Face Recognition in Python |Real-time | Part 2 | FaceNet, MTCNN, SVM

Поделиться
HTML-код
  • Опубликовано: 4 ноя 2024

Комментарии • 57

  • @ChilakapatiNarsimhaShrutiSagar
    @ChilakapatiNarsimhaShrutiSagar 7 месяцев назад +1

    good ex2planation bro
    thanx for explaining , it helped me

  • @rizkynurhadhi9738
    @rizkynurhadhi9738 Год назад +4

    hi, where is "svm_model_160x160.pkl" file come from? because i didn't see you create it from part I video

  • @azamafridi-c9v
    @azamafridi-c9v Год назад +1

    Thank you Sardor, The tutorials were amazing and it helped me alot!! Thanks alot for sharing the codes and the datasets as well!!

  • @OybekValiyev-dp2sf
    @OybekValiyev-dp2sf 6 месяцев назад +1

    Juda zo'r ma'lumot oldim rahmat kattakon

  • @ElenaEroshina
    @ElenaEroshina Год назад +1

    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!

    • @sardorabdirayimov
      @sardorabdirayimov  Год назад

      Glad to he helpful ))

    • @sanjeevikumar2896
      @sanjeevikumar2896 8 месяцев назад

      hello@@sardorabdirayimov have you found any better version of it. like using any other model that gives more accuracy

  • @abdoulazizmaiga9848
    @abdoulazizmaiga9848 11 месяцев назад

    Thank you for this well-explained tutorial. Can you make a video on voice recognition? Thanks in advance.

  • @이정희-i4i3f
    @이정희-i4i3f 2 дня назад

    Assalomu alaykum aka telegramdan bog'lansan bo'ladimi sizga bir narsada maslahatizni soramoqchi edim?

  • @KoreadanAmerikagacha
    @KoreadanAmerikagacha Год назад

    I like the way how you are explaining the concepts of the process but still should work on the quality of the content 👌🙌🙌

  • @abdulrafey2492
    @abdulrafey2492 3 месяца назад +1

    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.

    • @sardorabdirayimov
      @sardorabdirayimov  3 месяца назад

      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!

  • @scorpionkingcr4523
    @scorpionkingcr4523 Год назад +4

    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.

    • @naiteekchauhan7775
      @naiteekchauhan7775 Год назад

      same brother

    • @sardorabdirayimov
      @sardorabdirayimov  Год назад +1

      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”

    • @scorpionkingcr4523
      @scorpionkingcr4523 Год назад +1

      Thank you for the help. Love from India🇮🇳❣️

  • @ManiExperience
    @ManiExperience Год назад +2

    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

  • @vanthoduong3062
    @vanthoduong3062 Год назад +1

    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 ^^.

    • @sardorabdirayimov
      @sardorabdirayimov  Год назад +1

      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”

  • @shirobi_dts
    @shirobi_dts Год назад

    I wish I had seen you sooner ❤❤❤❤❤❤

  • @rahulmahesh9700
    @rahulmahesh9700 Год назад +1

    You're great, thanks man

  • @syedhurairahhassan1944
    @syedhurairahhassan1944 6 месяцев назад

    Helpful video

  • @sanjeevikumar2896
    @sanjeevikumar2896 8 месяцев назад

    hello @sardorabdirayimov its a great work.
    have you found any better version of it. like using any other model that gives more accuracy

  • @ashutoshgupta2758
    @ashutoshgupta2758 Год назад +1

    Hi can you please make a video on liveness (spoof) detection
    Replay and image attack

  • @jayhybercarocoy4452
    @jayhybercarocoy4452 8 месяцев назад

    Im getting an error : Error during unpickling: invalid load key, '\x02' when loading the pkl file. Im using joblib to generate the pkl file

  • @abdulrahmansabri4547
    @abdulrahmansabri4547 Год назад

    Thank you for your efforts. Do you know how to increase accuracy of svm? Thanks in advance

    • @sardorabdirayimov
      @sardorabdirayimov  Год назад +1

      I suggest you to do fine-tuning of hyperparams. I hope it helps you

  • @ahmadxrizvi
    @ahmadxrizvi 7 месяцев назад

    Hii Sardor I wanted to detect face shapes but I am not able to understand where to start

  • @ЖанеркеАйткалиева-ь3щ
    @ЖанеркеАйткалиева-ь3щ 5 месяцев назад

    how to make a file in the format .npz

  • @naiteekchauhan7775
    @naiteekchauhan7775 Год назад +1

    when it identifies a face which is not included in model the code recognize that person as known how to fix this issue.

    • @sardorabdirayimov
      @sardorabdirayimov  Год назад +1

      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”

    • @naiteekchauhan7775
      @naiteekchauhan7775 Год назад

      @@sardorabdirayimov thank you brother

  • @Painted_Skull
    @Painted_Skull 8 месяцев назад

    what about Unknown face?

  • @souleimenlabsi2337
    @souleimenlabsi2337 Год назад +1

    Thanks

  • @TheChipmonks
    @TheChipmonks 8 месяцев назад

    Check for Memory Leaks, tensorflow has a leak in it
    Please help

  • @NURHASYARUSHAIDAKAMARULASRI
    @NURHASYARUSHAIDAKAMARULASRI Год назад

    hi, can i know how can i show the accuracy of the face recognition?

  • @imenmabrouk6769
    @imenmabrouk6769 Год назад

    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?

    • @sardorabdirayimov
      @sardorabdirayimov  Год назад

      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”

  • @AnjaliYadav-lo8fo
    @AnjaliYadav-lo8fo 8 месяцев назад

    is mtcnn used in this for face detection in real time ?

  • @dre_purba
    @dre_purba Год назад +1

    Can this program implemented attendance record ?...

  • @Vibes_load
    @Vibes_load Год назад

    Where did you make this file (haarcascade_frontalface_default.xml) ?
    You used it out of nowhere that's why I am asking.

    • @sardorabdirayimov
      @sardorabdirayimov  Год назад

      I downloaded it from github repo of hasrcascade.
      Check the video description! It has google drive link for that file)

  • @oybekmatkosimov5849
    @oybekmatkosimov5849 Год назад +1

    🧠💪

  • @kalong9744
    @kalong9744 Год назад

    May I ask how to train a SVM model and save to pki?

    • @sardorabdirayimov
      @sardorabdirayimov  Год назад

      Thank you for question. Please refer to: ruclips.net/video/bG2tNYs7gw8/видео.html

  • @shivanitalks2713
    @shivanitalks2713 Год назад

    Course code please

  • @ManiExperience
    @ManiExperience Год назад

    sir , please respond quickly

  • @viratkohli-yk7ls
    @viratkohli-yk7ls 7 месяцев назад

    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

  • @ragulraja2452
    @ragulraja2452 Год назад +1

    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

    • @sardorabdirayimov
      @sardorabdirayimov  Год назад

      Use cv.VideoCapture(0) instead of 1 index.
      For images instead of variable cap, create variable image= cv.imread(img_path)