SlideShare uma empresa Scribd logo
1 de 29
Robust Real-Time Object DetectionAuthor: Paul Viola, Michael J. Jones
International Journal of Computer Vision 57(2), 137–154, 2004
Presented by ERLI – M10115801
Background & Motivation
• Detecting object on real time
• Detecting face
Outline
Introduction
Image Representation – Integral Image
Learning Algorithm – AdaBoost
Cascade Classifier
Experiment and Result
Introduction
Object Detection
Detection System
Object Detection
>> Face Detection
Paul Viola Michael J. Jones
Introduction
Detection System
24x24
Detection
Window
The size of
detection window
will be enlarged
with a certain scale
Introduction
Image
Representation
Integral Image
Integral Image Feature
Integral Image
• Image representation
• Feature
• The integral image at location x,y
contains the sum of the pixels
above and to the left of x,y
Integral Image | AdaBoost | Cascade
Sum of pixel
value in this area
(x,y)
Integral Image
• Image representation
• Feature
• The integral image at location x,y
contains the sum of the pixels
above and to the left of x,y
Integral Image | AdaBoost | Cascade
Sum of pixel
value in this area
(x,y)
How to calculate D ?
A B
C D
1 2
3 4
Integral Image
• Image representation
• Feature
Integral Image | AdaBoost | Cascade
How to calculate D ?
D = (1+4) – (2+3)
A B
C D
1 2
3 4
1
2
3
4
Integral Image Feature
Integral Image | AdaBoost | Cascade
Detection window
A
B
C
D
Detection window
Detection window Detection window
The value of integral image
feature is the difference between
the sum of the pixels within the
two rectangular regions.
S1 S2 |S1-S2|
Integral Image Feature
Integral Image | AdaBoost | Cascade
The size and position of feature can be
different.
• The eye region is darker
than the upper-cheeks.
• The nose bridge region is
brighter than the eyes.
Integral Image
• Different size and position of integral image give so many possible
features
• How do we obtain the best representing features possible?
• How can we refrain from wasting time on image background? (i.e.
non-object)
Integral Image | AdaBoost | Cascade
Good Feature Not Good Feature
AdaBoost…
AdaBoost
Weak Classifier
Strong Classifier
AdaBoost
Weak Classifier
• Consist of just 1 feature
• 1 feature that can separate the image data with error rate less than 0.5
Feature 1
Feature 2
Feature 3
θ 1
θ 2
θ 3
Weak
Classifier 1
Weak
Classifier 2
Weak
Classifier 3
1/10 = 0.1
6/10 = 0.6
3/10 = 0.3
Integral Image | AdaBoost | Cascade
Strong Classifier
• Set of features/weak classifier
Integral Image | AdaBoost | Cascade
1 1 1
strong
1
1 ( ) ( )
( ) 2
0 otherwise
n n nh h
h
x x
x
 
Weak Classifier
How to build the strong classifier?
AdaBoost
AdaBoost
Pseudo Code
• T = number of feature we choose
• h(x, f,p,θ)) = A weak classifier
• f = feature
• θ = threshold
• p = polarity indicating the direction of the
inequality (less than or greater than θ)
Integral Image | AdaBoost | Cascade
 AdaBoost starts with a uniform distribution
of “weights” over training examples.
 Select the classifier with the lowest weighted
error (i.e. a “weak” classifier)
 Increase the weights on the training
examples that were misclassified.
 (Repeat)
 At the end, carefully make a linear
combination of the weak classifiers obtained
at all iterations.
AdaBoost Ilustration
1 1 1
strong
1
1 ( ) ( )
( ) 2
0 otherwise
n n nh h
h
x x
x
 
Slide taken from a presentation by Qing Chen, Discover Lab, University of Ottawa
Integral Image | AdaBoost | Cascade
Classifier
• By increasing the number of features per classifier, we:
◦ Increase detection accuracy.
◦ Decrease detection speed.
• Experiments showed that a 200 feature classifier
makes a good face detector:
◦ Takes 0.7 seconds to scan an 384 by 288 pixel image.
• Problem: Not real time! (At most 0.067 seconds
needed).
Integral Image | AdaBoost | Cascade
Cascade of Classifier…
Cascade Classfifier
Cascade
Cascade of Classifier
• Classifier is structured as several layer/hierarchy
• Each layer consist of 1 strong classifier (set of weak
classifiers/features)
• Evaluating all input window
• Ignore non-face window
• Continue for processing “suspected” face window
Integral Image | AdaBoost | Cascade
Cascade of Classifier
• The number of feature/weak classifier in every layer is based on the
value of false positive rate and detection rate determined by user
• Previous layers have simpler classifier than next layer
Integral Image | AdaBoost | Cascade
Stage 1 Stage 2 Stage 3 …
Further
Processing
Input Image
Window
Ignore/Reject
Input
Ignore/Reject
Input
Ignore/Reject
Input
Ignore/Reject
Input
Y
N
Y
N
Y
N
Y
N
Cascade of Classifier
Integral Image | AdaBoost | Cascade
Stage 1
(2 feature)
N
Y Stage 2
(2++ feature)
Cascade of
Classifier
Pseudo Code
Integral Image | AdaBoost | Cascade
Experiment
• Training set
• Face: 4916 labeled frontal faces
•Testing / Real-time test
• Face: MIT + CMU frontal face test set
• Contain: 130 images with 507 labeled frontal faces
Result
Cascade Classifier
v.s
Non Cascade Classifier
Cascade classifier
nearly 10x faster.
Result
They use dataset MIT+CMU with 5 images removed
Voting (Using 3 Viola-Jones Classifier with different parameter)
++- : Face
--+ : Non Face
Failure Mode
• Informal observation suggests that the face detector can detect
faces that are tilted up to about ±15 degrees in plane and about ± 45
degrees out of plane
• Harsh backlighting in which the faces are very dark while the
background is relatively light sometimes causes failures
• Proposed algorithm will also fail on significantly occluded faces
Real-Time Object Detection

Mais conteúdo relacionado

Mais procurados

Object Detection Classification, tracking and Counting
Object Detection Classification, tracking and CountingObject Detection Classification, tracking and Counting
Object Detection Classification, tracking and CountingShounak Mitra
 
Content Based Image Retrieval
Content Based Image Retrieval Content Based Image Retrieval
Content Based Image Retrieval Swati Chauhan
 
Deep learning for object detection
Deep learning for object detectionDeep learning for object detection
Deep learning for object detectionWenjing Chen
 
Smoothing Filters in Spatial Domain
Smoothing Filters in Spatial DomainSmoothing Filters in Spatial Domain
Smoothing Filters in Spatial DomainMadhu Bala
 
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
[PR12] You Only Look Once (YOLO): Unified Real-Time Object DetectionTaegyun Jeon
 
Automated Face Detection System
Automated Face Detection SystemAutomated Face Detection System
Automated Face Detection SystemAbhiroop Ghatak
 
PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.
PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.
PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.Sunghoon Joo
 
OpenCV presentation series- part 1
OpenCV presentation series- part 1OpenCV presentation series- part 1
OpenCV presentation series- part 1Sairam Adithya
 
Moving object detection in video surveillance
Moving object detection in video surveillanceMoving object detection in video surveillance
Moving object detection in video surveillanceAshfaqul Haque John
 
Face detection and recognition
Face detection and recognitionFace detection and recognition
Face detection and recognitionPankaj Thakur
 
Object detection
Object detectionObject detection
Object detectionSomesh Vyas
 
Edge linking in image processing
Edge linking in image processingEdge linking in image processing
Edge linking in image processingVARUN KUMAR
 
Lect 02 second portion
Lect 02  second portionLect 02  second portion
Lect 02 second portionMoe Moe Myint
 
Content based image retrieval(cbir)
Content based image retrieval(cbir)Content based image retrieval(cbir)
Content based image retrieval(cbir)paddu123
 
Multi Object Tracking | Presentation 1 | ID 103001
Multi Object Tracking | Presentation 1 | ID 103001Multi Object Tracking | Presentation 1 | ID 103001
Multi Object Tracking | Presentation 1 | ID 103001Md. Minhazul Haque
 
Histogram equalization
Histogram equalizationHistogram equalization
Histogram equalization11mr11mahesh
 
Chapter 1 and 2 gonzalez and woods
Chapter 1 and 2 gonzalez and woodsChapter 1 and 2 gonzalez and woods
Chapter 1 and 2 gonzalez and woodsasodariyabhavesh
 

Mais procurados (20)

Object Detection Classification, tracking and Counting
Object Detection Classification, tracking and CountingObject Detection Classification, tracking and Counting
Object Detection Classification, tracking and Counting
 
Content Based Image Retrieval
Content Based Image Retrieval Content Based Image Retrieval
Content Based Image Retrieval
 
Deep learning for object detection
Deep learning for object detectionDeep learning for object detection
Deep learning for object detection
 
Smoothing Filters in Spatial Domain
Smoothing Filters in Spatial DomainSmoothing Filters in Spatial Domain
Smoothing Filters in Spatial Domain
 
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
 
Automated Face Detection System
Automated Face Detection SystemAutomated Face Detection System
Automated Face Detection System
 
PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.
PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.
PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.
 
OpenCV presentation series- part 1
OpenCV presentation series- part 1OpenCV presentation series- part 1
OpenCV presentation series- part 1
 
Histogram Equalization
Histogram EqualizationHistogram Equalization
Histogram Equalization
 
Moving object detection in video surveillance
Moving object detection in video surveillanceMoving object detection in video surveillance
Moving object detection in video surveillance
 
DIP - Image Restoration
DIP - Image RestorationDIP - Image Restoration
DIP - Image Restoration
 
Face detection and recognition
Face detection and recognitionFace detection and recognition
Face detection and recognition
 
Object detection
Object detectionObject detection
Object detection
 
Edge linking in image processing
Edge linking in image processingEdge linking in image processing
Edge linking in image processing
 
Lect 02 second portion
Lect 02  second portionLect 02  second portion
Lect 02 second portion
 
Content based image retrieval(cbir)
Content based image retrieval(cbir)Content based image retrieval(cbir)
Content based image retrieval(cbir)
 
Multi Object Tracking | Presentation 1 | ID 103001
Multi Object Tracking | Presentation 1 | ID 103001Multi Object Tracking | Presentation 1 | ID 103001
Multi Object Tracking | Presentation 1 | ID 103001
 
Watershed
WatershedWatershed
Watershed
 
Histogram equalization
Histogram equalizationHistogram equalization
Histogram equalization
 
Chapter 1 and 2 gonzalez and woods
Chapter 1 and 2 gonzalez and woodsChapter 1 and 2 gonzalez and woods
Chapter 1 and 2 gonzalez and woods
 

Destaque

Face Detection techniques
Face Detection techniquesFace Detection techniques
Face Detection techniquesAbhineet Bhamra
 
Face detection ppt by Batyrbek
Face detection ppt by Batyrbek Face detection ppt by Batyrbek
Face detection ppt by Batyrbek Batyrbek Ryskhan
 
Application de la théorie de graphe au problème de flot maximum
Application de la théorie de graphe au problème de flot maximumApplication de la théorie de graphe au problème de flot maximum
Application de la théorie de graphe au problème de flot maximumchagra bassem
 
Haar like feature
Haar like featureHaar like feature
Haar like featureczech0923
 
Pest analysis of indusind bank
Pest analysis of indusind bankPest analysis of indusind bank
Pest analysis of indusind bankViola Jones
 
Avihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slidesAvihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slideswolf
 
Face Detection
Face DetectionFace Detection
Face DetectionAmr Sheta
 
NEC NEOFACE- Biometric Face Recognition System
NEC NEOFACE- Biometric Face Recognition SystemNEC NEOFACE- Biometric Face Recognition System
NEC NEOFACE- Biometric Face Recognition SystemNECIndia
 
Face Recognition with OpenCV and scikit-learn
Face Recognition with OpenCV and scikit-learnFace Recognition with OpenCV and scikit-learn
Face Recognition with OpenCV and scikit-learnShiqiao Du
 
Introduction to OpenCV (with Java)
Introduction to OpenCV (with Java)Introduction to OpenCV (with Java)
Introduction to OpenCV (with Java)Luigi De Russis
 
Face Recognition using OpenCV
Face Recognition using OpenCVFace Recognition using OpenCV
Face Recognition using OpenCVVasile Chelban
 
Facial Expression Recognition / Removal
Facial Expression Recognition / RemovalFacial Expression Recognition / Removal
Facial Expression Recognition / RemovalRafael Dahis
 
Real-time Face Recognition & Detection Systems 1
Real-time Face Recognition & Detection Systems 1Real-time Face Recognition & Detection Systems 1
Real-time Face Recognition & Detection Systems 1Suvadip Shome
 
Facial recognition system
Facial recognition systemFacial recognition system
Facial recognition systemDivya Sushma
 
局所特徴量と統計学習手法による物体検出
局所特徴量と統計学習手法による物体検出局所特徴量と統計学習手法による物体検出
局所特徴量と統計学習手法による物体検出MPRG_Chubu_University
 

Destaque (20)

Face Detection techniques
Face Detection techniquesFace Detection techniques
Face Detection techniques
 
Face detection ppt by Batyrbek
Face detection ppt by Batyrbek Face detection ppt by Batyrbek
Face detection ppt by Batyrbek
 
Application de la théorie de graphe au problème de flot maximum
Application de la théorie de graphe au problème de flot maximumApplication de la théorie de graphe au problème de flot maximum
Application de la théorie de graphe au problème de flot maximum
 
Face Detection
Face DetectionFace Detection
Face Detection
 
Haar like feature
Haar like featureHaar like feature
Haar like feature
 
20141008物体検出器
20141008物体検出器20141008物体検出器
20141008物体検出器
 
Pest analysis of indusind bank
Pest analysis of indusind bankPest analysis of indusind bank
Pest analysis of indusind bank
 
Avihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slidesAvihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slides
 
Drone delivery service
Drone delivery serviceDrone delivery service
Drone delivery service
 
Face Detection
Face DetectionFace Detection
Face Detection
 
NEC NEOFACE- Biometric Face Recognition System
NEC NEOFACE- Biometric Face Recognition SystemNEC NEOFACE- Biometric Face Recognition System
NEC NEOFACE- Biometric Face Recognition System
 
Face Recognition with OpenCV and scikit-learn
Face Recognition with OpenCV and scikit-learnFace Recognition with OpenCV and scikit-learn
Face Recognition with OpenCV and scikit-learn
 
Introduction to OpenCV (with Java)
Introduction to OpenCV (with Java)Introduction to OpenCV (with Java)
Introduction to OpenCV (with Java)
 
Face Recognition using OpenCV
Face Recognition using OpenCVFace Recognition using OpenCV
Face Recognition using OpenCV
 
Facial Expression Recognition / Removal
Facial Expression Recognition / RemovalFacial Expression Recognition / Removal
Facial Expression Recognition / Removal
 
Real-time Face Recognition & Detection Systems 1
Real-time Face Recognition & Detection Systems 1Real-time Face Recognition & Detection Systems 1
Real-time Face Recognition & Detection Systems 1
 
Week6 face detection
Week6 face detectionWeek6 face detection
Week6 face detection
 
Facial recognition system
Facial recognition systemFacial recognition system
Facial recognition system
 
局所特徴量と統計学習手法による物体検出
局所特徴量と統計学習手法による物体検出局所特徴量と統計学習手法による物体検出
局所特徴量と統計学習手法による物体検出
 
Amazon Prime Air
Amazon Prime AirAmazon Prime Air
Amazon Prime Air
 

Semelhante a Real-Time Object Detection

Robust Real Time Face Detection
Robust Real Time Face DetectionRobust Real Time Face Detection
Robust Real Time Face DetectionSyed Zaid Irshad
 
Viola-Jones Object Detection
Viola-Jones Object DetectionViola-Jones Object Detection
Viola-Jones Object DetectionVenugopal Boddu
 
机器学习Adaboost
机器学习Adaboost机器学习Adaboost
机器学习AdaboostShocky1
 
Seeing is Not Believing: Camouflage Attacks on Image Scaling Algorithms Review
Seeing is Not Believing: Camouflage Attacks on Image Scaling Algorithms ReviewSeeing is Not Believing: Camouflage Attacks on Image Scaling Algorithms Review
Seeing is Not Believing: Camouflage Attacks on Image Scaling Algorithms ReviewJunyaup Kim
 
Rapid object detection using boosted cascade of simple features
Rapid object detection using boosted  cascade of simple featuresRapid object detection using boosted  cascade of simple features
Rapid object detection using boosted cascade of simple featuresHirantha Pradeep
 
Online video object segmentation via convolutional trident network
Online video object segmentation via convolutional trident networkOnline video object segmentation via convolutional trident network
Online video object segmentation via convolutional trident networkNAVER Engineering
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonAditya Bhattacharya
 
Face recognition.ppt
Face recognition.pptFace recognition.ppt
Face recognition.pptZohaibAnjum14
 
Road signs detection using voila jone's algorithm with the help of opencv
Road signs detection using voila jone's algorithm with the help of opencvRoad signs detection using voila jone's algorithm with the help of opencv
Road signs detection using voila jone's algorithm with the help of opencvMohdSalim34
 
cvpresentation-190812154654 (1).pptx
cvpresentation-190812154654 (1).pptxcvpresentation-190812154654 (1).pptx
cvpresentation-190812154654 (1).pptxPyariMohanJena
 
ppt 20BET1024.pptx
ppt 20BET1024.pptxppt 20BET1024.pptx
ppt 20BET1024.pptxManeetBali
 
GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用
GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用
GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用NVIDIA Taiwan
 
3D Multi Object GAN
3D Multi Object GAN3D Multi Object GAN
3D Multi Object GANYu Nishimura
 
Eugene Khvedchenya. State of the art Image Augmentations with Albumentations.
Eugene Khvedchenya. State of the art Image Augmentations with Albumentations.Eugene Khvedchenya. State of the art Image Augmentations with Albumentations.
Eugene Khvedchenya. State of the art Image Augmentations with Albumentations.Lviv Startup Club
 
ImageProcessingWithMatlab(HasithaEdiriweera)
ImageProcessingWithMatlab(HasithaEdiriweera)ImageProcessingWithMatlab(HasithaEdiriweera)
ImageProcessingWithMatlab(HasithaEdiriweera)Hasitha Ediriweera
 
Introduction to object detection
Introduction to object detectionIntroduction to object detection
Introduction to object detectionAmar Jindal
 
Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image ProcessingAzharo7
 

Semelhante a Real-Time Object Detection (20)

IMAGE PROCESSING
IMAGE PROCESSINGIMAGE PROCESSING
IMAGE PROCESSING
 
Robust Real Time Face Detection
Robust Real Time Face DetectionRobust Real Time Face Detection
Robust Real Time Face Detection
 
Face detection system design seminar
Face detection system design seminarFace detection system design seminar
Face detection system design seminar
 
Viola-Jones Object Detection
Viola-Jones Object DetectionViola-Jones Object Detection
Viola-Jones Object Detection
 
机器学习Adaboost
机器学习Adaboost机器学习Adaboost
机器学习Adaboost
 
thesis
thesisthesis
thesis
 
Seeing is Not Believing: Camouflage Attacks on Image Scaling Algorithms Review
Seeing is Not Believing: Camouflage Attacks on Image Scaling Algorithms ReviewSeeing is Not Believing: Camouflage Attacks on Image Scaling Algorithms Review
Seeing is Not Believing: Camouflage Attacks on Image Scaling Algorithms Review
 
Rapid object detection using boosted cascade of simple features
Rapid object detection using boosted  cascade of simple featuresRapid object detection using boosted  cascade of simple features
Rapid object detection using boosted cascade of simple features
 
Online video object segmentation via convolutional trident network
Online video object segmentation via convolutional trident networkOnline video object segmentation via convolutional trident network
Online video object segmentation via convolutional trident network
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathon
 
Face recognition.ppt
Face recognition.pptFace recognition.ppt
Face recognition.ppt
 
Road signs detection using voila jone's algorithm with the help of opencv
Road signs detection using voila jone's algorithm with the help of opencvRoad signs detection using voila jone's algorithm with the help of opencv
Road signs detection using voila jone's algorithm with the help of opencv
 
cvpresentation-190812154654 (1).pptx
cvpresentation-190812154654 (1).pptxcvpresentation-190812154654 (1).pptx
cvpresentation-190812154654 (1).pptx
 
ppt 20BET1024.pptx
ppt 20BET1024.pptxppt 20BET1024.pptx
ppt 20BET1024.pptx
 
GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用
GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用
GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用
 
3D Multi Object GAN
3D Multi Object GAN3D Multi Object GAN
3D Multi Object GAN
 
Eugene Khvedchenya. State of the art Image Augmentations with Albumentations.
Eugene Khvedchenya. State of the art Image Augmentations with Albumentations.Eugene Khvedchenya. State of the art Image Augmentations with Albumentations.
Eugene Khvedchenya. State of the art Image Augmentations with Albumentations.
 
ImageProcessingWithMatlab(HasithaEdiriweera)
ImageProcessingWithMatlab(HasithaEdiriweera)ImageProcessingWithMatlab(HasithaEdiriweera)
ImageProcessingWithMatlab(HasithaEdiriweera)
 
Introduction to object detection
Introduction to object detectionIntroduction to object detection
Introduction to object detection
 
Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image Processing
 

Real-Time Object Detection

  • 1. Robust Real-Time Object DetectionAuthor: Paul Viola, Michael J. Jones International Journal of Computer Vision 57(2), 137–154, 2004 Presented by ERLI – M10115801
  • 2. Background & Motivation • Detecting object on real time • Detecting face
  • 3. Outline Introduction Image Representation – Integral Image Learning Algorithm – AdaBoost Cascade Classifier Experiment and Result
  • 5. Object Detection >> Face Detection Paul Viola Michael J. Jones Introduction
  • 6. Detection System 24x24 Detection Window The size of detection window will be enlarged with a certain scale Introduction
  • 8. Integral Image • Image representation • Feature • The integral image at location x,y contains the sum of the pixels above and to the left of x,y Integral Image | AdaBoost | Cascade Sum of pixel value in this area (x,y)
  • 9. Integral Image • Image representation • Feature • The integral image at location x,y contains the sum of the pixels above and to the left of x,y Integral Image | AdaBoost | Cascade Sum of pixel value in this area (x,y) How to calculate D ? A B C D 1 2 3 4
  • 10. Integral Image • Image representation • Feature Integral Image | AdaBoost | Cascade How to calculate D ? D = (1+4) – (2+3) A B C D 1 2 3 4 1 2 3 4
  • 11. Integral Image Feature Integral Image | AdaBoost | Cascade Detection window A B C D Detection window Detection window Detection window The value of integral image feature is the difference between the sum of the pixels within the two rectangular regions. S1 S2 |S1-S2|
  • 12. Integral Image Feature Integral Image | AdaBoost | Cascade The size and position of feature can be different. • The eye region is darker than the upper-cheeks. • The nose bridge region is brighter than the eyes.
  • 13. Integral Image • Different size and position of integral image give so many possible features • How do we obtain the best representing features possible? • How can we refrain from wasting time on image background? (i.e. non-object) Integral Image | AdaBoost | Cascade Good Feature Not Good Feature AdaBoost…
  • 15. Weak Classifier • Consist of just 1 feature • 1 feature that can separate the image data with error rate less than 0.5 Feature 1 Feature 2 Feature 3 θ 1 θ 2 θ 3 Weak Classifier 1 Weak Classifier 2 Weak Classifier 3 1/10 = 0.1 6/10 = 0.6 3/10 = 0.3 Integral Image | AdaBoost | Cascade
  • 16. Strong Classifier • Set of features/weak classifier Integral Image | AdaBoost | Cascade 1 1 1 strong 1 1 ( ) ( ) ( ) 2 0 otherwise n n nh h h x x x   Weak Classifier How to build the strong classifier? AdaBoost
  • 17. AdaBoost Pseudo Code • T = number of feature we choose • h(x, f,p,θ)) = A weak classifier • f = feature • θ = threshold • p = polarity indicating the direction of the inequality (less than or greater than θ) Integral Image | AdaBoost | Cascade
  • 18.  AdaBoost starts with a uniform distribution of “weights” over training examples.  Select the classifier with the lowest weighted error (i.e. a “weak” classifier)  Increase the weights on the training examples that were misclassified.  (Repeat)  At the end, carefully make a linear combination of the weak classifiers obtained at all iterations. AdaBoost Ilustration 1 1 1 strong 1 1 ( ) ( ) ( ) 2 0 otherwise n n nh h h x x x   Slide taken from a presentation by Qing Chen, Discover Lab, University of Ottawa Integral Image | AdaBoost | Cascade
  • 19. Classifier • By increasing the number of features per classifier, we: ◦ Increase detection accuracy. ◦ Decrease detection speed. • Experiments showed that a 200 feature classifier makes a good face detector: ◦ Takes 0.7 seconds to scan an 384 by 288 pixel image. • Problem: Not real time! (At most 0.067 seconds needed). Integral Image | AdaBoost | Cascade Cascade of Classifier…
  • 21. Cascade of Classifier • Classifier is structured as several layer/hierarchy • Each layer consist of 1 strong classifier (set of weak classifiers/features) • Evaluating all input window • Ignore non-face window • Continue for processing “suspected” face window Integral Image | AdaBoost | Cascade
  • 22. Cascade of Classifier • The number of feature/weak classifier in every layer is based on the value of false positive rate and detection rate determined by user • Previous layers have simpler classifier than next layer Integral Image | AdaBoost | Cascade Stage 1 Stage 2 Stage 3 … Further Processing Input Image Window Ignore/Reject Input Ignore/Reject Input Ignore/Reject Input Ignore/Reject Input Y N Y N Y N Y N
  • 23. Cascade of Classifier Integral Image | AdaBoost | Cascade Stage 1 (2 feature) N Y Stage 2 (2++ feature)
  • 24. Cascade of Classifier Pseudo Code Integral Image | AdaBoost | Cascade
  • 25. Experiment • Training set • Face: 4916 labeled frontal faces •Testing / Real-time test • Face: MIT + CMU frontal face test set • Contain: 130 images with 507 labeled frontal faces
  • 26. Result Cascade Classifier v.s Non Cascade Classifier Cascade classifier nearly 10x faster.
  • 27. Result They use dataset MIT+CMU with 5 images removed Voting (Using 3 Viola-Jones Classifier with different parameter) ++- : Face --+ : Non Face
  • 28. Failure Mode • Informal observation suggests that the face detector can detect faces that are tilted up to about ±15 degrees in plane and about ± 45 degrees out of plane • Harsh backlighting in which the faces are very dark while the background is relatively light sometimes causes failures • Proposed algorithm will also fail on significantly occluded faces