A Convolutional Neural Network Cascade For Face Detection

Slides:



Advertisements
Similar presentations
A brief review of non-neural-network approaches to deep learning
Advertisements

Face Recognition: A Convolutional Neural Network Approach
Mixture of trees model: Face Detection, Pose Estimation and Landmark Localization Presenter: Zhang Li.
EE462 MLCV Lecture 5-6 Object Detection – Boosting Tae-Kyun Kim.
Smart Traveller with Visual Translator for OCR and Face Recognition LYU0203 FYP.
MACHINE LEARNING AND ARTIFICIAL NEURAL NETWORKS FOR FACE VERIFICATION
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
Hurieh Khalajzadeh Mohammad Mansouri Mohammad Teshnehlab
BING: Binarized Normed Gradients for Objectness Estimation at 300fps
CVPR2013 Poster Detecting and Naming Actors in Movies using Generative Appearance Models.
Learning Features and Parts for Fine-Grained Recognition Authors: Jonathan Krause, Timnit Gebru, Jia Deng, Li-Jia Li, Li Fei-Fei ICPR, 2014 Presented by:
Convolutional Restricted Boltzmann Machines for Feature Learning Mohammad Norouzi Advisor: Dr. Greg Mori Simon Fraser University 27 Nov
Computer Vision Scene Classification Using Neural Nets and a Knowledge Base Daniel Vevang.
Parsing Natural Scenes and Natural Language with Recursive Neural Networks INTERNATIONAL CONFERENCE ON MACHINE LEARNING (ICML 2011) RICHARD SOCHER CLIFF.
Cancer Metastases Classification in Histological Whole Slide Images
When deep learning meets object detection: Introduction to two technologies: SSD and YOLO Wenchi Ma.
Recent developments in object detection
CS 4501: Introduction to Computer Vision Object Localization, Detection, Semantic Segmentation Connelly Barnes Some slides from Fei-Fei Li / Andrej Karpathy.
Learning to Compare Image Patches via Convolutional Neural Networks
Demo.
The Relationship between Deep Learning and Brain Function
Object Detection based on Segment Masks
INSTITUT DE RECERCA EN VISIÓ PER COMPUTADOR I ROBÒTICA – vicorob. udg
Convolutional Neural Fabrics by Shreyas Saxena, Jakob Verbeek
Jure Zbontar, Yann LeCun
Robust Lung Nodule Classification using 2
Saliency detection Donghun Yeo CV Lab..
Face Classification: A Specialized Benchmark Study
Lecture 5 Smaller Network: CNN
R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.
Object detection.
State-of-the-art face recognition systems
Disguised Face Identification (DFI) with Facial KeyPoints using Spatial Fusion Convolutional Network Nathan Sun CIS601.
By: Kevin Yu Ph.D. in Computer Engineering
Bird-species Recognition Using Convolutional Neural Network
Convolutional Neural Networks
Learning to See in the Dark
Figure 4. Testing minimal configurations with existing models for spatiotemporal recognition. (A-B) A binary classifier is trained to separate a positive.
Counting in Dense Crowds using Deep Learning
Vessel Extraction in X-Ray Angiograms Using Deep Learning
Deep Learning Hierarchical Representations for Image Steganalysis
The Open World of Micro-Videos
Object Detection + Deep Learning
On-going research on Object Detection *Some modification after seminar
Creating Data Representations
Object Detection Creation from Scratch Samsung R&D Institute Ukraine
Faster R-CNN By Anthony Martinez.
Outline Background Motivation Proposed Model Experimental Results
Object Tracking: Comparison of
Analysis of Trained CNN (Receptive Field & Weights of Network)
RCNN, Fast-RCNN, Faster-RCNN
边缘检测年度进展概述 Ming-Ming Cheng Media Computing Lab, Nankai University
Heterogeneous convolutional neural networks for visual recognition
Convolutional Neural Network
Face Recognition: A Convolutional Neural Network Approach
Human-object interaction
Deep Object Co-Segmentation
Image Processing and Multi-domain Translation
DRC with Deep Networks Tanmay Lagare, Arpit Jain, Luis Francisco,
VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION
Semantic Segmentation
Weak-supervision based Multi-Object Tracking
End-to-End Facial Alignment and Recognition
Report 7 Brandon Silva.
Jiahe Li
Report 2 Brandon Silva.
Jiahe Li
Introduction Face detection and alignment are essential to many applications such as face recognition, facial expression recognition, age identification,
Shengcong Chen, Changxing Ding, Minfeng Liu 2018
Presentation transcript:

A Convolutional Neural Network Cascade For Face Detection 2015. 7. 28 CV lab Chanmi you

A Convolutional Neural Network Cascade For Face Detection H. Li, Z. Lin, X. Shen, J. Brandt, G. Hua, A Convolutional Neural Network Cascade for Face Detection, CVPR 2015

Contents Testing Process Training Process Experiments Conclusion

Testing process

12-net 12-calibration-net 24-net 24-calibration-net 48-calibration-net Apply 12-net to obtain face/non-face classification Calibrate each patches +NMS Input 24-net Calibrated patches Extract 12x12 patch from whole image Face patches after 12-net Apply 24-net Face patches after 24-net +NMS 24-calibration-net 48-calibration-net 48-net Calibrate each patches Calibrate each patches +NMS Apply 48-net Face patches after 48-net Calibrated patches Output

12-net (Detection net) : 12x12 detection window For each detection windows,

12-calibration-net CNN after 12-net for bounding box calibration Given detection window (𝑥, 𝑦, 𝑤, ℎ) Calibration patterns (𝑁=45) For apply

12-calibration-net (cont’d) Take the average results of the patterns After 12-calibration-net, Non-maximum suppression applied

24-net (Detection net) For multi-resolution, Fully-connected layer from 12-net is concatenated

24-calibration-net Similar with 12-calibration-net After 24-calibration-net, Non-maximum suppression applied

48-net (Detection net) For multi-resolution, Fully-connected layer from 24-net is concatenated. Relatively more complicated. After 48-net, Non-maximum suppression applied

48-calibration-net Relatively more complicated.

Training process Calibration nets Detection nets For the 𝑛-th pattern [ 𝑠 𝑛 , 𝑥 𝑛 , 𝑦 𝑛 ], apply [ 1/𝑠 𝑛 , −𝑥 𝑛 , −𝑦 𝑛 ] Detection nets 12-net Resize all training faces into 12x12 Randomly sample 200,000 non-face patches from background images Choose a threshold 𝑇 1 at 99 % recall rate 24-net Resize all training faces into 24x24 Densely scan all background images All detection windows with confidence score (after 12-net) larger than 𝑇 1 become negative training samples Choose a threshold 𝑇 2 at 97 % recall rate 48-net Resize all training faces into 48x48 Following same procedure. Neg: 5800 background images Pos: Annotated Facial Landmarks in the Wild(AFLW dataset)

Experiments Annotated Faces in the Wild (AFW dataset)

Experiments (cont’d) Face Detection Data Set and Benchmark (FDDB dataset)

Conclusion Face detection using CNN and cascade Reject non-face regions quickly at low resolution Process accurate detection at higher resolution Calibration nets are introduced in the cascade to accelerate detection and improve bounding box quality