Facial Recognition Challenge Among FaceNet, VGG-Face, DeepFace and OpenFace

แชร์
ฝัง
  • เผยแพร่เมื่อ 3 ก.พ. 2025

ความคิดเห็น • 27

  • @assadiqbal979
    @assadiqbal979 2 ปีที่แล้ว +2

    I don't know how they calculated the accuracy of these models, but VGGface is the best.

  • @matthewbrown797
    @matthewbrown797 3 ปีที่แล้ว +3

    VGG_Face works better. If I compare a photo of the same person with and without glasses, then VHG gives the best result. Other models generally say that they are not even alike.

  • @udaym4204
    @udaym4204 ปีที่แล้ว +1

    Thnak brother i try many Face Recognition library but I get best result from deepface thank you.

    • @sefiks
      @sefiks  ปีที่แล้ว

      Then, please star the repo to support the project. Thank you.

  • @HanClinto
    @HanClinto 4 ปีที่แล้ว +1

    Very helpful video, thank you!!

  • @krupalshah1487
    @krupalshah1487 4 ปีที่แล้ว

    This video is really helpful. Thank you Sefik !

    • @sefiks
      @sefiks  4 ปีที่แล้ว +1

      You're welcome!

  • @eduardmart1237
    @eduardmart1237 2 ปีที่แล้ว

    do you have videos on how to train, retrain with frozen layers one of these models?

    • @sefiks
      @sefiks  2 ปีที่แล้ว

      if your question is for deepface, then no, it offers just pre-trained weights
      on the other hand, you can find how to train videos and tutorials in my blog

  • @SS-gu2tx
    @SS-gu2tx ปีที่แล้ว

    Which combination of model and detector_backend do you feel works the best? In terms of accuracy and speed?

    • @sefiks
      @sefiks  ปีที่แล้ว +1

      Facenet + mtcnn

    • @SS-gu2tx
      @SS-gu2tx ปีที่แล้ว

      Right on! Thank you for all your work! I'm going to throw you a sub on Paetron this week. Such a cool tool.
      Currently I've been using Facenet with mediapipe. I'm guessing mediapipe is missing detection on a lot of faces?
      @@sefiks

    • @SS-gu2tx
      @SS-gu2tx ปีที่แล้ว

      Also if getting images from all over the place. Thousands taken with random coloring, lighting, angles, etc. Should I be using align=True to generate a representation of them all?@@sefiks

    • @sefiks
      @sefiks  ปีที่แล้ว

      @@SS-gu2tx alignment increases accuracy

  • @g8kN
    @g8kN 3 ปีที่แล้ว

    Very nice video. I have a doubt: is the OpenFace's structure the same as FaceNet's structure? What would be the diffence between them?

    • @sefiks
      @sefiks  3 ปีที่แล้ว

      Structure is different, the data set they were trained different as well.

    • @g8kN
      @g8kN 3 ปีที่แล้ว

      @@sefiks ok but why did you put in the video OpenFace and FaceNet with the same structure?

    • @sefiks
      @sefiks  3 ปีที่แล้ว

      They are both based on resnet but have little differences

  • @abhiksarkar9278
    @abhiksarkar9278 4 ปีที่แล้ว

    What about arcface?

    • @sefiks
      @sefiks  4 ปีที่แล้ว +1

      ArcFace shows a close score to FaceNet. I haven't implement it when I record this video. That's why, it is not mentioned here.

    • @tanpengshi
      @tanpengshi 4 ปีที่แล้ว

      @@sefiks Would you know what are the benefits of ArcFace in comparison with FaceNet? FaceNet is considered an old algorithm.

    • @sefiks
      @sefiks  4 ปีที่แล้ว +4

      @@tanpengshi The both FaceNet and ArcFace have more than 99% accuracy. The new is not always better :)

  • @mk12347
    @mk12347 4 ปีที่แล้ว

    what about vggface2

    • @sefiks
      @sefiks  4 ปีที่แล้ว +3

      vggface2 is a facial data set. it is not a face recognition model. you can train any face recognition model with vggface2.

    • @krupalshah1487
      @krupalshah1487 4 ปีที่แล้ว

      @@sefiks Ohk... That clears my doubt. I was wondering why VGGFace2 isn't covered over here.
      That helps ! Thank you !

  • @blackout1819
    @blackout1819 2 ปีที่แล้ว

    do i need to have nvidia to use deepface? because i havn't nvidia and gpu in my linux server and i get errors:
    - Could not load dynamic library 'libcudart.so.11.0'
    - Could not load dynamic library 'libnvinfer.so.7'
    - Could not load dynamic library 'libnvinfer_plugin.so.7
    - Warning: Cannot dlopen some TensorRT libraries.

    • @sefiks
      @sefiks  2 ปีที่แล้ว

      No, gpu is not a must. Your tensorflow installation seems problematic.