executing your method it went really well , but at last i got an error like
" global obsensor_uvc_stream_channel.cpp:156 cv::obsensor::getStreamChannelGroup Camera index out of range "
how to fix this
and bro how to PASS a image as input
Use cv.VideoCapture(0) instead of 1 index.
For images instead of variable cap, create variable image= cv.imread(img_path)