SlideShare a Scribd company logo
1 of 16
An investigation Into bias in
Facial Recognition using
Learning Algorithms
Clockwise from Top Left:
 Michael Murray: Serial killer lives in Dublin 4
 Miranda Barbour: Teen serial killer 22
murders
 Mezut Oezil: Football player
 Jessie Sleator : Teen girl from Dublin
Just as a human would find it hard to spot
a criminal, a machine learning algorithm
faces same challenge.
Motivation for research
▪ Initially, the motivation came from work such as that of Wu & Zhang (2016) who
claimed to have high accuracy in classifying criminality from facial images.
▪ There were strong reactions to their work with accusations of biases within their
dataset.
▪ Algorithm may not pick up on underlying physical structures associated with
criminality, but rather may discriminate based on context-specific cues from the
situations under which the photographs were taken.
▪ Machine learning algorithms are only as good as their training data
▪ Bias example: criminal mug-shots may be more likely to show negative emotion
Related Work
▪ Automated Inference on criminality (2016)
- Wu, X. and Zhang, X. (2016). Automated inference on criminality using face images.
▪ A.I. Gaydar (2017)
- Wang, Y. and Kosinski, M. (2017). Deep neural networks are more accurate than
humans at detecting sexual orientation from facial images.
▪ Instagram photos predict depression. (2016)
- Reece, A. G. and Danforth, C. M. (2016). Instagram photos reveal predictive markers of
depression
Research Question/Objectives
▪ The aim of this paper is to investigate the presence and effects of biases in
training datasets by focusing on the facial recognition features pattern
identification problem applied to criminal classification.
▪ There are many types of biases e.g. Emotion, gender, race, facial features such
as tattoos, hairstyles, image background.
▪ E.g. Given the context, criminal mug-shots tend to exhibit negative emotional
states such as fear, contempt and anger.
▪ Many datasets are open datasets that do not require informed consent for usage.
In comparison, some datasets are prepared by researchers that endeavour to
create unbiased image sets.
▪ This fact makes the awareness of biases even more important.
Methodology
Data Sources
PCA
 1102 images of criminals and non-criminal.
 40,000 features (200 x 200 pixels).
 PCA is applied to reduce dimensions while
maintaining explained variance.
 A graph of no. of components vs. explained
variance was used for optimisation.
Implementation – Criminal Classifier
 Main steps involved in criminal classifier model design:
1. Read in images, convert to grayscale, align eyes and crop using OpenCv functionality.
2. Applied PCA to reduce dimensions from 40,000 to 300-750.
3. Used supervised learning algorithm (Keras Sequential NN) for training and validating the
model. (Stratified K-fold cross validation).
4. Neural net optimisation using various architectures and hyper-parameter tuning.
(Epochs, batches, Dropout)
5. Obtained performance metrics i.e .accuracy, confusion matrix and learning curves
(python sklearn).
Implementation – Emotion Classifier
 FACS (Ekman, 1978)
 (Cohn-Kanade database)
 Classifier trained and tested using Fisherface Recognizer (OpenCv)
Emotion Classification of Image Sets
Emotion Profile Criminals Emotion profile Non-Criminals
The emotion profiling above shows an imbalance across datasets which may well be a source of bias
that could over-estimate the classifier efficacy. Overlapping emotions sets are small and would require
a larger dataset to incorporate into the classifier.
Evaluation Scenarios
 A number of biases were investigated:
Scenario 1: Classifier was run on all images (481 non-criminals & 621 criminals).
Scenario 2: Classifier was run on 240 criminal men and 252 non-criminal women.
Scenario 3: To compare with Scenario 2, the classifier was run for 240 criminal men and
224 non-criminal men. Given that Scenario 2 has a gender bias, we may expect that
Scenario 3 may perform worse.
Scenario 4: 77 Criminal women vs. 78 non-criminal men. This scenario attempted to
investigate if accuracy is improved due to gender bias (Small dataset a concern for
predictive power)
Evaluation
Results Set Scenario 1 – All Images
 (Mixed gender, race and emotion)
Criminal images: 621
Non-criminal images: 481
No. of Principal Components: 750
Explained Variance: 99.1%
Stratified 10-Fold Cross Validation Accuracy: 60%
 Multiple potential biases – gender, emotion,
tattoos, hair
Confusion matrix is a single cross-validated fold i.e.
111 from 1102 images (90:10 train-test)
Evaluation
Results Set Scenario 2 – Criminal Men vs.
Non-criminal women
 (Mixed race and emotion)
Criminal images (Men): 240
Non-criminal images (Women): 252
No. of Principal Components: 300
Explained Variance: 97.8%
Stratified 10-Fold Cross Validation Accuracy: 59.2%
 Accuracy in Scenario 2 similar to Scenario 1 but
Scenario 2 has 45% of the image count of Scenario
1. (1102 vs. 492 images)
Evaluation
Results Set Scenario 3 – Criminal Men vs.
Non-criminal men
 (Mixed race and emotion)
Criminal images (Men): 240
Non-criminal images (Men): 224
No. of Principal Components: 300
Explained Variance: 98 %
Stratified 10-Fold Cross Validation Accuracy: 51.3%
 Scenario 2 and 3 were trained/validated on similar
image set sizes.
 The Stratified 10-fold cross validated accuracy is
8% higher for the Scenario 2 which has a data sets
with opposing genders – perhaps gender aided
classification.
Evaluation
Results Set Scenario 4 – Criminal women
vs. Non-criminal men
 Mixed race and emotion)
Criminal images (Women): 77
Non-criminal images (Men): 78
No. of Principal Components: 120
Explained Variance: 98%
Stratified 10-Fold Cross Validation Accuracy: 59%
 Given that there was only 77 criminal women
images, the classifier may be limited in its predictive
power.
Conclusions/Future Work
▪ Many biases can exist within images. This research attempted to show that both gender and
emotion biases could affect the performance of a classifier.
▪ The model shows a high emotion imbalance across criminal and non-criminal datasets as well
as performance differences when gender bias was included.
▪ In the case of labelling people based on categories such as criminal, gay, IQ etc, there are
serious consideration s to be addressed if machine learning algorithms are to be utilised and
trusted as accurate.
▪ Future Work:
▪ Larger training dataset.
▪ With more images, the classifier could be run in emotion balanced sets.
▪ Use of VGG Face which uses a DNN (pretrained on 2.6 million images) to extract facial features.
▪ Investigation of Kernal PCA and Convolutional Neural Networks

More Related Content

Similar to Criminals presentation

Don't blindly trust your ML System, it may change your life (Azzurra Ragone, ...
Don't blindly trust your ML System, it may change your life (Azzurra Ragone, ...Don't blindly trust your ML System, it may change your life (Azzurra Ragone, ...
Don't blindly trust your ML System, it may change your life (Azzurra Ragone, ...Data Driven Innovation
 
9th may net sci presentation (1)
9th may net sci presentation (1)9th may net sci presentation (1)
9th may net sci presentation (1)Rajath Mahesh
 
San Francisco Crime Prediction Report
San Francisco Crime Prediction ReportSan Francisco Crime Prediction Report
San Francisco Crime Prediction ReportRohit Dandona
 
photo detection in personal photo collection
photo detection in personal photo collectionphoto detection in personal photo collection
photo detection in personal photo collectionsonalijagtap15
 
San Francisco Crime Analysis Classification Kaggle contest
San Francisco Crime Analysis Classification Kaggle contestSan Francisco Crime Analysis Classification Kaggle contest
San Francisco Crime Analysis Classification Kaggle contestSameer Darekar
 
Helping Chicago Communities Identify Subjects Who Are Likely to be Involved i...
Helping Chicago Communities Identify Subjects Who Are Likely to be Involved i...Helping Chicago Communities Identify Subjects Who Are Likely to be Involved i...
Helping Chicago Communities Identify Subjects Who Are Likely to be Involved i...Brendan Sigale
 
ZERNIKE-ENTROPY IMAGE SIMILARITY MEASURE BASED ON JOINT HISTOGRAM FOR FACE RE...
ZERNIKE-ENTROPY IMAGE SIMILARITY MEASURE BASED ON JOINT HISTOGRAM FOR FACE RE...ZERNIKE-ENTROPY IMAGE SIMILARITY MEASURE BASED ON JOINT HISTOGRAM FOR FACE RE...
ZERNIKE-ENTROPY IMAGE SIMILARITY MEASURE BASED ON JOINT HISTOGRAM FOR FACE RE...AM Publications
 
Neo4j - Responsible AI
Neo4j - Responsible AINeo4j - Responsible AI
Neo4j - Responsible AINeo4j
 
Predicting the Crimes in Chicago
Predicting the Crimes in Chicago Predicting the Crimes in Chicago
Predicting the Crimes in Chicago Swati Arora
 
Crime analysis mapping, intrusion detection using data mining
Crime analysis mapping, intrusion detection using data miningCrime analysis mapping, intrusion detection using data mining
Crime analysis mapping, intrusion detection using data miningVenkat Projects
 
Crime analysis mapping, intrusion detection using data mining
Crime analysis mapping, intrusion detection using data miningCrime analysis mapping, intrusion detection using data mining
Crime analysis mapping, intrusion detection using data miningVenkat Projects
 
Face identification
Face  identificationFace  identification
Face identification27vipin92
 
Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)Krishnaram Kenthapadi
 
project-classified-333.pptx
project-classified-333.pptxproject-classified-333.pptx
project-classified-333.pptxJessesGus
 
Using fairness metrics to solve ethical dilemmas of machine learning
Using fairness metrics to solve ethical dilemmas of machine learningUsing fairness metrics to solve ethical dilemmas of machine learning
Using fairness metrics to solve ethical dilemmas of machine learningLászló Kovács
 
Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...
Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...
Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...Shift Conference
 
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)Krishnaram Kenthapadi
 
Fairness in Machine Learning @Codemotion
Fairness in Machine Learning @CodemotionFairness in Machine Learning @Codemotion
Fairness in Machine Learning @CodemotionAzzurra Ragone
 

Similar to Criminals presentation (20)

Don't blindly trust your ML System, it may change your life (Azzurra Ragone, ...
Don't blindly trust your ML System, it may change your life (Azzurra Ragone, ...Don't blindly trust your ML System, it may change your life (Azzurra Ragone, ...
Don't blindly trust your ML System, it may change your life (Azzurra Ragone, ...
 
Netsci
NetsciNetsci
Netsci
 
9th may net sci presentation (1)
9th may net sci presentation (1)9th may net sci presentation (1)
9th may net sci presentation (1)
 
San Francisco Crime Prediction Report
San Francisco Crime Prediction ReportSan Francisco Crime Prediction Report
San Francisco Crime Prediction Report
 
photo detection in personal photo collection
photo detection in personal photo collectionphoto detection in personal photo collection
photo detection in personal photo collection
 
San Francisco Crime Analysis Classification Kaggle contest
San Francisco Crime Analysis Classification Kaggle contestSan Francisco Crime Analysis Classification Kaggle contest
San Francisco Crime Analysis Classification Kaggle contest
 
Helping Chicago Communities Identify Subjects Who Are Likely to be Involved i...
Helping Chicago Communities Identify Subjects Who Are Likely to be Involved i...Helping Chicago Communities Identify Subjects Who Are Likely to be Involved i...
Helping Chicago Communities Identify Subjects Who Are Likely to be Involved i...
 
ZERNIKE-ENTROPY IMAGE SIMILARITY MEASURE BASED ON JOINT HISTOGRAM FOR FACE RE...
ZERNIKE-ENTROPY IMAGE SIMILARITY MEASURE BASED ON JOINT HISTOGRAM FOR FACE RE...ZERNIKE-ENTROPY IMAGE SIMILARITY MEASURE BASED ON JOINT HISTOGRAM FOR FACE RE...
ZERNIKE-ENTROPY IMAGE SIMILARITY MEASURE BASED ON JOINT HISTOGRAM FOR FACE RE...
 
Neo4j - Responsible AI
Neo4j - Responsible AINeo4j - Responsible AI
Neo4j - Responsible AI
 
Predicting the Crimes in Chicago
Predicting the Crimes in Chicago Predicting the Crimes in Chicago
Predicting the Crimes in Chicago
 
Crime analysis mapping, intrusion detection using data mining
Crime analysis mapping, intrusion detection using data miningCrime analysis mapping, intrusion detection using data mining
Crime analysis mapping, intrusion detection using data mining
 
Crime analysis mapping, intrusion detection using data mining
Crime analysis mapping, intrusion detection using data miningCrime analysis mapping, intrusion detection using data mining
Crime analysis mapping, intrusion detection using data mining
 
Face identification
Face  identificationFace  identification
Face identification
 
Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)
 
Final presentation
Final presentationFinal presentation
Final presentation
 
project-classified-333.pptx
project-classified-333.pptxproject-classified-333.pptx
project-classified-333.pptx
 
Using fairness metrics to solve ethical dilemmas of machine learning
Using fairness metrics to solve ethical dilemmas of machine learningUsing fairness metrics to solve ethical dilemmas of machine learning
Using fairness metrics to solve ethical dilemmas of machine learning
 
Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...
Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...
Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...
 
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
 
Fairness in Machine Learning @Codemotion
Fairness in Machine Learning @CodemotionFairness in Machine Learning @Codemotion
Fairness in Machine Learning @Codemotion
 

Recently uploaded

Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...Suhani Kapoor
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort servicejennyeacort
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPramod Kumar Srivastava
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceSapana Sha
 
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改atducpo
 
9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home ServiceSapana Sha
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...dajasot375
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998YohFuh
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024thyngster
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfJohn Sterrett
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Callshivangimorya083
 
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfKantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfSocial Samosa
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubaihf8803863
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsappssapnasaifi408
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Serviceranjana rawat
 

Recently uploaded (20)

꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts Service
 
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
 
9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
 
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998
 
Decoding Loan Approval: Predictive Modeling in Action
Decoding Loan Approval: Predictive Modeling in ActionDecoding Loan Approval: Predictive Modeling in Action
Decoding Loan Approval: Predictive Modeling in Action
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdf
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
 
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfKantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
 

Criminals presentation

  • 1. An investigation Into bias in Facial Recognition using Learning Algorithms
  • 2. Clockwise from Top Left:  Michael Murray: Serial killer lives in Dublin 4  Miranda Barbour: Teen serial killer 22 murders  Mezut Oezil: Football player  Jessie Sleator : Teen girl from Dublin Just as a human would find it hard to spot a criminal, a machine learning algorithm faces same challenge.
  • 3. Motivation for research ▪ Initially, the motivation came from work such as that of Wu & Zhang (2016) who claimed to have high accuracy in classifying criminality from facial images. ▪ There were strong reactions to their work with accusations of biases within their dataset. ▪ Algorithm may not pick up on underlying physical structures associated with criminality, but rather may discriminate based on context-specific cues from the situations under which the photographs were taken. ▪ Machine learning algorithms are only as good as their training data ▪ Bias example: criminal mug-shots may be more likely to show negative emotion
  • 4. Related Work ▪ Automated Inference on criminality (2016) - Wu, X. and Zhang, X. (2016). Automated inference on criminality using face images. ▪ A.I. Gaydar (2017) - Wang, Y. and Kosinski, M. (2017). Deep neural networks are more accurate than humans at detecting sexual orientation from facial images. ▪ Instagram photos predict depression. (2016) - Reece, A. G. and Danforth, C. M. (2016). Instagram photos reveal predictive markers of depression
  • 5. Research Question/Objectives ▪ The aim of this paper is to investigate the presence and effects of biases in training datasets by focusing on the facial recognition features pattern identification problem applied to criminal classification. ▪ There are many types of biases e.g. Emotion, gender, race, facial features such as tattoos, hairstyles, image background. ▪ E.g. Given the context, criminal mug-shots tend to exhibit negative emotional states such as fear, contempt and anger. ▪ Many datasets are open datasets that do not require informed consent for usage. In comparison, some datasets are prepared by researchers that endeavour to create unbiased image sets. ▪ This fact makes the awareness of biases even more important.
  • 7. PCA  1102 images of criminals and non-criminal.  40,000 features (200 x 200 pixels).  PCA is applied to reduce dimensions while maintaining explained variance.  A graph of no. of components vs. explained variance was used for optimisation.
  • 8. Implementation – Criminal Classifier  Main steps involved in criminal classifier model design: 1. Read in images, convert to grayscale, align eyes and crop using OpenCv functionality. 2. Applied PCA to reduce dimensions from 40,000 to 300-750. 3. Used supervised learning algorithm (Keras Sequential NN) for training and validating the model. (Stratified K-fold cross validation). 4. Neural net optimisation using various architectures and hyper-parameter tuning. (Epochs, batches, Dropout) 5. Obtained performance metrics i.e .accuracy, confusion matrix and learning curves (python sklearn).
  • 9. Implementation – Emotion Classifier  FACS (Ekman, 1978)  (Cohn-Kanade database)  Classifier trained and tested using Fisherface Recognizer (OpenCv)
  • 10. Emotion Classification of Image Sets Emotion Profile Criminals Emotion profile Non-Criminals The emotion profiling above shows an imbalance across datasets which may well be a source of bias that could over-estimate the classifier efficacy. Overlapping emotions sets are small and would require a larger dataset to incorporate into the classifier.
  • 11. Evaluation Scenarios  A number of biases were investigated: Scenario 1: Classifier was run on all images (481 non-criminals & 621 criminals). Scenario 2: Classifier was run on 240 criminal men and 252 non-criminal women. Scenario 3: To compare with Scenario 2, the classifier was run for 240 criminal men and 224 non-criminal men. Given that Scenario 2 has a gender bias, we may expect that Scenario 3 may perform worse. Scenario 4: 77 Criminal women vs. 78 non-criminal men. This scenario attempted to investigate if accuracy is improved due to gender bias (Small dataset a concern for predictive power)
  • 12. Evaluation Results Set Scenario 1 – All Images  (Mixed gender, race and emotion) Criminal images: 621 Non-criminal images: 481 No. of Principal Components: 750 Explained Variance: 99.1% Stratified 10-Fold Cross Validation Accuracy: 60%  Multiple potential biases – gender, emotion, tattoos, hair Confusion matrix is a single cross-validated fold i.e. 111 from 1102 images (90:10 train-test)
  • 13. Evaluation Results Set Scenario 2 – Criminal Men vs. Non-criminal women  (Mixed race and emotion) Criminal images (Men): 240 Non-criminal images (Women): 252 No. of Principal Components: 300 Explained Variance: 97.8% Stratified 10-Fold Cross Validation Accuracy: 59.2%  Accuracy in Scenario 2 similar to Scenario 1 but Scenario 2 has 45% of the image count of Scenario 1. (1102 vs. 492 images)
  • 14. Evaluation Results Set Scenario 3 – Criminal Men vs. Non-criminal men  (Mixed race and emotion) Criminal images (Men): 240 Non-criminal images (Men): 224 No. of Principal Components: 300 Explained Variance: 98 % Stratified 10-Fold Cross Validation Accuracy: 51.3%  Scenario 2 and 3 were trained/validated on similar image set sizes.  The Stratified 10-fold cross validated accuracy is 8% higher for the Scenario 2 which has a data sets with opposing genders – perhaps gender aided classification.
  • 15. Evaluation Results Set Scenario 4 – Criminal women vs. Non-criminal men  Mixed race and emotion) Criminal images (Women): 77 Non-criminal images (Men): 78 No. of Principal Components: 120 Explained Variance: 98% Stratified 10-Fold Cross Validation Accuracy: 59%  Given that there was only 77 criminal women images, the classifier may be limited in its predictive power.
  • 16. Conclusions/Future Work ▪ Many biases can exist within images. This research attempted to show that both gender and emotion biases could affect the performance of a classifier. ▪ The model shows a high emotion imbalance across criminal and non-criminal datasets as well as performance differences when gender bias was included. ▪ In the case of labelling people based on categories such as criminal, gay, IQ etc, there are serious consideration s to be addressed if machine learning algorithms are to be utilised and trusted as accurate. ▪ Future Work: ▪ Larger training dataset. ▪ With more images, the classifier could be run in emotion balanced sets. ▪ Use of VGG Face which uses a DNN (pretrained on 2.6 million images) to extract facial features. ▪ Investigation of Kernal PCA and Convolutional Neural Networks