SlideShare a Scribd company logo
Recognition of Partially Occluded Face Using
Gradientface and Local Binary Patterns

George D. C. Cavalcanti
Tsang Ing Ren,
Josivan R. Reis

2012 IEEE International Conference on Systems, Man, and Cybernetics
October 14-17, 2012, COEX, Seoul, Korea
Outline
 Introduction
 Occlusion Detection
 Recognition
 Experiments and results
 Conclusion

2
INTRODUCTION

3
Introduction
‫ ﻪ‬Challenges of face recognition systems is
the problem of occlusion.
‫ ﻪ‬Uncontrolled environments such as drastic
change of lighting, change of expression,
beards and occlusions.

4
Proposed approach
‫ ﻪ‬Apply in the problem for face recognition
with sunglasses and scarf occlusion.
‫ ﻪ‬Consider illumination, rotation and
inclination problems.

5
Flowchart

Occlusion

Non-occlusion

6
OCCLUSION DETECTION

7
‫ ﻪ‬The image is divided into equal parts that
are classified into occluded and nonoccluded using MultiLayer Perceptron
(MLP)

8
‫ ﻪ‬Occlusion detection is a classification
problem

N: a set of training images
X: input layer
Y: output layer

Indicate :
1: non-occluded
-1: occlude

Partial Face Classifier Using LDA and MLP”. In Proceedings of the 2010. IEEE/ACIS 9th
International Conference on Computer and Information Science (ICIS '10)

9
RECOGNITION

10
‫ ﻪ‬For the recognition, Local binary Pattern(LBP)
feature is used on the non-occluded image
part.
‫ ﻪ‬LBP widely used in face recognition
‫ ﻩ‬Discriminative power
‫ ﻩ‬Computational simplicity
‫ ﻩ‬Robustness to changes in grayscale.
11
But:
LBP is not efficient for drastic lighting
variations.
Solve:↓
we use a Gradientface as a preprocessing
step before LBP.
12
GradientFace
‫ ﻪ‬It is insensitive to variations in illumination
and stands out in face recognition applications.
‫ ﻪ‬Gradientface Method:
1. Transforms to the gradient domain
2. Eliminate noise or shadow (Gaussian filter)

13
‫ ﻪ‬Smooth the image through a convolution with a
Gaussian function
∗ is the convolution operator
σ is the Gaussian function

‫ ﻪ‬Compute the image gradient I convolving in
directions x, y
‫ ﻪ‬Generate as result ,Gradientface

14
15
Local binary patterns

ln : Corresponds to the central pixel value
lc : The 8-neigbor pixels values

16
Recognition

17
‫[ ﻪ‬Gradientface + LBP ]
computational simplicity
robust to scales changes and illumination variations.
‫ ﻪ‬Define the similarity between the LBP histograms of
each image a similarity distance is used [7].
[E. P. Xing, A. Y. Ng, M. I. Jordan, and S. Russell, “Distance metric learning with application to clustering with side
information,” in Advances in Neural Information Processing Systems 15 , S. Becker, S.Thrun, and K. Obermayer, Eds.
Cambridge, MA: MIT Press, 2003, pp. 505–512 ]

18
EXPERIMENTS AND RESULTS

19
Database
‫ ﻪ‬AR Face
‫ ﻩ‬More than 4000 color images (70 men 56 women)

‫ ﻩ‬With different facial expressions, lighting conditions
and occlusions (sun glasses and scarf)

20
‫ ﻪ‬ORL
‫ 04 ﻩ‬subjects, 10 different images for each subject.
‫ ﻩ‬Facial expressions (open or closed eyes)
‫ ﻩ‬Facial details (glasses and without glasses)

21
Experiments1- MLPClassifier
‫ ﻪ‬Occlusion detection

22
Experiments2- Recognition
Database: AR Face

23
Experiments2- Recognition
Database: ORL Face

24
CONCLUSION

25
Conclusion
‫ ﻪ‬Address the problem of face recognition with
occlusion caused by sunglasses and scarf.
‫ ﻪ‬The Gradientface applied to image with
illumination problem and used to pre-processing
the image, improved the recognition.
‫ ﻪ‬Combination of pre-processing techniques and
classifies can still demonstrate improvements in
face recognition problems.
26
Q&A

27
END

Thanks

More Related Content

What's hot

APPLICATION OF CONVOLUTIONAL NEURAL NETWORK IN IMAGE CLASSIFICATION
APPLICATION OF CONVOLUTIONAL NEURAL NETWORK IN IMAGE CLASSIFICATIONAPPLICATION OF CONVOLUTIONAL NEURAL NETWORK IN IMAGE CLASSIFICATION
APPLICATION OF CONVOLUTIONAL NEURAL NETWORK IN IMAGE CLASSIFICATION
Writers Per Hour
 
Skin Cancer Detection Using Deep Learning Techniques
Skin Cancer Detection Using Deep Learning TechniquesSkin Cancer Detection Using Deep Learning Techniques
Skin Cancer Detection Using Deep Learning Techniques
IRJET Journal
 
Machine learning in image processing
Machine learning in image processingMachine learning in image processing
Machine learning in image processing
Data Science Thailand
 
Deep learning for image super resolution
Deep learning for image super resolutionDeep learning for image super resolution
Deep learning for image super resolution
Prudhvi Raj
 
Project Face Detection
Project Face Detection Project Face Detection
Project Face Detection Abu Saleh Musa
 
Local binary pattern
Local binary patternLocal binary pattern
Local binary pattern
International Islamic University
 
deep learning applications in medical image analysis brain tumor
deep learning applications in medical image analysis brain tumordeep learning applications in medical image analysis brain tumor
deep learning applications in medical image analysis brain tumor
Venkat Projects
 
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
Universitat Politècnica de Catalunya
 
Mixed reality(ft. microsoft hololens)
Mixed reality(ft. microsoft hololens)Mixed reality(ft. microsoft hololens)
Mixed reality(ft. microsoft hololens)
DipenVaja
 
Image segmentation using a genetic algorithm and hierarchical local search
Image segmentation using a genetic algorithm and hierarchical local searchImage segmentation using a genetic algorithm and hierarchical local search
Image segmentation using a genetic algorithm and hierarchical local search
Martin Pelikan
 
Image processing
Image processingImage processing
Image processing
Raga Deepthi
 
Deep learning for 3-D Scene Reconstruction and Modeling
Deep learning for 3-D Scene Reconstruction and Modeling Deep learning for 3-D Scene Reconstruction and Modeling
Deep learning for 3-D Scene Reconstruction and Modeling
Yu Huang
 
Detect COVID-19 with Deep Learning- A survey on Deep Learning for Pulmonary M...
Detect COVID-19 with Deep Learning- A survey on Deep Learning for Pulmonary M...Detect COVID-19 with Deep Learning- A survey on Deep Learning for Pulmonary M...
Detect COVID-19 with Deep Learning- A survey on Deep Learning for Pulmonary M...
JumanaNadir
 
Brain Tumor Segmentation in MRI Images
Brain Tumor Segmentation in MRI ImagesBrain Tumor Segmentation in MRI Images
Brain Tumor Segmentation in MRI Images
IJRAT
 
Marker Based Augmented Reality
Marker Based Augmented RealityMarker Based Augmented Reality
Marker Based Augmented Reality
Arshiya Sayyed
 
Neural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdfNeural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdf
NavneetPaul2
 
Computer vision
Computer vision Computer vision
Computer vision
Dmitry Ryabokon
 
“Processing Raw Images Efficiently on the MAX78000 Neural Network Accelerator...
“Processing Raw Images Efficiently on the MAX78000 Neural Network Accelerator...“Processing Raw Images Efficiently on the MAX78000 Neural Network Accelerator...
“Processing Raw Images Efficiently on the MAX78000 Neural Network Accelerator...
Edge AI and Vision Alliance
 
Android - Broadcast Receiver
Android - Broadcast ReceiverAndroid - Broadcast Receiver
Android - Broadcast Receiver
Yong Heui Cho
 

What's hot (20)

APPLICATION OF CONVOLUTIONAL NEURAL NETWORK IN IMAGE CLASSIFICATION
APPLICATION OF CONVOLUTIONAL NEURAL NETWORK IN IMAGE CLASSIFICATIONAPPLICATION OF CONVOLUTIONAL NEURAL NETWORK IN IMAGE CLASSIFICATION
APPLICATION OF CONVOLUTIONAL NEURAL NETWORK IN IMAGE CLASSIFICATION
 
Skin Cancer Detection Using Deep Learning Techniques
Skin Cancer Detection Using Deep Learning TechniquesSkin Cancer Detection Using Deep Learning Techniques
Skin Cancer Detection Using Deep Learning Techniques
 
Machine learning in image processing
Machine learning in image processingMachine learning in image processing
Machine learning in image processing
 
Deep learning for image super resolution
Deep learning for image super resolutionDeep learning for image super resolution
Deep learning for image super resolution
 
Project Face Detection
Project Face Detection Project Face Detection
Project Face Detection
 
Local binary pattern
Local binary patternLocal binary pattern
Local binary pattern
 
deep learning applications in medical image analysis brain tumor
deep learning applications in medical image analysis brain tumordeep learning applications in medical image analysis brain tumor
deep learning applications in medical image analysis brain tumor
 
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
 
Mixed reality(ft. microsoft hololens)
Mixed reality(ft. microsoft hololens)Mixed reality(ft. microsoft hololens)
Mixed reality(ft. microsoft hololens)
 
Image segmentation using a genetic algorithm and hierarchical local search
Image segmentation using a genetic algorithm and hierarchical local searchImage segmentation using a genetic algorithm and hierarchical local search
Image segmentation using a genetic algorithm and hierarchical local search
 
Image processing
Image processingImage processing
Image processing
 
Deep learning for 3-D Scene Reconstruction and Modeling
Deep learning for 3-D Scene Reconstruction and Modeling Deep learning for 3-D Scene Reconstruction and Modeling
Deep learning for 3-D Scene Reconstruction and Modeling
 
Detect COVID-19 with Deep Learning- A survey on Deep Learning for Pulmonary M...
Detect COVID-19 with Deep Learning- A survey on Deep Learning for Pulmonary M...Detect COVID-19 with Deep Learning- A survey on Deep Learning for Pulmonary M...
Detect COVID-19 with Deep Learning- A survey on Deep Learning for Pulmonary M...
 
Brain Tumor Segmentation in MRI Images
Brain Tumor Segmentation in MRI ImagesBrain Tumor Segmentation in MRI Images
Brain Tumor Segmentation in MRI Images
 
Marker Based Augmented Reality
Marker Based Augmented RealityMarker Based Augmented Reality
Marker Based Augmented Reality
 
Neural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdfNeural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdf
 
Computer vision
Computer vision Computer vision
Computer vision
 
“Processing Raw Images Efficiently on the MAX78000 Neural Network Accelerator...
“Processing Raw Images Efficiently on the MAX78000 Neural Network Accelerator...“Processing Raw Images Efficiently on the MAX78000 Neural Network Accelerator...
“Processing Raw Images Efficiently on the MAX78000 Neural Network Accelerator...
 
Implementation Model
Implementation ModelImplementation Model
Implementation Model
 
Android - Broadcast Receiver
Android - Broadcast ReceiverAndroid - Broadcast Receiver
Android - Broadcast Receiver
 

Viewers also liked

A completed modeling of local binary pattern operator
A completed modeling of local binary pattern operatorA completed modeling of local binary pattern operator
A completed modeling of local binary pattern operatorWin Yu
 
face recognition system using LBP
face recognition system using LBPface recognition system using LBP
face recognition system using LBP
Marwan H. Noman
 
Video Face Recognition , Pattern Recognition Final Report
Video Face Recognition , Pattern Recognition Final ReportVideo Face Recognition , Pattern Recognition Final Report
Video Face Recognition , Pattern Recognition Final Report
Win Yu
 
Bundling Features for Large Scale Partial-Duplicate Web Image Search
Bundling Features for Large Scale Partial-Duplicate Web Image SearchBundling Features for Large Scale Partial-Duplicate Web Image Search
Bundling Features for Large Scale Partial-Duplicate Web Image SearchWin Yu
 
Lbp based edge-texture features for object recoginition
Lbp based edge-texture features for object recoginitionLbp based edge-texture features for object recoginition
Lbp based edge-texture features for object recoginition
IGEEKS TECHNOLOGIES
 
2016 ModernWeb 分享 - 恰如其分 MySQL 程式設計 (修)
2016 ModernWeb 分享 - 恰如其分 MySQL 程式設計 (修)2016 ModernWeb 分享 - 恰如其分 MySQL 程式設計 (修)
2016 ModernWeb 分享 - 恰如其分 MySQL 程式設計 (修)
Win Yu
 
Facial Image Analysis for age and gender and
Facial Image Analysis for age and gender andFacial Image Analysis for age and gender and
Facial Image Analysis for age and gender andYuheng Wang
 
無瑕的程式碼 Clean Code 心得分享
無瑕的程式碼 Clean Code 心得分享無瑕的程式碼 Clean Code 心得分享
無瑕的程式碼 Clean Code 心得分享
Win Yu
 
Garment Texture Classification for Automated Product Suggestion
Garment Texture Classification for Automated Product SuggestionGarment Texture Classification for Automated Product Suggestion
Garment Texture Classification for Automated Product Suggestion
Md. Shafiuzzaman Hira
 
SegmentationAndClassificationOfMaritimeMan-MadeObjectsInTerraSAR-X-Images_Teu...
SegmentationAndClassificationOfMaritimeMan-MadeObjectsInTerraSAR-X-Images_Teu...SegmentationAndClassificationOfMaritimeMan-MadeObjectsInTerraSAR-X-Images_Teu...
SegmentationAndClassificationOfMaritimeMan-MadeObjectsInTerraSAR-X-Images_Teu...grssieee
 
Modified Census Transform
Modified Census TransformModified Census Transform
Modified Census Transform
Noah Kim
 
Automated Face Recognition System for Office Door Access Control Application
Automated Face Recognition System for Office Door Access Control Application Automated Face Recognition System for Office Door Access Control Application
Automated Face Recognition System for Office Door Access Control Application
Er. Ashish Pandey
 
Career Plan
Career PlanCareer Plan
Hybrid clustering based 3 d face modeling upon non-perfect orthogonality
Hybrid clustering based 3 d face modeling upon non-perfect orthogonalityHybrid clustering based 3 d face modeling upon non-perfect orthogonality
Hybrid clustering based 3 d face modeling upon non-perfect orthogonality
Win Yu
 
Year 12 Media Coursework Evaluation- Question 2
Year 12 Media Coursework Evaluation- Question 2Year 12 Media Coursework Evaluation- Question 2
Year 12 Media Coursework Evaluation- Question 2Mediamoogle
 
Age classifications
Age classificationsAge classifications
Age classifications
herrg003
 
Audience age classification
Audience age classificationAudience age classification
Audience age classificationZaraWolf
 
Audience and Age classification
Audience and Age classificationAudience and Age classification
Audience and Age classification
jackswingler
 
BBFC Age Classifications
BBFC Age ClassificationsBBFC Age Classifications
BBFC Age Classifications
Elisa Dubignon
 
Audience Classification
Audience ClassificationAudience Classification
Audience Classification
heatherlarkin1
 

Viewers also liked (20)

A completed modeling of local binary pattern operator
A completed modeling of local binary pattern operatorA completed modeling of local binary pattern operator
A completed modeling of local binary pattern operator
 
face recognition system using LBP
face recognition system using LBPface recognition system using LBP
face recognition system using LBP
 
Video Face Recognition , Pattern Recognition Final Report
Video Face Recognition , Pattern Recognition Final ReportVideo Face Recognition , Pattern Recognition Final Report
Video Face Recognition , Pattern Recognition Final Report
 
Bundling Features for Large Scale Partial-Duplicate Web Image Search
Bundling Features for Large Scale Partial-Duplicate Web Image SearchBundling Features for Large Scale Partial-Duplicate Web Image Search
Bundling Features for Large Scale Partial-Duplicate Web Image Search
 
Lbp based edge-texture features for object recoginition
Lbp based edge-texture features for object recoginitionLbp based edge-texture features for object recoginition
Lbp based edge-texture features for object recoginition
 
2016 ModernWeb 分享 - 恰如其分 MySQL 程式設計 (修)
2016 ModernWeb 分享 - 恰如其分 MySQL 程式設計 (修)2016 ModernWeb 分享 - 恰如其分 MySQL 程式設計 (修)
2016 ModernWeb 分享 - 恰如其分 MySQL 程式設計 (修)
 
Facial Image Analysis for age and gender and
Facial Image Analysis for age and gender andFacial Image Analysis for age and gender and
Facial Image Analysis for age and gender and
 
無瑕的程式碼 Clean Code 心得分享
無瑕的程式碼 Clean Code 心得分享無瑕的程式碼 Clean Code 心得分享
無瑕的程式碼 Clean Code 心得分享
 
Garment Texture Classification for Automated Product Suggestion
Garment Texture Classification for Automated Product SuggestionGarment Texture Classification for Automated Product Suggestion
Garment Texture Classification for Automated Product Suggestion
 
SegmentationAndClassificationOfMaritimeMan-MadeObjectsInTerraSAR-X-Images_Teu...
SegmentationAndClassificationOfMaritimeMan-MadeObjectsInTerraSAR-X-Images_Teu...SegmentationAndClassificationOfMaritimeMan-MadeObjectsInTerraSAR-X-Images_Teu...
SegmentationAndClassificationOfMaritimeMan-MadeObjectsInTerraSAR-X-Images_Teu...
 
Modified Census Transform
Modified Census TransformModified Census Transform
Modified Census Transform
 
Automated Face Recognition System for Office Door Access Control Application
Automated Face Recognition System for Office Door Access Control Application Automated Face Recognition System for Office Door Access Control Application
Automated Face Recognition System for Office Door Access Control Application
 
Career Plan
Career PlanCareer Plan
Career Plan
 
Hybrid clustering based 3 d face modeling upon non-perfect orthogonality
Hybrid clustering based 3 d face modeling upon non-perfect orthogonalityHybrid clustering based 3 d face modeling upon non-perfect orthogonality
Hybrid clustering based 3 d face modeling upon non-perfect orthogonality
 
Year 12 Media Coursework Evaluation- Question 2
Year 12 Media Coursework Evaluation- Question 2Year 12 Media Coursework Evaluation- Question 2
Year 12 Media Coursework Evaluation- Question 2
 
Age classifications
Age classificationsAge classifications
Age classifications
 
Audience age classification
Audience age classificationAudience age classification
Audience age classification
 
Audience and Age classification
Audience and Age classificationAudience and Age classification
Audience and Age classification
 
BBFC Age Classifications
BBFC Age ClassificationsBBFC Age Classifications
BBFC Age Classifications
 
Audience Classification
Audience ClassificationAudience Classification
Audience Classification
 

Similar to Recognition of Partially Occluded Face Using Gradientface and Local Binary Patterns

Selective local binary pattern with convolutional neural network for facial ...
Selective local binary pattern with convolutional neural  network for facial ...Selective local binary pattern with convolutional neural  network for facial ...
Selective local binary pattern with convolutional neural network for facial ...
IJECEIAES
 
N348295
N348295N348295
N348295
IJERA Editor
 
IRJET-Face Recognition using LDN Code
IRJET-Face Recognition using LDN CodeIRJET-Face Recognition using LDN Code
IRJET-Face Recognition using LDN Code
IRJET Journal
 
NEURAL NETWORK APPROACH FOR EYE DETECTION
NEURAL NETWORK APPROACH FOR EYE DETECTIONNEURAL NETWORK APPROACH FOR EYE DETECTION
NEURAL NETWORK APPROACH FOR EYE DETECTION
cscpconf
 
F044045052
F044045052F044045052
F044045052
inventy
 
A Review on Face Detection under Occlusion by Facial Accessories
A Review on Face Detection under Occlusion by Facial AccessoriesA Review on Face Detection under Occlusion by Facial Accessories
A Review on Face Detection under Occlusion by Facial Accessories
IRJET Journal
 
fuzzy LBP for face recognition ppt
fuzzy LBP for face recognition pptfuzzy LBP for face recognition ppt
fuzzy LBP for face recognition ppt
Abdullah Gubbi
 
HVDLP : HORIZONTAL VERTICAL DIAGONAL LOCAL PATTERN BASED FACE RECOGNITION
HVDLP : HORIZONTAL VERTICAL DIAGONAL LOCAL PATTERN BASED FACE RECOGNITION HVDLP : HORIZONTAL VERTICAL DIAGONAL LOCAL PATTERN BASED FACE RECOGNITION
HVDLP : HORIZONTAL VERTICAL DIAGONAL LOCAL PATTERN BASED FACE RECOGNITION
sipij
 
Optimized Biometric System Based on Combination of Face Images and Log Transf...
Optimized Biometric System Based on Combination of Face Images and Log Transf...Optimized Biometric System Based on Combination of Face Images and Log Transf...
Optimized Biometric System Based on Combination of Face Images and Log Transf...
sipij
 
Face recognition using laplacian faces
Face recognition using laplacian facesFace recognition using laplacian faces
Face recognition using laplacian facesPulkiŧ Sharma
 
Fourier mellin transform based face recognition
Fourier mellin transform based face recognitionFourier mellin transform based face recognition
Fourier mellin transform based face recognitioniaemedu
 
Fourier mellin transform based face recognition
Fourier mellin transform based face recognitionFourier mellin transform based face recognition
Fourier mellin transform based face recognitionIAEME Publication
 
Fourier mellin transform based face recognition
Fourier mellin transform based face recognitionFourier mellin transform based face recognition
Fourier mellin transform based face recognitioniaemedu
 
Fourier mellin transform based face recognition
Fourier mellin transform based face recognitionFourier mellin transform based face recognition
Fourier mellin transform based face recognitionIAEME Publication
 
Hybrid Domain based Face Recognition using DWT, FFT and Compressed CLBP
Hybrid Domain based Face Recognition using DWT, FFT and Compressed CLBPHybrid Domain based Face Recognition using DWT, FFT and Compressed CLBP
Hybrid Domain based Face Recognition using DWT, FFT and Compressed CLBP
CSCJournals
 
TOP 5 Most View Article From Academia in 2019
TOP 5 Most View Article From Academia in 2019TOP 5 Most View Article From Academia in 2019
TOP 5 Most View Article From Academia in 2019
sipij
 
Face recognition
Face recognitionFace recognition
Face recognition
Satyendra Rajput
 
COMPRESSION BASED FACE RECOGNITION USING DWT AND SVM
COMPRESSION BASED FACE RECOGNITION USING DWT AND SVMCOMPRESSION BASED FACE RECOGNITION USING DWT AND SVM
COMPRESSION BASED FACE RECOGNITION USING DWT AND SVM
sipij
 
Face detection using the 3 x3 block rank patterns of gradient magnitude images
Face detection using the 3 x3 block rank patterns of gradient magnitude imagesFace detection using the 3 x3 block rank patterns of gradient magnitude images
Face detection using the 3 x3 block rank patterns of gradient magnitude images
sipij
 
LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...
LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...
LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...
csijjournal
 

Similar to Recognition of Partially Occluded Face Using Gradientface and Local Binary Patterns (20)

Selective local binary pattern with convolutional neural network for facial ...
Selective local binary pattern with convolutional neural  network for facial ...Selective local binary pattern with convolutional neural  network for facial ...
Selective local binary pattern with convolutional neural network for facial ...
 
N348295
N348295N348295
N348295
 
IRJET-Face Recognition using LDN Code
IRJET-Face Recognition using LDN CodeIRJET-Face Recognition using LDN Code
IRJET-Face Recognition using LDN Code
 
NEURAL NETWORK APPROACH FOR EYE DETECTION
NEURAL NETWORK APPROACH FOR EYE DETECTIONNEURAL NETWORK APPROACH FOR EYE DETECTION
NEURAL NETWORK APPROACH FOR EYE DETECTION
 
F044045052
F044045052F044045052
F044045052
 
A Review on Face Detection under Occlusion by Facial Accessories
A Review on Face Detection under Occlusion by Facial AccessoriesA Review on Face Detection under Occlusion by Facial Accessories
A Review on Face Detection under Occlusion by Facial Accessories
 
fuzzy LBP for face recognition ppt
fuzzy LBP for face recognition pptfuzzy LBP for face recognition ppt
fuzzy LBP for face recognition ppt
 
HVDLP : HORIZONTAL VERTICAL DIAGONAL LOCAL PATTERN BASED FACE RECOGNITION
HVDLP : HORIZONTAL VERTICAL DIAGONAL LOCAL PATTERN BASED FACE RECOGNITION HVDLP : HORIZONTAL VERTICAL DIAGONAL LOCAL PATTERN BASED FACE RECOGNITION
HVDLP : HORIZONTAL VERTICAL DIAGONAL LOCAL PATTERN BASED FACE RECOGNITION
 
Optimized Biometric System Based on Combination of Face Images and Log Transf...
Optimized Biometric System Based on Combination of Face Images and Log Transf...Optimized Biometric System Based on Combination of Face Images and Log Transf...
Optimized Biometric System Based on Combination of Face Images and Log Transf...
 
Face recognition using laplacian faces
Face recognition using laplacian facesFace recognition using laplacian faces
Face recognition using laplacian faces
 
Fourier mellin transform based face recognition
Fourier mellin transform based face recognitionFourier mellin transform based face recognition
Fourier mellin transform based face recognition
 
Fourier mellin transform based face recognition
Fourier mellin transform based face recognitionFourier mellin transform based face recognition
Fourier mellin transform based face recognition
 
Fourier mellin transform based face recognition
Fourier mellin transform based face recognitionFourier mellin transform based face recognition
Fourier mellin transform based face recognition
 
Fourier mellin transform based face recognition
Fourier mellin transform based face recognitionFourier mellin transform based face recognition
Fourier mellin transform based face recognition
 
Hybrid Domain based Face Recognition using DWT, FFT and Compressed CLBP
Hybrid Domain based Face Recognition using DWT, FFT and Compressed CLBPHybrid Domain based Face Recognition using DWT, FFT and Compressed CLBP
Hybrid Domain based Face Recognition using DWT, FFT and Compressed CLBP
 
TOP 5 Most View Article From Academia in 2019
TOP 5 Most View Article From Academia in 2019TOP 5 Most View Article From Academia in 2019
TOP 5 Most View Article From Academia in 2019
 
Face recognition
Face recognitionFace recognition
Face recognition
 
COMPRESSION BASED FACE RECOGNITION USING DWT AND SVM
COMPRESSION BASED FACE RECOGNITION USING DWT AND SVMCOMPRESSION BASED FACE RECOGNITION USING DWT AND SVM
COMPRESSION BASED FACE RECOGNITION USING DWT AND SVM
 
Face detection using the 3 x3 block rank patterns of gradient magnitude images
Face detection using the 3 x3 block rank patterns of gradient magnitude imagesFace detection using the 3 x3 block rank patterns of gradient magnitude images
Face detection using the 3 x3 block rank patterns of gradient magnitude images
 
LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...
LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...
LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...
 

More from Win Yu

運用 Cloud Pub/Sub 實作 PIXNET 跨產品動態整合 #modernWeb2018
運用 Cloud Pub/Sub 實作 PIXNET 跨產品動態整合 #modernWeb2018運用 Cloud Pub/Sub 實作 PIXNET 跨產品動態整合 #modernWeb2018
運用 Cloud Pub/Sub 實作 PIXNET 跨產品動態整合 #modernWeb2018
Win Yu
 
AMP Roadshow Taipei
AMP Roadshow TaipeiAMP Roadshow Taipei
AMP Roadshow Taipei
Win Yu
 
Easy to recap AWS reinvent 2017
Easy to recap AWS reinvent 2017Easy to recap AWS reinvent 2017
Easy to recap AWS reinvent 2017
Win Yu
 
PHP 良好實踐 (Best Practice)
PHP 良好實踐 (Best Practice)PHP 良好實踐 (Best Practice)
PHP 良好實踐 (Best Practice)
Win Yu
 
與設計架構當朋友
與設計架構當朋友 與設計架構當朋友
與設計架構當朋友
Win Yu
 
用 Bitbar Tool 寫 Script 自動擷取外幣
用 Bitbar Tool 寫 Script 自動擷取外幣用 Bitbar Tool 寫 Script 自動擷取外幣
用 Bitbar Tool 寫 Script 自動擷取外幣
Win Yu
 
Pattern Recognition midterm Proposal
Pattern Recognition midterm ProposalPattern Recognition midterm Proposal
Pattern Recognition midterm Proposal
Win Yu
 
A rank based ensemble classifier for image classification
A rank based ensemble classifier for image classificationA rank based ensemble classifier for image classification
A rank based ensemble classifier for image classification
Win Yu
 
MSR-Bing Image Retrieval Challenge ,written by Win
MSR-Bing Image Retrieval Challenge ,written by WinMSR-Bing Image Retrieval Challenge ,written by Win
MSR-Bing Image Retrieval Challenge ,written by Win
Win Yu
 
Tpr star tree
Tpr star treeTpr star tree
Tpr star treeWin Yu
 

More from Win Yu (10)

運用 Cloud Pub/Sub 實作 PIXNET 跨產品動態整合 #modernWeb2018
運用 Cloud Pub/Sub 實作 PIXNET 跨產品動態整合 #modernWeb2018運用 Cloud Pub/Sub 實作 PIXNET 跨產品動態整合 #modernWeb2018
運用 Cloud Pub/Sub 實作 PIXNET 跨產品動態整合 #modernWeb2018
 
AMP Roadshow Taipei
AMP Roadshow TaipeiAMP Roadshow Taipei
AMP Roadshow Taipei
 
Easy to recap AWS reinvent 2017
Easy to recap AWS reinvent 2017Easy to recap AWS reinvent 2017
Easy to recap AWS reinvent 2017
 
PHP 良好實踐 (Best Practice)
PHP 良好實踐 (Best Practice)PHP 良好實踐 (Best Practice)
PHP 良好實踐 (Best Practice)
 
與設計架構當朋友
與設計架構當朋友 與設計架構當朋友
與設計架構當朋友
 
用 Bitbar Tool 寫 Script 自動擷取外幣
用 Bitbar Tool 寫 Script 自動擷取外幣用 Bitbar Tool 寫 Script 自動擷取外幣
用 Bitbar Tool 寫 Script 自動擷取外幣
 
Pattern Recognition midterm Proposal
Pattern Recognition midterm ProposalPattern Recognition midterm Proposal
Pattern Recognition midterm Proposal
 
A rank based ensemble classifier for image classification
A rank based ensemble classifier for image classificationA rank based ensemble classifier for image classification
A rank based ensemble classifier for image classification
 
MSR-Bing Image Retrieval Challenge ,written by Win
MSR-Bing Image Retrieval Challenge ,written by WinMSR-Bing Image Retrieval Challenge ,written by Win
MSR-Bing Image Retrieval Challenge ,written by Win
 
Tpr star tree
Tpr star treeTpr star tree
Tpr star tree
 

Recently uploaded

Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
OnBoard
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
UiPathCommunity
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
DanBrown980551
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
Product School
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
Cheryl Hung
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
Paul Groth
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
Product School
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Ramesh Iyer
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Jeffrey Haguewood
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
Elena Simperl
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
g2nightmarescribd
 

Recently uploaded (20)

Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
 

Recognition of Partially Occluded Face Using Gradientface and Local Binary Patterns

  • 1. Recognition of Partially Occluded Face Using Gradientface and Local Binary Patterns George D. C. Cavalcanti Tsang Ing Ren, Josivan R. Reis 2012 IEEE International Conference on Systems, Man, and Cybernetics October 14-17, 2012, COEX, Seoul, Korea
  • 2. Outline  Introduction  Occlusion Detection  Recognition  Experiments and results  Conclusion 2
  • 4. Introduction ‫ ﻪ‬Challenges of face recognition systems is the problem of occlusion. ‫ ﻪ‬Uncontrolled environments such as drastic change of lighting, change of expression, beards and occlusions. 4
  • 5. Proposed approach ‫ ﻪ‬Apply in the problem for face recognition with sunglasses and scarf occlusion. ‫ ﻪ‬Consider illumination, rotation and inclination problems. 5
  • 8. ‫ ﻪ‬The image is divided into equal parts that are classified into occluded and nonoccluded using MultiLayer Perceptron (MLP) 8
  • 9. ‫ ﻪ‬Occlusion detection is a classification problem N: a set of training images X: input layer Y: output layer Indicate : 1: non-occluded -1: occlude Partial Face Classifier Using LDA and MLP”. In Proceedings of the 2010. IEEE/ACIS 9th International Conference on Computer and Information Science (ICIS '10) 9
  • 11. ‫ ﻪ‬For the recognition, Local binary Pattern(LBP) feature is used on the non-occluded image part. ‫ ﻪ‬LBP widely used in face recognition ‫ ﻩ‬Discriminative power ‫ ﻩ‬Computational simplicity ‫ ﻩ‬Robustness to changes in grayscale. 11
  • 12. But: LBP is not efficient for drastic lighting variations. Solve:↓ we use a Gradientface as a preprocessing step before LBP. 12
  • 13. GradientFace ‫ ﻪ‬It is insensitive to variations in illumination and stands out in face recognition applications. ‫ ﻪ‬Gradientface Method: 1. Transforms to the gradient domain 2. Eliminate noise or shadow (Gaussian filter) 13
  • 14. ‫ ﻪ‬Smooth the image through a convolution with a Gaussian function ∗ is the convolution operator σ is the Gaussian function ‫ ﻪ‬Compute the image gradient I convolving in directions x, y ‫ ﻪ‬Generate as result ,Gradientface 14
  • 15. 15
  • 16. Local binary patterns ln : Corresponds to the central pixel value lc : The 8-neigbor pixels values 16
  • 18. ‫[ ﻪ‬Gradientface + LBP ] computational simplicity robust to scales changes and illumination variations. ‫ ﻪ‬Define the similarity between the LBP histograms of each image a similarity distance is used [7]. [E. P. Xing, A. Y. Ng, M. I. Jordan, and S. Russell, “Distance metric learning with application to clustering with side information,” in Advances in Neural Information Processing Systems 15 , S. Becker, S.Thrun, and K. Obermayer, Eds. Cambridge, MA: MIT Press, 2003, pp. 505–512 ] 18
  • 20. Database ‫ ﻪ‬AR Face ‫ ﻩ‬More than 4000 color images (70 men 56 women) ‫ ﻩ‬With different facial expressions, lighting conditions and occlusions (sun glasses and scarf) 20
  • 21. ‫ ﻪ‬ORL ‫ 04 ﻩ‬subjects, 10 different images for each subject. ‫ ﻩ‬Facial expressions (open or closed eyes) ‫ ﻩ‬Facial details (glasses and without glasses) 21
  • 26. Conclusion ‫ ﻪ‬Address the problem of face recognition with occlusion caused by sunglasses and scarf. ‫ ﻪ‬The Gradientface applied to image with illumination problem and used to pre-processing the image, improved the recognition. ‫ ﻪ‬Combination of pre-processing techniques and classifies can still demonstrate improvements in face recognition problems. 26