SlideShare una empresa de Scribd logo
1 de 21
Region-based Skin Color Detection
Rudra P K Poudel (Presenter), Hammadi Nait-Charif, Jian Jun Zhang
Media School, Bournemouth University, UK
David Liu
Siemens Corporate Research, USA
Outline of the talk
1. Introduction- skin color detection
2. Literature Review
3. Current Problems
4. Region-Based Technique
5. Proposed Region-Based Technique
6. Experimental Results
7. Conclusions
1. Introduction
• Task: separate skin and non-skin
regions (not pixels)
• Motivation: invariant of rotation,
scaling and occlusion
• Problems: illumination, ethnicity
background, make-up, hairstyle,
eyeglasses, background color,
shadows, motion illumination, skin
look like colors, etc.
Source: Harry Potter movie
1.1 Applications
• Hand tracking, face detection, pornography detection, person
tracking
• Skin color detection module equally applicable for other color
editing, detection etc applications
• Color is used as primary clue in many image processing and
computer vision applications
2. Literature Review
2.1 Color space
• RGB
• HSV
• YCbCr
• Perceptually uniform color systems (CILLAB, CIELUV,
LAB)
• Normalized RGB
2.2 Skin color classifier
• Nonparametric methods: histogram, Bayes classifier,
self-organizing map
• Parametric methods: single Gaussian, mixture of
Gaussian
• Others: neural network
2. Literature Review
Summary:
• Color space: RGB and HSV are two widely used techniques
• Classification method: Naïve Bayes classifier and mixture of
Gaussian are widely used techniques
• Gaussian model: need few training data, difficulties on parameter
tuning, need less memory space, processing/detection slow
• Bayes theorem: need for larger training data, easy for learning,
need more memory space, processing/detection fast
State-of-the-art method:
• Jones, M. J. and Rehg, J. M. (2002). Statistical color models with
application to skin detection. International Journal of Computer Vision,
46(1):81–96.
3. Current Problem
• Probability accumulation for higher level vision task- as
probability for skin/non-skin vary highly even for adjacent
pixels
Naturally skin is
continuous region
4 Region Based Approach
• Yang and Ahuja (1998) and Kruppa et al. (2002)- search
elliptical regions for face detection
• Sebe Sebe et al.(2004)- 3x3 fixed size patches to train
Bayesian network
• Our approach treat skin as region with varying sizes, which is
purely based on image evidence
Proposed Technique/Framework
1. Region extraction- quick shift image
segmentation, also know as “superpixels”
2. Region classification- pixel/region based
3. Smoothing- Conditional Random Field (CRF)
5. Proposed Region-Based technique
5.1 Region Extraction
Region/Superpixel
extraction – quick shift
image segmentation using
RGB color and positional
(XY) coordinate
5.1 Region Extraction
- Region extraction is purely evidence based i.e. based on RGB
color and spatial location (xy-coordinate) of the image
- Regions have different size and shape, which is depend upon
complexity of the image
- No explicit concept of boundary
- Quick shift preserve the boundary of the objects, hence we
could get very accurate object segmentation
- We could set importance on color difference vs spatial distance
5.2 Region Classification
5.2.1 Basic Skin Color Classifer
Naïve Bayes: posterior likelihood * prior∝
However, we could use any suitable/best method for skin classification
)(
)()/(
)/(
cp
spscp
csp =
)(
)()/(
)/(
cp
nspnscp
cnsp =
Θ>
)/(
)/(
cnsp
csp
Θ>
)()/(
)()/(
nspnscp
spscp
1
)/(
)/(
>
nscp
scp Where, c = color, s = skin and ns = non-skin
5.2 Region Classification
• Average the skin probability (s) of all color pixels (c)
belongs to the given superpixel (sp)
• Average the non-skin probability (ns) of all color pixels
(c) belongs to the given superpixel (sp)
∑=
N
i
icsP
N
spsP )|(
1
)|(
∑=
N
i
icnsP
N
spnsP )|(
1
)|(
5.3 Smoothing with CRF
• Conditional Random Field (CRF) optimization
equation
• Color potential
• Edge and boundary potential
∑∑ ∈∈
Φ+Ψ−=−
Ess
jiji
Ss
ii
jii
ssccslSLP
),(
),|,()|());|(log( ωω
))|(log()|( iiii slPsl =ψ
[ ]ji
ji
ji
jiji cc
ss
ssL
sscc ≠








−+
=Φ ,
||||1
),(
),|,(
5.4 Training
First Phase (training histogram):
• Train 2 histograms for skin and non-skin separately
Second phase (training CRF): learning :
si sj
…
px1(s|c)
px1(ns|c)
px1(s|c)
px1(ns|c)
color difference
+
boundary length
∑∑ ∈∈
Φ+Ψ−=−
Ess
jiji
Ss
ii
jii
ssccslSLP
),(
),|,()|());|(log( ωω
ω
6 Experimental Results
• Dataset content 14 thousands images collected freely from
the web (Compaq dataset)
• 4,700 are skin and 9,000 non-skin images
• Approximately 1 billion pixels are manually labeled
• 50% is use for training and 50% for testing
Method True
Positive
False Positive
Jones and Rehg (2002) 90% 14.2%
Our (Superpixel only) 91.44% 13.73%
Our (Superpixel and CRF) 91.17% 13.12%
6 Experimental Results
Our proposed new region-
based technique outperform
current state-of-the–art
technique
6 Experimental Results
Applying CRF is always not good !
6 Experimental Results
However, in aggregate CRF performs better!
7. Conclusions
• Region-based technique performs better than pixel-based
• Region-based technique could easily incorporate texture info
and other type of features to improve the result
• Aggregation of pixels into region help to reduce local
redundancy.
• Region-based technique extracts larger smooth regions,
which is very helpful for higher-level vision task
The message to take home:
It is better/natural to treat skin as regions instead of
individual pixels!
Thank you !
Questions ???

Más contenido relacionado

La actualidad más candente

An Automatic Method for Red-eye Detection and Correction in Digital Images
An Automatic Method for Red-eye Detection and Correction in Digital ImagesAn Automatic Method for Red-eye Detection and Correction in Digital Images
An Automatic Method for Red-eye Detection and Correction in Digital ImagesMushfekur Rahman
 
Miniproject final group 14
Miniproject final group 14Miniproject final group 14
Miniproject final group 14Ashish Mundhra
 
Contour Line Tracing Algorithm for Digital Topographic Maps
Contour Line Tracing Algorithm for Digital Topographic MapsContour Line Tracing Algorithm for Digital Topographic Maps
Contour Line Tracing Algorithm for Digital Topographic MapsCSCJournals
 
COMPARATIVE ANALYSIS OF SKIN COLOR BASED MODELS FOR FACE DETECTION
COMPARATIVE ANALYSIS OF SKIN COLOR  BASED MODELS FOR FACE DETECTIONCOMPARATIVE ANALYSIS OF SKIN COLOR  BASED MODELS FOR FACE DETECTION
COMPARATIVE ANALYSIS OF SKIN COLOR BASED MODELS FOR FACE DETECTIONsipij
 
CV_Chap 6 Motion Representation
CV_Chap 6 Motion RepresentationCV_Chap 6 Motion Representation
CV_Chap 6 Motion RepresentationKhushali Kathiriya
 
Color Guided Thermal image Super Resolution
Color Guided Thermal image Super ResolutionColor Guided Thermal image Super Resolution
Color Guided Thermal image Super ResolutionSafayet Hossain
 
Orientation Effectiveness in the Objects Detected Areas Using Different Types...
Orientation Effectiveness in the Objects Detected Areas Using Different Types...Orientation Effectiveness in the Objects Detected Areas Using Different Types...
Orientation Effectiveness in the Objects Detected Areas Using Different Types...IJCSES Journal
 
ENHANCED SKIN COLOUR CLASSIFIER USING RGB RATIO MODEL
ENHANCED SKIN COLOUR CLASSIFIER USING RGB RATIO MODELENHANCED SKIN COLOUR CLASSIFIER USING RGB RATIO MODEL
ENHANCED SKIN COLOUR CLASSIFIER USING RGB RATIO MODELijsc
 
Wolfgang | Bikeability Workshop December 2010
Wolfgang | Bikeability Workshop December 2010Wolfgang | Bikeability Workshop December 2010
Wolfgang | Bikeability Workshop December 2010Morten Meyer
 
An Edge Detection Method for Hexagonal Images
An Edge Detection Method for Hexagonal ImagesAn Edge Detection Method for Hexagonal Images
An Edge Detection Method for Hexagonal ImagesCSCJournals
 
SIFT Based Feature Extraction and Matching for Archaeological Artifacts
SIFT Based Feature Extraction and Matching for Archaeological ArtifactsSIFT Based Feature Extraction and Matching for Archaeological Artifacts
SIFT Based Feature Extraction and Matching for Archaeological ArtifactsBIPUL MOHANTO [LION]
 

La actualidad más candente (14)

An Automatic Method for Red-eye Detection and Correction in Digital Images
An Automatic Method for Red-eye Detection and Correction in Digital ImagesAn Automatic Method for Red-eye Detection and Correction in Digital Images
An Automatic Method for Red-eye Detection and Correction in Digital Images
 
Miniproject final group 14
Miniproject final group 14Miniproject final group 14
Miniproject final group 14
 
Overview of ImageCLEF 2014
Overview of ImageCLEF 2014Overview of ImageCLEF 2014
Overview of ImageCLEF 2014
 
Contour Line Tracing Algorithm for Digital Topographic Maps
Contour Line Tracing Algorithm for Digital Topographic MapsContour Line Tracing Algorithm for Digital Topographic Maps
Contour Line Tracing Algorithm for Digital Topographic Maps
 
Cv_Chap 4 Segmentation
Cv_Chap 4 SegmentationCv_Chap 4 Segmentation
Cv_Chap 4 Segmentation
 
COMPARATIVE ANALYSIS OF SKIN COLOR BASED MODELS FOR FACE DETECTION
COMPARATIVE ANALYSIS OF SKIN COLOR  BASED MODELS FOR FACE DETECTIONCOMPARATIVE ANALYSIS OF SKIN COLOR  BASED MODELS FOR FACE DETECTION
COMPARATIVE ANALYSIS OF SKIN COLOR BASED MODELS FOR FACE DETECTION
 
CV_Chap 6 Motion Representation
CV_Chap 6 Motion RepresentationCV_Chap 6 Motion Representation
CV_Chap 6 Motion Representation
 
Color Guided Thermal image Super Resolution
Color Guided Thermal image Super ResolutionColor Guided Thermal image Super Resolution
Color Guided Thermal image Super Resolution
 
Orientation Effectiveness in the Objects Detected Areas Using Different Types...
Orientation Effectiveness in the Objects Detected Areas Using Different Types...Orientation Effectiveness in the Objects Detected Areas Using Different Types...
Orientation Effectiveness in the Objects Detected Areas Using Different Types...
 
ENHANCED SKIN COLOUR CLASSIFIER USING RGB RATIO MODEL
ENHANCED SKIN COLOUR CLASSIFIER USING RGB RATIO MODELENHANCED SKIN COLOUR CLASSIFIER USING RGB RATIO MODEL
ENHANCED SKIN COLOUR CLASSIFIER USING RGB RATIO MODEL
 
Wolfgang | Bikeability Workshop December 2010
Wolfgang | Bikeability Workshop December 2010Wolfgang | Bikeability Workshop December 2010
Wolfgang | Bikeability Workshop December 2010
 
An Edge Detection Method for Hexagonal Images
An Edge Detection Method for Hexagonal ImagesAn Edge Detection Method for Hexagonal Images
An Edge Detection Method for Hexagonal Images
 
S0450598102
S0450598102S0450598102
S0450598102
 
SIFT Based Feature Extraction and Matching for Archaeological Artifacts
SIFT Based Feature Extraction and Matching for Archaeological ArtifactsSIFT Based Feature Extraction and Matching for Archaeological Artifacts
SIFT Based Feature Extraction and Matching for Archaeological Artifacts
 

Destacado (6)

HSV color model
HSV color modelHSV color model
HSV color model
 
HSL & HSV colour models
HSL & HSV colour modelsHSL & HSV colour models
HSL & HSV colour models
 
Skin tone based steganography
Skin tone based steganographySkin tone based steganography
Skin tone based steganography
 
YUV, Y CB CR and Subsampling
YUV, Y CB CR and SubsamplingYUV, Y CB CR and Subsampling
YUV, Y CB CR and Subsampling
 
Color models
Color modelsColor models
Color models
 
Color Models
Color ModelsColor Models
Color Models
 

Similar a Region Based Skin Color Detection

Skin Color Detection Using Region-Based Approach
Skin Color Detection Using Region-Based ApproachSkin Color Detection Using Region-Based Approach
Skin Color Detection Using Region-Based ApproachCSCJournals
 
Skin Detection Based on Color Model and Low Level Features Combined with Expl...
Skin Detection Based on Color Model and Low Level Features Combined with Expl...Skin Detection Based on Color Model and Low Level Features Combined with Expl...
Skin Detection Based on Color Model and Low Level Features Combined with Expl...IJERA Editor
 
Intro+Imaging.ppt
Intro+Imaging.pptIntro+Imaging.ppt
Intro+Imaging.pptshohel rana
 
Cbir final ppt
Cbir final pptCbir final ppt
Cbir final pptrinki nag
 
Cbir final ppt
Cbir final pptCbir final ppt
Cbir final pptrinki nag
 
50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...
50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...
50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...idescitation
 
BayesianDecisionTheoryCaseStudiesf .pptx
BayesianDecisionTheoryCaseStudiesf .pptxBayesianDecisionTheoryCaseStudiesf .pptx
BayesianDecisionTheoryCaseStudiesf .pptxJulius346776
 
Face spoofing detection using texture analysis
Face spoofing detection  using texture analysisFace spoofing detection  using texture analysis
Face spoofing detection using texture analysisSREEKUTTY SREEKUMAR
 
A New Algorithm for Human Face Detection Using Skin Color Tone
A New Algorithm for Human Face Detection Using Skin Color ToneA New Algorithm for Human Face Detection Using Skin Color Tone
A New Algorithm for Human Face Detection Using Skin Color ToneIOSR Journals
 
Module 1
Module 1Module 1
Module 1ushaBS2
 
Data Mining Based Skin Pixel Detection Applied On Human Images: A Study Paper
Data Mining Based Skin Pixel Detection Applied On Human Images: A Study PaperData Mining Based Skin Pixel Detection Applied On Human Images: A Study Paper
Data Mining Based Skin Pixel Detection Applied On Human Images: A Study PaperIJERA Editor
 
Non-Local Means and its Applications
Non-Local Means and its ApplicationsNon-Local Means and its Applications
Non-Local Means and its ApplicationsManchor Ko
 
Computer Graphics: Visible surface detection methods
Computer Graphics: Visible surface detection methodsComputer Graphics: Visible surface detection methods
Computer Graphics: Visible surface detection methodsJoseph Charles
 
ICCASP Human Skin Detection using RGB, HSV and YCbCr Color Models
ICCASP Human Skin Detection using RGB, HSV and YCbCr Color ModelsICCASP Human Skin Detection using RGB, HSV and YCbCr Color Models
ICCASP Human Skin Detection using RGB, HSV and YCbCr Color ModelsChaitanya Bapat
 
Skin segmentation using different integrated color model approaches for face ...
Skin segmentation using different integrated color model approaches for face ...Skin segmentation using different integrated color model approaches for face ...
Skin segmentation using different integrated color model approaches for face ...eSAT Publishing House
 
Real-time Face Detection and Recognition
Real-time Face Detection and RecognitionReal-time Face Detection and Recognition
Real-time Face Detection and RecognitionJia-Bin Huang
 

Similar a Region Based Skin Color Detection (20)

Skin Color Detection Using Region-Based Approach
Skin Color Detection Using Region-Based ApproachSkin Color Detection Using Region-Based Approach
Skin Color Detection Using Region-Based Approach
 
FaceRecognition.ppt
FaceRecognition.pptFaceRecognition.ppt
FaceRecognition.ppt
 
FaceRecognition.ppt
FaceRecognition.pptFaceRecognition.ppt
FaceRecognition.ppt
 
FaceRecognition.ppt
FaceRecognition.pptFaceRecognition.ppt
FaceRecognition.ppt
 
Skin Detection Based on Color Model and Low Level Features Combined with Expl...
Skin Detection Based on Color Model and Low Level Features Combined with Expl...Skin Detection Based on Color Model and Low Level Features Combined with Expl...
Skin Detection Based on Color Model and Low Level Features Combined with Expl...
 
PPT s12-machine vision-s2
PPT s12-machine vision-s2PPT s12-machine vision-s2
PPT s12-machine vision-s2
 
Intro+Imaging.ppt
Intro+Imaging.pptIntro+Imaging.ppt
Intro+Imaging.ppt
 
Cbir final ppt
Cbir final pptCbir final ppt
Cbir final ppt
 
Cbir final ppt
Cbir final pptCbir final ppt
Cbir final ppt
 
50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...
50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...
50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...
 
BayesianDecisionTheoryCaseStudiesf .pptx
BayesianDecisionTheoryCaseStudiesf .pptxBayesianDecisionTheoryCaseStudiesf .pptx
BayesianDecisionTheoryCaseStudiesf .pptx
 
Face spoofing detection using texture analysis
Face spoofing detection  using texture analysisFace spoofing detection  using texture analysis
Face spoofing detection using texture analysis
 
A New Algorithm for Human Face Detection Using Skin Color Tone
A New Algorithm for Human Face Detection Using Skin Color ToneA New Algorithm for Human Face Detection Using Skin Color Tone
A New Algorithm for Human Face Detection Using Skin Color Tone
 
Module 1
Module 1Module 1
Module 1
 
Data Mining Based Skin Pixel Detection Applied On Human Images: A Study Paper
Data Mining Based Skin Pixel Detection Applied On Human Images: A Study PaperData Mining Based Skin Pixel Detection Applied On Human Images: A Study Paper
Data Mining Based Skin Pixel Detection Applied On Human Images: A Study Paper
 
Non-Local Means and its Applications
Non-Local Means and its ApplicationsNon-Local Means and its Applications
Non-Local Means and its Applications
 
Computer Graphics: Visible surface detection methods
Computer Graphics: Visible surface detection methodsComputer Graphics: Visible surface detection methods
Computer Graphics: Visible surface detection methods
 
ICCASP Human Skin Detection using RGB, HSV and YCbCr Color Models
ICCASP Human Skin Detection using RGB, HSV and YCbCr Color ModelsICCASP Human Skin Detection using RGB, HSV and YCbCr Color Models
ICCASP Human Skin Detection using RGB, HSV and YCbCr Color Models
 
Skin segmentation using different integrated color model approaches for face ...
Skin segmentation using different integrated color model approaches for face ...Skin segmentation using different integrated color model approaches for face ...
Skin segmentation using different integrated color model approaches for face ...
 
Real-time Face Detection and Recognition
Real-time Face Detection and RecognitionReal-time Face Detection and Recognition
Real-time Face Detection and Recognition
 

Último

08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024Results
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 

Último (20)

08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 

Region Based Skin Color Detection

  • 1. Region-based Skin Color Detection Rudra P K Poudel (Presenter), Hammadi Nait-Charif, Jian Jun Zhang Media School, Bournemouth University, UK David Liu Siemens Corporate Research, USA
  • 2. Outline of the talk 1. Introduction- skin color detection 2. Literature Review 3. Current Problems 4. Region-Based Technique 5. Proposed Region-Based Technique 6. Experimental Results 7. Conclusions
  • 3. 1. Introduction • Task: separate skin and non-skin regions (not pixels) • Motivation: invariant of rotation, scaling and occlusion • Problems: illumination, ethnicity background, make-up, hairstyle, eyeglasses, background color, shadows, motion illumination, skin look like colors, etc. Source: Harry Potter movie
  • 4. 1.1 Applications • Hand tracking, face detection, pornography detection, person tracking • Skin color detection module equally applicable for other color editing, detection etc applications • Color is used as primary clue in many image processing and computer vision applications
  • 5. 2. Literature Review 2.1 Color space • RGB • HSV • YCbCr • Perceptually uniform color systems (CILLAB, CIELUV, LAB) • Normalized RGB 2.2 Skin color classifier • Nonparametric methods: histogram, Bayes classifier, self-organizing map • Parametric methods: single Gaussian, mixture of Gaussian • Others: neural network
  • 6. 2. Literature Review Summary: • Color space: RGB and HSV are two widely used techniques • Classification method: Naïve Bayes classifier and mixture of Gaussian are widely used techniques • Gaussian model: need few training data, difficulties on parameter tuning, need less memory space, processing/detection slow • Bayes theorem: need for larger training data, easy for learning, need more memory space, processing/detection fast State-of-the-art method: • Jones, M. J. and Rehg, J. M. (2002). Statistical color models with application to skin detection. International Journal of Computer Vision, 46(1):81–96.
  • 7. 3. Current Problem • Probability accumulation for higher level vision task- as probability for skin/non-skin vary highly even for adjacent pixels Naturally skin is continuous region
  • 8. 4 Region Based Approach • Yang and Ahuja (1998) and Kruppa et al. (2002)- search elliptical regions for face detection • Sebe Sebe et al.(2004)- 3x3 fixed size patches to train Bayesian network • Our approach treat skin as region with varying sizes, which is purely based on image evidence
  • 9. Proposed Technique/Framework 1. Region extraction- quick shift image segmentation, also know as “superpixels” 2. Region classification- pixel/region based 3. Smoothing- Conditional Random Field (CRF) 5. Proposed Region-Based technique
  • 10. 5.1 Region Extraction Region/Superpixel extraction – quick shift image segmentation using RGB color and positional (XY) coordinate
  • 11. 5.1 Region Extraction - Region extraction is purely evidence based i.e. based on RGB color and spatial location (xy-coordinate) of the image - Regions have different size and shape, which is depend upon complexity of the image - No explicit concept of boundary - Quick shift preserve the boundary of the objects, hence we could get very accurate object segmentation - We could set importance on color difference vs spatial distance
  • 12. 5.2 Region Classification 5.2.1 Basic Skin Color Classifer Naïve Bayes: posterior likelihood * prior∝ However, we could use any suitable/best method for skin classification )( )()/( )/( cp spscp csp = )( )()/( )/( cp nspnscp cnsp = Θ> )/( )/( cnsp csp Θ> )()/( )()/( nspnscp spscp 1 )/( )/( > nscp scp Where, c = color, s = skin and ns = non-skin
  • 13. 5.2 Region Classification • Average the skin probability (s) of all color pixels (c) belongs to the given superpixel (sp) • Average the non-skin probability (ns) of all color pixels (c) belongs to the given superpixel (sp) ∑= N i icsP N spsP )|( 1 )|( ∑= N i icnsP N spnsP )|( 1 )|(
  • 14. 5.3 Smoothing with CRF • Conditional Random Field (CRF) optimization equation • Color potential • Edge and boundary potential ∑∑ ∈∈ Φ+Ψ−=− Ess jiji Ss ii jii ssccslSLP ),( ),|,()|());|(log( ωω ))|(log()|( iiii slPsl =ψ [ ]ji ji ji jiji cc ss ssL sscc ≠         −+ =Φ , ||||1 ),( ),|,(
  • 15. 5.4 Training First Phase (training histogram): • Train 2 histograms for skin and non-skin separately Second phase (training CRF): learning : si sj … px1(s|c) px1(ns|c) px1(s|c) px1(ns|c) color difference + boundary length ∑∑ ∈∈ Φ+Ψ−=− Ess jiji Ss ii jii ssccslSLP ),( ),|,()|());|(log( ωω ω
  • 16. 6 Experimental Results • Dataset content 14 thousands images collected freely from the web (Compaq dataset) • 4,700 are skin and 9,000 non-skin images • Approximately 1 billion pixels are manually labeled • 50% is use for training and 50% for testing Method True Positive False Positive Jones and Rehg (2002) 90% 14.2% Our (Superpixel only) 91.44% 13.73% Our (Superpixel and CRF) 91.17% 13.12%
  • 17. 6 Experimental Results Our proposed new region- based technique outperform current state-of-the–art technique
  • 18. 6 Experimental Results Applying CRF is always not good !
  • 19. 6 Experimental Results However, in aggregate CRF performs better!
  • 20. 7. Conclusions • Region-based technique performs better than pixel-based • Region-based technique could easily incorporate texture info and other type of features to improve the result • Aggregation of pixels into region help to reduce local redundancy. • Region-based technique extracts larger smooth regions, which is very helpful for higher-level vision task The message to take home: It is better/natural to treat skin as regions instead of individual pixels!