Dictionary Representation of Deep Features for Robust Face Recognition

Slides:



Advertisements
Similar presentations
Limin Wang, Yu Qiao, and Xiaoou Tang
Advertisements

Face Representations Learning by Deep Models
UPM, Faculty of Computer Science & IT, A robust automated attendance system using face recognition techniques PhD proposal; May 2009 Gawed Nagi.
Methods in Leading Face Verification Algorithms
Spatial Pyramid Pooling in Deep Convolutional
MACHINE LEARNING AND ARTIFICIAL NEURAL NETWORKS FOR FACE VERIFICATION
Oral Defense by Sunny Tang 15 Aug 2003
Partial Face Recognition
Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION.
Person-Specific Domain Adaptation with Applications to Heterogeneous Face Recognition (HFR) Presenter: Yao-Hung Tsai Dept. of Electrical Engineering, NTU.
COMPUTER VISION: SOME CLASSICAL PROBLEMS ADWAY MITRA MACHINE LEARNING LABORATORY COMPUTER SCIENCE AND AUTOMATION INDIAN INSTITUTE OF SCIENCE June 24, 2013.
Hurieh Khalajzadeh Mohammad Mansouri Mohammad Teshnehlab
Deep face recognition Omkar M. Parkhi, Andrea Vedaldi, Andrew Zisserman.
Face recognition via sparse representation. Breakdown Problem Classical techniques New method based on sparsity Results.
Deep Convolutional Nets
PANDA: Pose Aligned Networks for Deep Attribute Modeling Ning Zhang 1,2 Manohar Paluri 1 Marć Aurelio Ranzato 1 Trevor Darrell 2 Lumbomir Boudev 1 1 Facebook.
Face Recognition Technology By Catherine jenni christy.M.sc.
Facial Smile Detection Based on Deep Learning Features Authors: Kaihao Zhang, Yongzhen Huang, Hong Wu and Liang Wang Center for Research on Intelligent.
Presented By Bhargav (08BQ1A0435).  Images play an important role in todays information because A single image represents a thousand words.  Google's.
Yann LeCun Other Methods and Applications of Deep Learning Yann Le Cun The Courant Institute of Mathematical Sciences New York University
FINGERTEC FACE ID FACE RECOGNITION Technology Overview.
Comparing TensorFlow Deep Learning Performance Using CPUs, GPUs, Local PCs and Cloud Pace University, Research Day, May 5, 2017 John Lawrence, Jonas Malmsten,
Wenchi MA CV Group EECS,KU 03/20/2017
Recent developments in object detection
Unsupervised Learning of Video Representations using LSTMs
Deep Learning for Dual-Energy X-Ray
A Discriminative Feature Learning Approach for Deep Face Recognition
Deeply learned face representations are sparse, selective, and robust
The Relationship between Deep Learning and Brain Function
Guillaume-Alexandre Bilodeau
Krishna Kumar Singh, Yong Jae Lee University of California, Davis
Regularizing Face Verification Nets To Discrete-Valued Pain Regression
FACE Facial Acquisition, Comparison and Enforcement
FACE DETECTION USING ARTIFICIAL INTELLIGENCE
Ajita Rattani and Reza Derakhshani,
Inception and Residual Architecture in Deep Convolutional Networks
EMOTIONAL INTELLIGENCE
Recovery from Occlusion in Deep Feature Space for Face Recognition
FaceNet A Unified Embedding for Face Recognition and Clustering
State-of-the-art face recognition systems
Layer-wise Performance Bottleneck Analysis of Deep Neural Networks
Bird-species Recognition Using Convolutional Neural Network
Deep Face Recognition Omkar M. Parkhi Andrea Vedaldi Andrew Zisserman
Introduction to Neural Networks
Outline Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no.
NormFace:
A Comparative Study of Convolutional Neural Network Models with Rosenblatt’s Brain Model Abu Kamruzzaman, Atik Khatri , Milind Ikke, Damiano Mastrandrea,
Deep Learning Tutorial
Bolun Wang*, Yuanshun Yao, Bimal Viswanath§ Haitao Zheng, Ben Y. Zhao
Domingo Mery Department of Computer Science
A Proposal Defense On Deep Residual Network For Face Recognition Presented By SAGAR MISHRA MECE
On Convolutional Neural Network
Lecture: Deep Convolutional Neural Networks
Outline Background Motivation Proposed Model Experimental Results
RCNN, Fast-RCNN, Faster-RCNN
Designing Neural Network Architectures Using Reinforcement Learning
Introduction to Object Tracking
Heterogeneous convolutional neural networks for visual recognition
Face Recognition: A Convolutional Neural Network Approach
Course Recap and What’s Next?
Domingo Mery Department of Computer Science
CS 534 Spring 2019 Machine Vision Showcase
Automatic Handwriting Generation
Human-object interaction
Object Detection Implementations
End-to-End Facial Alignment and Recognition
Week 3 Volodymyr Bobyr.
Directional Occlusion with Neural Network
Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer Vision.
Presentation transcript:

Dictionary Representation of Deep Features for Robust Face Recognition Feng Cen

Outline Recent advances in face recognition (FR) Our research work on occluded FR

Face Recognition: applications Biometrics / access control No action required Scan many people at once Places: airports, banks, safes Data: laptops, medical info Searching mugshot databases Tagging photo albums Detecting fake ID cards Identifying TV shows … A face recognition system is a computer application capable of identifying or verifying a person from a digital image or a video frame from a video source. One of the ways to do this is by comparing selected facial features from the image and a face database. It is typically used in security systems and can be compared to other biometrics such as fingerprint or eye iris recognition systems.[1] Recently, it has also become popular as a commercial identification and marketing tool. Identifying TV shows One of a number of apps aiming to be ‘Shazam for TV’, TVtak is an app that identifies the TV show you’re watching, simply by pointing your iPhone’s camera at the screen. Within one second, it will work out exactly the show or ad that you are watching. From there, users will be able to share details of the show they’re viewing via Twitter or Facebook, with a comment attached. The Israeli startup behind it plans to allow advertisers to use it as a ‘call to action’, too. You could be watching an ad for a new snack; taking a shot of the screen with TVtak could then take you to a voucher entitling you to a free sample. Still in beat and only available in Israel, TVtak’s rollout further could be slowed by the way it uses server-side monitoring of the output of multiple TV stations to allow for fast matching. Read more about it here. Gaming Image and face recognition is bringing a whole new dimension to gaming. Microsoft’s Kinect’s advanced motion sensing capabilities have given the Xbox 360 a whole new lease of life and opened up gaming to new audiences by completely doing away with hardware controllers. Meanwhile, startup Viewdle recently launched a game that uses face recognition to decide whether you’re a human or vampire, setting the stage for a battle between the two species. We’re sure to see many more examples face recognition in games in the future too – with all kinds of interesting possibilities. Humans: Built-in" face detection / recognition ability detection & recognition in different areas of the brain can be fooled by look-alikes Computers: Algorithms must be built from scratch Virtually perfect memory Can work 24/7 without degrading performance Can apply stricter matching criteria

Face Recognition Pipeline Detection Alignment Recognition

Two Types of Comparison in Face Recognition 1.Verification- The system compare the given individual with who that individual says they are. 1:1 2.Identification-The system compares a given individual to all the other individuals in the database and gives a ranked list of matches. 1:N

Conventional Image-based FR

Labeled Faces in the Wild (LFW) 13,233 face images 5,749 people

Deep Learning and Face Recognition CVPR 2014: DeepFace, DeepID Now: Deep learning achieves 99.80% face verification accuracy on Labeled Faces in the Wild (LFW), higher than human performance

Convolutional Neural Networks (CNN) – First proposed by Fukushima in 1980 – Improved by LeCun, Bottou, Bengio and Haffner in 1998 CNNs are basically layers of convolutions followed by subsampling and dense layers. Intuitively speaking, convolutions and subsampling layers works as feature extraction layers while a dense layer classifies which category current input belongs to using extracted features.

Popular CNN Architectures AlexNet (2012) VGG (2014) 3x3 convolution

Popular CNN architectures GoogLeNet (2014) 22 layers ResNet (2015) 152 layers

CNN-based FR DeepFace Alignment: 2D, 3D Input: RGB image 152x152 Output feature size: 4096 Parameters: ~ 120 million Y. Taigman, M. Yang, M. Ranzato, and L. Wolf. Deepface: Closing the gap to human-level performance in face verification. In CVPR, 2014

CNN-based FR DeepID For each patch: Alignment: Input: 39x31 RGB or grayscale Output feature size: 160 Alignment: 2D Patch Y. Sun, X. Wang, and X. Tang. Deep learning face representation from predicting 10,000 classes. In CVPR, 2014.

CNN-based FR VGG Face (2015) FaceNet (Google 2015) image Conv-64 maxpool fc-4096 Softmax Conv-128 Conv-256 Conv-512 fc-2622 CNN-based FR VGG Face (2015) FaceNet (Google 2015)

OpenFace https://cmusatyalab.github.io/openface/

OpenFace

What makes deep learning successful in computer vision?

Comparison of CNN-based FR Method #Training images Acc. on LFW DeepFace 4M 97.35% VGG Face 2.6M 98.95% FaceNet 200M 99.65%

Face Datasets Dataset #Subjects #Images Availability LFW 5,749 13,233 Public CACD 2,000 163,446 CASIA-WebFace 10,575 494,414 MegaFace 672,057 4,753,520 MS-Celeb-1M 100k 10M public

Is Face Recognition Solved? Performance of Face++ 99.50% on LFW Not good enough on a Chinese identification task: 10-5 FPR, 66% TPR “Results show that 90% failed cases can be solved by human. There still exists a big gap between machine recognition and human level.”

Is Face Recognition Solved? How well do current face recognition algorithms scale? Is the size of training data Important? How does age affect recognition performance? How does pose and corruption affect recognition performance? … (Kemelmacher-Shlizerman et al 2016) (MS-Celeb-1M 2016 challenge)

Outline Recent advances in face recognition (FR) Our research work on occluded FR

Motivation Deep convolutional neural networks: Outperform human vision for face verification on LFW database Fail to handle contiguous occlusion Sparse representation classifier Classical method for face images with occlusion Image space or linear feature space Difficult to deal with pose variations, facial expressions, and illumination changes etc. Training dictionary:

Observation

Assumption

Algorithm Training Testing

Algorithm Residual:

Algorithm Dimension reduction with PCA Normalization of the dictionary atom Normalization of the residual with the l2 -norm of gallery coding coefficients

Experiments: AR Database Parameters Auxiliary dictionary

Experiments: AR Database Auxiliary dictionary generation

Experiments: AR Database Performance

Experiments: AR Database A single training sample per person

Experiments: FERET database Training: 150 subjects, non-occlusion ‘ba’, ‘bj’, ‘bk’ Testing: 150 subjects, block occlusion Auxiliary dictionary: other 44 subjects

Time comsumption Less than 0.4s per image – Intel i7 CPU Dictionary coding: <2ms CNNs : <0.4s without GPU acceleration

Thank you! Q&A