Face recognition with Deep Neural Network

Download Face recognition with Deep Neural Network

Post on 16-Apr-2017

442 views

Category:

Technology

4 download

TRANSCRIPT

  • (Face Recognition with Deep Neural Network)

    ..*

    .**, , -, ,

    *: , ., , -, , **: , , -, ,

    2016-11-30

  • , 99.5%, DeepFace 99.7%, EigenFace 64.8%

    : ImageNet

    : GPU, CUDA, cuDNN, Caffe, Torch

    , ,

    CS131: Computer Vision: Foundations and Applications

    Brandon Amos

  • : , , , , CT, MRI ( ) , , , , , ...

    Nvidia.com, Omate.com

  • , Computer Vision, Image Classification, Machine & Deep Learning, CNN, RNN, Softmax, SVM, ..

    , , (ImageNet 14 ) ...

    : GPU, , ..

    : Numpy, Scikit-learn, Linux, OpenCV, Dlib, CUDA, cuDNN, Caffe, Torch, TensorFlow, ..

    , , , ,

    , NVIDIA GPU Educators Program, AI & Autonomous Robotic , .

    AI Robot of smart home

  • Pre-trained VGG models by Oxford University, *

  • ,

    ( Face Detection and Recognition: Theory and Practice )

  • : HOG

    Histogram of Oriented Gradients

    1. 2. HOG

    3. HOG

    Machine Learning is Fun! Part 4: Modern Face Recognition with Deep Learning

  • Convolutional, Non-linear, Pooling (Down sampling), Fully Connected layers, Output

    A Beginner's Guide To Understanding Convolutional Neural Networks

  • CNN: (Convolving)

    A Beginner's Guide To Understanding Convolutional Neural Networks

  • CNN: (neuron)

    A Beginner's Guide To Understanding Convolutional Neural Networks

  • CNN: (feature)

    A Beginner's Guide To Understanding Convolutional Neural Networks

    Andrew Ng

  • CNN: Backpropagation

    Forward pass, Lost function, Backward pass, Weight update MSE (Mean Squared Error), Softmax, SVM, Gradient descent, Epoch

    A Beginner's Guide To Understanding Convolutional Neural Networks

  • :

    4 226 , 50 Dlib, OpenCV, Python

  • : ,

    Python, OpenCV, Dlib, Torch, OpenFace, CUDA, cuDNN, LinuxMint

    HOG face detection, pre-trained CNN model with Linear SVM classifier

  • 92.54%, DeepFace 99.97%, 99.5%

    (True positive)

    , 2 50 0.83 0.87 0.91 0.98 0.86 0.97 0.97 0.99 0.97 0.92 0.927 0

    , 8 68 0.99 0.99 0.68 0.97 0.99 0.94 1.00 1.00 0.99 0.48 0.903 2

    , 26 0.92 0.95 0.90 0.78 0.90 0.93 0.87 0.97 0.96 0.93 0.911 1

    , 82 0.83 0.98 0.99 0.91 0.93 0.98 0.99 0.98 1.00 0.99 0.958 0

    226 0.925 3

    (True negative)

    10 0.49 0.59 0.42 0.21 0.28 0.53 0.03 0.06 0.64 0.54 0.379 6

  • ,

    ,

    ,

    , , (noise)

    , 92.5%

    ( 500-1000) GPU

    , -

  • [1] Baidus Artificial-Intelligence Supercomputer Beats Google at Image Recognition, MIT Technology Review, 2015

    [2] DeepFace: Closing the Gap to Human-Level Performance in Face Verification. Facebook AI Research Publication, 2014

    [3] Machine Learning is Fun! Part 4: Modern Face Recognition with Deep Learning, 2016

    [4] Navneet Dalal, Bill Triggs. "Histograms of Oriented Gradients for Human Detection, 2005

    [5] Vahid Kazemi, Josephine Sullivan. One Millisecond Face Alignment with an Ensemble of Regression Trees, 2014

    [6] Florian Schroff, Dmitry Kalenichenko, James Philbin. FaceNet: A Unified Embedding for Face Recognition and Clustering, 2015

    [7] Brandon Amos. OpenFace. https://cmusatyalab.github.io/openface/

    [8] D. A. Forsyth and J. Ponce. "Computer Vision: A Modern Approach (2nd edition)". Prence Hall, 2011

    [9] opencv.org, dlib.com, http://torch.ch

    [10] CUDA, cuDNN. http://nvidia.com

    [11] CS231n Convolutional Neural Networks for Visual Recognition, Stanford University

    [12] Stan Z. Li Anil K. Jain. Handbook of Face Recognition. Springer, 2004

    [13] Asit Kumar Datta, Madhura Datta, Pradipta Kumar Banerjee. Face Detection and Recognition: Theory and Practice. Taylor & Francis, 2015

    [14] Mohamed Daoudi, Anuj Srivastava, Remco Veltkamp. 3D Face Modeling, Analysis and Recognition. Wiley, 2013

  • !

    ?

    Engineers turn dreams into reality

    Hayao Miyazaki

    Slide 1Slide 2Slide 3Slide 4Slide 5Slide 6Slide 7Slide 11Slide 12Slide 13Slide 16Slide 17Slide 18Slide 19Slide 20Slide 21Slide 22Slide 23

Recommended

View more >