SlideShare a Scribd company logo
Object Detection Using the Documented Viola-Jones Technique. Student: Nathan Faggian,  Supervisors: Dr. Andrew Paplinski, Prof. Bala Srinivasan. Version  1.1
What is Object Detection? Detecting a specified object class within a image. Object detection has many applications in computer based vision. Object tracking, object recognition, scene surveillance. The focus of this project was to implement object detection, and to detect objects of the class face.
How Is It Done? A standard pattern recognition problem. Feature extraction. Something that can be representative of a face. Feature evaluation. Does this “something” really represent a face. A bit of a black art… Classification. Given a sample and its features,  what is it?
Common Techniques Strong focuses on statistics. Statistical models of images. Schneiderman-Kanade A lot of work with Neural networks. Generally slow systems. Rowley-Balauja Feature and Template methods seem to be the most common.
Features of Good Techniques Quick to compute. Classification of a face does not require a lot of offline processing. Accurate. Most good implementations can provide accuracy above the 90 percentile. Capitalization on invariance. Features are invariant. Scale, luminance, rotation.
Paul Viola and Michael Jones Devised a technique that was both robust and very quick.  15 times quicker than any technique at the time of release. A detection algorithm that could be operated in real-time.   95% accuracy at around 17fps. Understanding is the primary goal. It is a good technique !
The Viola-Jones Technique Feature extraction and feature evaluation. Rectangular features are used, with a new image representation their calculation is very fast. Classifier training and feature selection using a method called AdaBoost. A long and exhaustive training process. A degenerate decision tree of classifiers is formed. The key to the techniques speed.
Features Four basic types. They are easy to calculate. The white areas are subtracted from the black ones. A special representation of the sample called the  integral image  makes feature extraction faster.
Integral images Summed area tables A representation that means any rectangle’s area can be calculated in four indexes to the integral image.
Feature Extraction Features are extracted from sub windows of an sample image. The base size for a sub window is 24 by 24 pixels. In a 24 pixel by 24 pixel sub window there are 180,000 possible features to be calculated. What is the end result of feature extraction? A lot of data!  This is called over fitting and the amount of data must be reduced. Overfitting can be compensated to an extent by logical elimination.
Weak Classifiers A feature, a threshold and a parity. Thresholds are obtained by obtaining the mean value for the feature on both class sets and then averaging the two values. Parity defines the direction of the equality.
Feature/Classifier Evaluation Using AdaBoost the number of features is dramatically reduced. A simple algorithm that selects one feature at a time and assigns weights to the feature. Producing a strong classifier. It is a method of selecting features but also able to train classifiers in a tree as well.  Features are clustered together to form nodes in a degenerate decision tree.
AdaBoost Given a sample set of images.  For t = 1…T (rounds of boosting) A weak classifier is trained using a single feature. The error of the classifier is calculated. The classifier (or single feature) with the lowest error is selected, and combined with the priors to make a strong classifier. After a  T  rounds a  T  strong classifier is created.  It is the weighted linear combination of the weak classifiers selected.
Hard examples are isolated…
Classifier error is driven down.
The Attentional Cascade Referred here as a degenerate decision tree. The reason the technique is fast. Quick rejection of sub windows.
Motivation for a cascade Speed. Reduction of false positives. Each node is trained with the false positives of the prior.  AdaBoost can be used in conjunction with a simple bootstrapping process to drive detection error down.  Viola and Jones presented a method to do this, that  iteratively  builds boosted nodes, to a desired false positive rate.
Implementations Two implementations were realized. Matlab based. Improved flexibility, able to produce quicker results. C++ system, more of a framework. (much faster)  Far faster than the interpreted Matlab scripts yet less flexibility.
Current Progress Attentional cascade training code is complete. Matlab/C++ framework for future work. Numerous monolithic detectors have been trained.
An existing system OpenCV (intel) There is still much work to do!
Questions? How was my talk? Can anything be explained better? Email: nathan.faggian@mail.csse.monash.edu.au

More Related Content

What's hot (20)

PDF
Semantic Segmentation - Fully Convolutional Networks for Semantic Segmentation
岳華 杜
 
PDF
Image segmentation with deep learning
Antonio Rueda-Toicen
 
PPTX
Object detection
Jksuryawanshi
 
PPT
Face detection ppt
Pooja R
 
PPTX
Viola-Jones Object Detection
Venugopal Boddu
 
PPTX
Detection and recognition of face using neural network
Smriti Tikoo
 
PPTX
Yolo releases gianmaria
Deep Learning Italia
 
PPTX
Object Detection & Tracking
Akshay Gujarathi
 
PDF
Object tracking presentation
MrsShwetaBanait1
 
PPTX
Real Time Object Dectection using machine learning
pratik pratyay
 
PPTX
Face detection ppt by Batyrbek
Batyrbek Ryskhan
 
PPTX
Recognition and enhancement of traffic sign for computer generated images
Shailesh kumar
 
PPTX
Moving object detection in video surveillance
Ashfaqul Haque John
 
PPTX
Final year ppt
Shruti Chandra
 
PPTX
face detection
Smriti Tikoo
 
PPT
Facial recognition technology by vaibhav
Vaibhav P
 
PDF
Deep learning for 3-D Scene Reconstruction and Modeling
Yu Huang
 
PPTX
ppt 20BET1024.pptx
ManeetBali
 
PPTX
Image feature extraction
Rushin Shah
 
PDF
Deep Learning for Computer Vision: Image Classification (UPC 2016)
Universitat Politècnica de Catalunya
 
Semantic Segmentation - Fully Convolutional Networks for Semantic Segmentation
岳華 杜
 
Image segmentation with deep learning
Antonio Rueda-Toicen
 
Object detection
Jksuryawanshi
 
Face detection ppt
Pooja R
 
Viola-Jones Object Detection
Venugopal Boddu
 
Detection and recognition of face using neural network
Smriti Tikoo
 
Yolo releases gianmaria
Deep Learning Italia
 
Object Detection & Tracking
Akshay Gujarathi
 
Object tracking presentation
MrsShwetaBanait1
 
Real Time Object Dectection using machine learning
pratik pratyay
 
Face detection ppt by Batyrbek
Batyrbek Ryskhan
 
Recognition and enhancement of traffic sign for computer generated images
Shailesh kumar
 
Moving object detection in video surveillance
Ashfaqul Haque John
 
Final year ppt
Shruti Chandra
 
face detection
Smriti Tikoo
 
Facial recognition technology by vaibhav
Vaibhav P
 
Deep learning for 3-D Scene Reconstruction and Modeling
Yu Huang
 
ppt 20BET1024.pptx
ManeetBali
 
Image feature extraction
Rushin Shah
 
Deep Learning for Computer Vision: Image Classification (UPC 2016)
Universitat Politècnica de Catalunya
 

Viewers also liked (20)

PPT
Avihu Efrat's Viola and Jones face detection slides
wolf
 
PPSX
Face recognition technology - BEST PPT
Siddharth Modi
 
PPT
Face recognition ppt
Santosh Kumar
 
PPT
Face detection using template matching
Brijesh Borad
 
PPTX
Robust real time object detection
Erliyah Jannah
 
PPTX
Face detection By Abdul Hanan
Abdul Hanan
 
PPTX
Facial recognition system
Divya Sushma
 
PPTX
Face detection presentation slide
Sanjoy Dutta
 
PPTX
Face Recognition on MATLAB
Mukesh Taneja
 
PPSX
Real-time Face Recognition & Detection Systems 1
Suvadip Shome
 
PDF
Face detection and recognition
Derek Budde
 
PPTX
Text Detection and Recognition
Badruz Nasrin Basri
 
PDF
Face Detection System on Ada boost Algorithm Using Haar Classifiers
IJMER
 
PPTX
Face recognition using arm 7
swathi b
 
DOCX
Pest analysis of indusind bank
Viola Jones
 
PPTX
Face recogntion Using PCA Algorithm
Ashwini Awatare
 
PPTX
Object detection
Somesh Vyas
 
PPTX
Automated attendance system based on facial recognition
Dhanush Kasargod
 
PPTX
Real Time Object Tracking
Vanya Valindria
 
PPT
Eigenface For Face Recognition
Minh Tran
 
Avihu Efrat's Viola and Jones face detection slides
wolf
 
Face recognition technology - BEST PPT
Siddharth Modi
 
Face recognition ppt
Santosh Kumar
 
Face detection using template matching
Brijesh Borad
 
Robust real time object detection
Erliyah Jannah
 
Face detection By Abdul Hanan
Abdul Hanan
 
Facial recognition system
Divya Sushma
 
Face detection presentation slide
Sanjoy Dutta
 
Face Recognition on MATLAB
Mukesh Taneja
 
Real-time Face Recognition & Detection Systems 1
Suvadip Shome
 
Face detection and recognition
Derek Budde
 
Text Detection and Recognition
Badruz Nasrin Basri
 
Face Detection System on Ada boost Algorithm Using Haar Classifiers
IJMER
 
Face recognition using arm 7
swathi b
 
Pest analysis of indusind bank
Viola Jones
 
Face recogntion Using PCA Algorithm
Ashwini Awatare
 
Object detection
Somesh Vyas
 
Automated attendance system based on facial recognition
Dhanush Kasargod
 
Real Time Object Tracking
Vanya Valindria
 
Eigenface For Face Recognition
Minh Tran
 
Ad

Similar to Face Detection techniques (20)

PPT
Robust Real Time Face Detection
Syed Zaid Irshad
 
PPT
Face recognition.ppt
ZohaibAnjum14
 
PDF
机器学习Adaboost
Shocky1
 
PPTX
Rapid object detection using boosted cascade of simple features
Hirantha Pradeep
 
PPTX
The objectdetection using the Artificialintelligence.pptx
RahulRaut98
 
PPTX
IMAGE PROCESSING
ABHISHEK MAURYA
 
DOCX
Road signs detection using voila jone's algorithm with the help of opencv
MohdSalim34
 
PDF
pxc3888681
AMR ELMAGHARAY
 
PDF
HIGHLY SCALABLE, PARALLEL AND DISTRIBUTED ADABOOST ALGORITHM USING LIGHT WEIG...
ijdpsjournal
 
PPTX
A neural ada boost based facial expression recogniton System
International Islamic University
 
PPT
Cvpr2007 object category recognition p3 - discriminative models
zukun
 
PPTX
An Introduction to Face Detection
Livares Technologies Pvt Ltd
 
PPTX
LEARNING BASES OF ACTICITY
Padma Kannan
 
PDF
AUTOMATIC THEFT SECURITY SYSTEM (SMART SURVEILLANCE CAMERA)
csandit
 
PPTX
Road signs detection using voila jone's algorithm with the help of opencv
MohdSalim34
 
PDF
Face Recognition Based Intelligent Door Control System
ijtsrd
 
PDF
IRJET- Face Detection and Tracking Algorithm using Open CV with Raspberry Pi
IRJET Journal
 
PPTX
Face detection system design seminar
Sreerag Mandakathil Sreenath
 
PPT
iccv2009 tutorial: boosting and random forest - part III
zukun
 
PPTX
Cahall Final Intern Presentation
Daniel Cahall
 
Robust Real Time Face Detection
Syed Zaid Irshad
 
Face recognition.ppt
ZohaibAnjum14
 
机器学习Adaboost
Shocky1
 
Rapid object detection using boosted cascade of simple features
Hirantha Pradeep
 
The objectdetection using the Artificialintelligence.pptx
RahulRaut98
 
IMAGE PROCESSING
ABHISHEK MAURYA
 
Road signs detection using voila jone's algorithm with the help of opencv
MohdSalim34
 
pxc3888681
AMR ELMAGHARAY
 
HIGHLY SCALABLE, PARALLEL AND DISTRIBUTED ADABOOST ALGORITHM USING LIGHT WEIG...
ijdpsjournal
 
A neural ada boost based facial expression recogniton System
International Islamic University
 
Cvpr2007 object category recognition p3 - discriminative models
zukun
 
An Introduction to Face Detection
Livares Technologies Pvt Ltd
 
LEARNING BASES OF ACTICITY
Padma Kannan
 
AUTOMATIC THEFT SECURITY SYSTEM (SMART SURVEILLANCE CAMERA)
csandit
 
Road signs detection using voila jone's algorithm with the help of opencv
MohdSalim34
 
Face Recognition Based Intelligent Door Control System
ijtsrd
 
IRJET- Face Detection and Tracking Algorithm using Open CV with Raspberry Pi
IRJET Journal
 
Face detection system design seminar
Sreerag Mandakathil Sreenath
 
iccv2009 tutorial: boosting and random forest - part III
zukun
 
Cahall Final Intern Presentation
Daniel Cahall
 
Ad

Recently uploaded (20)

PDF
Jak MŚP w Europie Środkowo-Wschodniej odnajdują się w świecie AI
dominikamizerska1
 
PDF
CIFDAQ Market Wrap for the week of 4th July 2025
CIFDAQ
 
PDF
Newgen Beyond Frankenstein_Build vs Buy_Digital_version.pdf
darshakparmar
 
PPTX
"Autonomy of LLM Agents: Current State and Future Prospects", Oles` Petriv
Fwdays
 
PDF
DevBcn - Building 10x Organizations Using Modern Productivity Metrics
Justin Reock
 
PPTX
WooCommerce Workshop: Bring Your Laptop
Laura Hartwig
 
PDF
Reverse Engineering of Security Products: Developing an Advanced Microsoft De...
nwbxhhcyjv
 
PDF
Blockchain Transactions Explained For Everyone
CIFDAQ
 
PDF
NewMind AI - Journal 100 Insights After The 100th Issue
NewMind AI
 
PDF
July Patch Tuesday
Ivanti
 
PDF
Fl Studio 24.2.2 Build 4597 Crack for Windows Free Download 2025
faizk77g
 
PDF
Achieving Consistent and Reliable AI Code Generation - Medusa AI
medusaaico
 
PDF
Using FME to Develop Self-Service CAD Applications for a Major UK Police Force
Safe Software
 
PDF
CIFDAQ Market Insights for July 7th 2025
CIFDAQ
 
PDF
Empower Inclusion Through Accessible Java Applications
Ana-Maria Mihalceanu
 
PDF
HubSpot Main Hub: A Unified Growth Platform
Jaswinder Singh
 
PDF
New from BookNet Canada for 2025: BNC BiblioShare - Tech Forum 2025
BookNet Canada
 
PDF
What Makes Contify’s News API Stand Out: Key Features at a Glance
Contify
 
PDF
[Newgen] NewgenONE Marvin Brochure 1.pdf
darshakparmar
 
PDF
HCIP-Data Center Facility Deployment V2.0 Training Material (Without Remarks ...
mcastillo49
 
Jak MŚP w Europie Środkowo-Wschodniej odnajdują się w świecie AI
dominikamizerska1
 
CIFDAQ Market Wrap for the week of 4th July 2025
CIFDAQ
 
Newgen Beyond Frankenstein_Build vs Buy_Digital_version.pdf
darshakparmar
 
"Autonomy of LLM Agents: Current State and Future Prospects", Oles` Petriv
Fwdays
 
DevBcn - Building 10x Organizations Using Modern Productivity Metrics
Justin Reock
 
WooCommerce Workshop: Bring Your Laptop
Laura Hartwig
 
Reverse Engineering of Security Products: Developing an Advanced Microsoft De...
nwbxhhcyjv
 
Blockchain Transactions Explained For Everyone
CIFDAQ
 
NewMind AI - Journal 100 Insights After The 100th Issue
NewMind AI
 
July Patch Tuesday
Ivanti
 
Fl Studio 24.2.2 Build 4597 Crack for Windows Free Download 2025
faizk77g
 
Achieving Consistent and Reliable AI Code Generation - Medusa AI
medusaaico
 
Using FME to Develop Self-Service CAD Applications for a Major UK Police Force
Safe Software
 
CIFDAQ Market Insights for July 7th 2025
CIFDAQ
 
Empower Inclusion Through Accessible Java Applications
Ana-Maria Mihalceanu
 
HubSpot Main Hub: A Unified Growth Platform
Jaswinder Singh
 
New from BookNet Canada for 2025: BNC BiblioShare - Tech Forum 2025
BookNet Canada
 
What Makes Contify’s News API Stand Out: Key Features at a Glance
Contify
 
[Newgen] NewgenONE Marvin Brochure 1.pdf
darshakparmar
 
HCIP-Data Center Facility Deployment V2.0 Training Material (Without Remarks ...
mcastillo49
 

Face Detection techniques

  • 1. Object Detection Using the Documented Viola-Jones Technique. Student: Nathan Faggian, Supervisors: Dr. Andrew Paplinski, Prof. Bala Srinivasan. Version 1.1
  • 2. What is Object Detection? Detecting a specified object class within a image. Object detection has many applications in computer based vision. Object tracking, object recognition, scene surveillance. The focus of this project was to implement object detection, and to detect objects of the class face.
  • 3. How Is It Done? A standard pattern recognition problem. Feature extraction. Something that can be representative of a face. Feature evaluation. Does this “something” really represent a face. A bit of a black art… Classification. Given a sample and its features, what is it?
  • 4. Common Techniques Strong focuses on statistics. Statistical models of images. Schneiderman-Kanade A lot of work with Neural networks. Generally slow systems. Rowley-Balauja Feature and Template methods seem to be the most common.
  • 5. Features of Good Techniques Quick to compute. Classification of a face does not require a lot of offline processing. Accurate. Most good implementations can provide accuracy above the 90 percentile. Capitalization on invariance. Features are invariant. Scale, luminance, rotation.
  • 6. Paul Viola and Michael Jones Devised a technique that was both robust and very quick. 15 times quicker than any technique at the time of release. A detection algorithm that could be operated in real-time. 95% accuracy at around 17fps. Understanding is the primary goal. It is a good technique !
  • 7. The Viola-Jones Technique Feature extraction and feature evaluation. Rectangular features are used, with a new image representation their calculation is very fast. Classifier training and feature selection using a method called AdaBoost. A long and exhaustive training process. A degenerate decision tree of classifiers is formed. The key to the techniques speed.
  • 8. Features Four basic types. They are easy to calculate. The white areas are subtracted from the black ones. A special representation of the sample called the integral image makes feature extraction faster.
  • 9. Integral images Summed area tables A representation that means any rectangle’s area can be calculated in four indexes to the integral image.
  • 10. Feature Extraction Features are extracted from sub windows of an sample image. The base size for a sub window is 24 by 24 pixels. In a 24 pixel by 24 pixel sub window there are 180,000 possible features to be calculated. What is the end result of feature extraction? A lot of data! This is called over fitting and the amount of data must be reduced. Overfitting can be compensated to an extent by logical elimination.
  • 11. Weak Classifiers A feature, a threshold and a parity. Thresholds are obtained by obtaining the mean value for the feature on both class sets and then averaging the two values. Parity defines the direction of the equality.
  • 12. Feature/Classifier Evaluation Using AdaBoost the number of features is dramatically reduced. A simple algorithm that selects one feature at a time and assigns weights to the feature. Producing a strong classifier. It is a method of selecting features but also able to train classifiers in a tree as well. Features are clustered together to form nodes in a degenerate decision tree.
  • 13. AdaBoost Given a sample set of images. For t = 1…T (rounds of boosting) A weak classifier is trained using a single feature. The error of the classifier is calculated. The classifier (or single feature) with the lowest error is selected, and combined with the priors to make a strong classifier. After a T rounds a T strong classifier is created. It is the weighted linear combination of the weak classifiers selected.
  • 14. Hard examples are isolated…
  • 15. Classifier error is driven down.
  • 16. The Attentional Cascade Referred here as a degenerate decision tree. The reason the technique is fast. Quick rejection of sub windows.
  • 17. Motivation for a cascade Speed. Reduction of false positives. Each node is trained with the false positives of the prior. AdaBoost can be used in conjunction with a simple bootstrapping process to drive detection error down. Viola and Jones presented a method to do this, that iteratively builds boosted nodes, to a desired false positive rate.
  • 18. Implementations Two implementations were realized. Matlab based. Improved flexibility, able to produce quicker results. C++ system, more of a framework. (much faster) Far faster than the interpreted Matlab scripts yet less flexibility.
  • 19. Current Progress Attentional cascade training code is complete. Matlab/C++ framework for future work. Numerous monolithic detectors have been trained.
  • 20. An existing system OpenCV (intel) There is still much work to do!
  • 21. Questions? How was my talk? Can anything be explained better? Email: [email protected]