SlideShare a Scribd company logo
Self Adaptive Systems: An Experimental
Analysis of the Performance Over Time

   Ajita Rattani, Gian Luca Marcialis, Fabio Roli
Biometric Verification Systems
   They operate in two distinct stages:
                                           Image is acquired for each user
                                          (gallery) in controlled environment
       1) The enrolment stage             (for instance ISO/ IEC FCD 19794-5 standard)

       2) The verification stage.         “Template” is created and identity
                                            labels assigned



The performance of biometric systems degrades quickly when input images
exhibit substantial variations compared to the enrolled “templates”

  Some face examples showing intra-class variations in input data un-
 represented by enrolled template
          TEMPLATE                QUERY IMAGES




                                                                                         2
Initial Attempts to Increase Template
              Representativeness

• Re-enrollment

• Multibiometrics (Handbook of Multi-biometrics, 2006)

• Virtual biometric template synthesis (pose correction,
  illumination correction, de-ageing transformations) (Wang et
  al. 2006, Geng et al. 2007)




                                                                 3
Recent Introduction-
             Template update Methods
•    Characteristics:
    –   Adapt themselves to the intra-class variation of the input
        data.


    –   Minimizing performance loss due to unrepresentative
        and outdated templates


•    Commonly adopted is self-adaptive systems.



                                                                     4
Self-Adaptive Systems
           • Highly confidently
             classified samples are
             used for adaptation
           • In order to avoid
             impostor introduction
           • Claimed to be robust
             against short and
             medium term intra-
             class variations
State-of-the-art
Reference      Modality Impostor Database
X. Jiang       Finger       No           100x8
and W. Ser                               12x200
Roli et al     Face         No           100x8
Ryu et al.     Finger       No           41x100
Pavani et      Face         No           5 months
al.


   Till date: No paper has shown the performance robustness
   over time
   Reason: Unavailability of large number of samples collected
   over a period of time, per user basis
   Assumption of absence of impostor
   No theoretical explanation of the functioning
Contributions
– This is the first study evaluating the
  performance of self-adaptive systems, on the
  input batch of samples as available over time

– The conceptual explanation of the functioning
  of self-adaptive systems, supported by
  experimental validations

– DIEE multimodal database has been explicitly
  collected for this aim, over a span of 1.5 years
Conceptual representation




A hypothetical diagram showing the           The representational capability of each
initial condition where the enrolled         template in the updated set on
template is shown with the help of star      adaptation using samples 1, 2 and 3
and encircled in its representation region
Contd...




As a result overall genuine region        In the real time environment impostor
expands                                   samples may also be present
Experimental Validations
• Dataset: DIEE Multimodal database
  – 49 subjects with 50 samples per subject acquired in five
    sessions with 10 samples per session
  – Acquired in a time span of 1.5 years
  – Containing temporal as well as other intra-class variations




               Example facial images taken from two different
               sessions for a randomnly choosen user
Experimental Protocol
• Training: 2 enrolled images per person from
  the batch b_1

• Updating: batches two to four

• Performance evaluation:On updating
  using batch b_i performance is evaluated
  for batch b_i+1and EER_i computed
Experiment #1
• Aim: to evaluate the performance of self adaptive
  systems over time

• Assumption of absence of impostor’s access.

• Updating threshold: 0.01 % FAR
Results

                                                             Performance
                                                             enhancement
                                                             and stability can
                                                             be attained over
                                                             time




Performance of self-adaptive systems for index and
thumbprint biometrics in comparison to baseline classifier
At varying threshold conditions

                                                            Large variation in
                                                            the performance
                                                                from one
                                                            updating cycle to
                                                              another as a
                                                                 result of
                                                             representation
                                                            region expansion
                                                               significantly




 Performance of self-adaptive face recognition system
 at varying thresholds from stringent to relaxed for face
 biometrics
Table: showing percentage of samples gradually
added to the user’s gallery for face biometrics

    Threshold   (%) Cycle 1   (%) Cycle 2   (%) Cycle 3   (%) Cycle 4
    at % FAR
    0.00001 %   31.17         21.60         19.75         19.36
    0.00001 %   33.3          26.54         26.95         27.70
    0.01 %      52.16         55.86         61.83         65.74
    0.1 %       56.79         62.03         68.31         70.98
    1%          60.8          68.51         73.66         75.30
Further confirmation:- representation
            region expansion




The scores obtained on fifth batch using the   The scores obtained on fifth batch using the
baseline matcher enrolled with two templates   self-adaptive system updated using 1 to 4
from a random user for thumb biometric         batches for a random user for thumb biometric
Experiment #2
• Aim: is to evaluate the performance of self adaptive systems over
  time on the assumption of presence of impostor’s access.

• Assumption: Presence of impostors, enabling the evaluation of
  impostor’s intrusion over time

• Updating Threshold: 0.001 % FAR
•Performance
                                               strongly suffers
                                               from the operation
                                               at stringent
                                               threshold
                                               •However, the
                                               stability can be
                                               obtained over time
                                               •Different
                                               biometrics show
                                               difference trend in
                                               performance
                                               improvement
Performance of self adaptive thumb and index
fingerprint system under the assumption of
impostor presence
Conclusions and Future work
• Self-adaptive systems can result in performance enhancement and
  classifier’s stability over time

• The obtained performance enhancement is very much dependent
  on the set updating threshold

• Different biometric may show different performance trend over time.

• The possibility of presence and updating due to impostor is a
  serious and open issue.

• Future work will rely on further development of the conceptual
  behaviour and significant in-depth analysis of impostor’s effect over
  time.

More Related Content

Viewers also liked

A Bayesian Approach for Modeling Sensor Influence on Quality, Liveness and Ma...
A Bayesian Approach for Modeling SensorInfluence on Quality, Liveness and Ma...A Bayesian Approach for Modeling SensorInfluence on Quality, Liveness and Ma...
A Bayesian Approach for Modeling Sensor Influence on Quality, Liveness and Ma...AjitaRattani
 
Gambar skg
Gambar skgGambar skg
Gambar skgNur Ayob
 
Gambar acara saringan dan raptai sukan skg1
Gambar acara saringan dan raptai sukan skg1Gambar acara saringan dan raptai sukan skg1
Gambar acara saringan dan raptai sukan skg1Nur Ayob
 
Exploting the Doddindton zoo effect in biometric fusion
Exploting the Doddindton zoo effect in biometric fusionExploting the Doddindton zoo effect in biometric fusion
Exploting the Doddindton zoo effect in biometric fusionAjitaRattani
 
Dipd rt.002 004
Dipd rt.002 004Dipd rt.002 004
Dipd rt.002 004
Desa Dawuan Timur
 
Benifit profile
Benifit profileBenifit profile
Benifit profile
Shardul Kapooria
 
Dipd rt.002 006
Dipd rt.002 006Dipd rt.002 006
Dipd rt.002 006
Desa Dawuan Timur
 
Dokumentasi pertandingan bercerita bahasa melayu tahap 1 dan 2 nur azlina bt....
Dokumentasi pertandingan bercerita bahasa melayu tahap 1 dan 2 nur azlina bt....Dokumentasi pertandingan bercerita bahasa melayu tahap 1 dan 2 nur azlina bt....
Dokumentasi pertandingan bercerita bahasa melayu tahap 1 dan 2 nur azlina bt....Nur Ayob
 
Dipd rt.002 001
Dipd rt.002 001Dipd rt.002 001
Dipd rt.002 001
Desa Dawuan Timur
 
C M E on Cervical Cancer Screening Program
C M E on  Cervical Cancer Screening Program C M E on  Cervical Cancer Screening Program
C M E on Cervical Cancer Screening Program
Shardul Kapooria
 
Architectural Design Spaces for Feedback Control in Self-Adaptive Systems Con...
Architectural Design Spaces for Feedback Control in Self-Adaptive Systems Con...Architectural Design Spaces for Feedback Control in Self-Adaptive Systems Con...
Architectural Design Spaces for Feedback Control in Self-Adaptive Systems Con...
Sandro Andrade
 
ACTRESS: Domain-Specific Modeling of Self-Adaptive Software Architectures
ACTRESS: Domain-Specific Modeling of Self-Adaptive Software ArchitecturesACTRESS: Domain-Specific Modeling of Self-Adaptive Software Architectures
ACTRESS: Domain-Specific Modeling of Self-Adaptive Software Architectures
Filip Krikava
 
Powerpoint penyediaan bekas akuarium
Powerpoint penyediaan bekas akuariumPowerpoint penyediaan bekas akuarium
Powerpoint penyediaan bekas akuariumAhmad Izzuddin
 
Athena khanh duy
Athena khanh duyAthena khanh duy
Athena khanh duy
Takashi Akimoto
 
Cơ sở lý thuyết (autosaved)
Cơ sở lý thuyết (autosaved)Cơ sở lý thuyết (autosaved)
Cơ sở lý thuyết (autosaved)
Takashi Akimoto
 
Uu no 6_2014_dawuantimur.com
Uu no 6_2014_dawuantimur.comUu no 6_2014_dawuantimur.com
Uu no 6_2014_dawuantimur.com
Desa Dawuan Timur
 
Hausi Müller - Towards Self-Adaptive Software-Intensive Systems
Hausi Müller - Towards Self-Adaptive Software-Intensive SystemsHausi Müller - Towards Self-Adaptive Software-Intensive Systems
Hausi Müller - Towards Self-Adaptive Software-Intensive Systems
CHOOSE
 

Viewers also liked (17)

A Bayesian Approach for Modeling Sensor Influence on Quality, Liveness and Ma...
A Bayesian Approach for Modeling SensorInfluence on Quality, Liveness and Ma...A Bayesian Approach for Modeling SensorInfluence on Quality, Liveness and Ma...
A Bayesian Approach for Modeling Sensor Influence on Quality, Liveness and Ma...
 
Gambar skg
Gambar skgGambar skg
Gambar skg
 
Gambar acara saringan dan raptai sukan skg1
Gambar acara saringan dan raptai sukan skg1Gambar acara saringan dan raptai sukan skg1
Gambar acara saringan dan raptai sukan skg1
 
Exploting the Doddindton zoo effect in biometric fusion
Exploting the Doddindton zoo effect in biometric fusionExploting the Doddindton zoo effect in biometric fusion
Exploting the Doddindton zoo effect in biometric fusion
 
Dipd rt.002 004
Dipd rt.002 004Dipd rt.002 004
Dipd rt.002 004
 
Benifit profile
Benifit profileBenifit profile
Benifit profile
 
Dipd rt.002 006
Dipd rt.002 006Dipd rt.002 006
Dipd rt.002 006
 
Dokumentasi pertandingan bercerita bahasa melayu tahap 1 dan 2 nur azlina bt....
Dokumentasi pertandingan bercerita bahasa melayu tahap 1 dan 2 nur azlina bt....Dokumentasi pertandingan bercerita bahasa melayu tahap 1 dan 2 nur azlina bt....
Dokumentasi pertandingan bercerita bahasa melayu tahap 1 dan 2 nur azlina bt....
 
Dipd rt.002 001
Dipd rt.002 001Dipd rt.002 001
Dipd rt.002 001
 
C M E on Cervical Cancer Screening Program
C M E on  Cervical Cancer Screening Program C M E on  Cervical Cancer Screening Program
C M E on Cervical Cancer Screening Program
 
Architectural Design Spaces for Feedback Control in Self-Adaptive Systems Con...
Architectural Design Spaces for Feedback Control in Self-Adaptive Systems Con...Architectural Design Spaces for Feedback Control in Self-Adaptive Systems Con...
Architectural Design Spaces for Feedback Control in Self-Adaptive Systems Con...
 
ACTRESS: Domain-Specific Modeling of Self-Adaptive Software Architectures
ACTRESS: Domain-Specific Modeling of Self-Adaptive Software ArchitecturesACTRESS: Domain-Specific Modeling of Self-Adaptive Software Architectures
ACTRESS: Domain-Specific Modeling of Self-Adaptive Software Architectures
 
Powerpoint penyediaan bekas akuarium
Powerpoint penyediaan bekas akuariumPowerpoint penyediaan bekas akuarium
Powerpoint penyediaan bekas akuarium
 
Athena khanh duy
Athena khanh duyAthena khanh duy
Athena khanh duy
 
Cơ sở lý thuyết (autosaved)
Cơ sở lý thuyết (autosaved)Cơ sở lý thuyết (autosaved)
Cơ sở lý thuyết (autosaved)
 
Uu no 6_2014_dawuantimur.com
Uu no 6_2014_dawuantimur.comUu no 6_2014_dawuantimur.com
Uu no 6_2014_dawuantimur.com
 
Hausi Müller - Towards Self-Adaptive Software-Intensive Systems
Hausi Müller - Towards Self-Adaptive Software-Intensive SystemsHausi Müller - Towards Self-Adaptive Software-Intensive Systems
Hausi Müller - Towards Self-Adaptive Software-Intensive Systems
 

Similar to Self adaptive biometric systems

Bab ii testing throughout the software life cycle
Bab ii testing throughout the software life cycleBab ii testing throughout the software life cycle
Bab ii testing throughout the software life cycle
Syakir Arsalan
 
Software archiecture lecture05
Software archiecture   lecture05Software archiecture   lecture05
Software archiecture lecture05Luktalja
 
Bab ii testing throughout the software life cycle (yoga)
Bab ii testing throughout the software life cycle (yoga)Bab ii testing throughout the software life cycle (yoga)
Bab ii testing throughout the software life cycle (yoga)
sidjdhdjsks
 
Chapter 2 Testing Throughout the Software Life Cycle
Chapter 2 Testing Throughout the Software Life CycleChapter 2 Testing Throughout the Software Life Cycle
Chapter 2 Testing Throughout the Software Life Cycle
Siti Deny Nadiroha
 
Bab ii testing throughout the software life cycle
Bab ii testing throughout the software life cycleBab ii testing throughout the software life cycle
Bab ii testing throughout the software life cycle
Riauly Putra
 
Testing throughout the software life cycle
Testing throughout the software life cycleTesting throughout the software life cycle
Testing throughout the software life cycle
aidul azmi
 
Using evolutionary testing to improve efficiency and quality
Using evolutionary testing to improve efficiency and qualityUsing evolutionary testing to improve efficiency and quality
Using evolutionary testing to improve efficiency and quality
Faysal Ahmed
 
Examen de ingles
Examen de inglesExamen de ingles
Examen de ingleschino101
 
Practical Testing Definition for Mobile Devices
Practical Testing Definition for Mobile DevicesPractical Testing Definition for Mobile Devices
Practical Testing Definition for Mobile DevicesJohan Hoberg
 
Testing the Untestable: Model Testing of Complex Software-Intensive Systems
Testing the Untestable: Model Testing of Complex Software-Intensive SystemsTesting the Untestable: Model Testing of Complex Software-Intensive Systems
Testing the Untestable: Model Testing of Complex Software-Intensive Systems
Lionel Briand
 
Testing throughout the software life cycle
Testing throughout the software life cycleTesting throughout the software life cycle
Testing throughout the software life cycle
Muhammad Khairil
 
Basic Engineering Design (Part 6): Test and Evaluate
Basic Engineering Design (Part 6): Test and EvaluateBasic Engineering Design (Part 6): Test and Evaluate
Basic Engineering Design (Part 6): Test and Evaluate
Denise Wilson
 
Testing throughout the software life cycle - Testing & Implementation
Testing throughout the software life cycle - Testing & ImplementationTesting throughout the software life cycle - Testing & Implementation
Testing throughout the software life cycle - Testing & Implementation
yogi syafrialdi
 
Testing throughout the software life cycle 2
Testing throughout the software life cycle 2Testing throughout the software life cycle 2
Testing throughout the software life cycle 2
Afridol Afridol
 
Agile methodology
Agile methodologyAgile methodology
Agile methodology
bipulpwc
 
02. testing throughout the software life cycle
02. testing throughout the software life cycle02. testing throughout the software life cycle
02. testing throughout the software life cycle
Tricia Karina
 
Static analysis and reliability testing (CS 5032 2012)
Static analysis and reliability testing (CS 5032 2012)Static analysis and reliability testing (CS 5032 2012)
Static analysis and reliability testing (CS 5032 2012)Ian Sommerville
 
Testing throughout the software life cycle
Testing throughout the software life cycleTesting throughout the software life cycle
Testing throughout the software life cycle
Emi Rizki Ayunanda
 
Requirements & system modelling for verification
Requirements & system modelling for verificationRequirements & system modelling for verification
Requirements & system modelling for verificationJohan Hoberg
 

Similar to Self adaptive biometric systems (20)

Bab ii testing throughout the software life cycle
Bab ii testing throughout the software life cycleBab ii testing throughout the software life cycle
Bab ii testing throughout the software life cycle
 
Software archiecture lecture05
Software archiecture   lecture05Software archiecture   lecture05
Software archiecture lecture05
 
Bab ii testing throughout the software life cycle (yoga)
Bab ii testing throughout the software life cycle (yoga)Bab ii testing throughout the software life cycle (yoga)
Bab ii testing throughout the software life cycle (yoga)
 
Chapter 2 Testing Throughout the Software Life Cycle
Chapter 2 Testing Throughout the Software Life CycleChapter 2 Testing Throughout the Software Life Cycle
Chapter 2 Testing Throughout the Software Life Cycle
 
Bab ii testing throughout the software life cycle
Bab ii testing throughout the software life cycleBab ii testing throughout the software life cycle
Bab ii testing throughout the software life cycle
 
Testing throughout the software life cycle
Testing throughout the software life cycleTesting throughout the software life cycle
Testing throughout the software life cycle
 
Using evolutionary testing to improve efficiency and quality
Using evolutionary testing to improve efficiency and qualityUsing evolutionary testing to improve efficiency and quality
Using evolutionary testing to improve efficiency and quality
 
Examen de ingles
Examen de inglesExamen de ingles
Examen de ingles
 
Practical Testing Definition for Mobile Devices
Practical Testing Definition for Mobile DevicesPractical Testing Definition for Mobile Devices
Practical Testing Definition for Mobile Devices
 
Testing the Untestable: Model Testing of Complex Software-Intensive Systems
Testing the Untestable: Model Testing of Complex Software-Intensive SystemsTesting the Untestable: Model Testing of Complex Software-Intensive Systems
Testing the Untestable: Model Testing of Complex Software-Intensive Systems
 
Testing throughout the software life cycle
Testing throughout the software life cycleTesting throughout the software life cycle
Testing throughout the software life cycle
 
Basic Engineering Design (Part 6): Test and Evaluate
Basic Engineering Design (Part 6): Test and EvaluateBasic Engineering Design (Part 6): Test and Evaluate
Basic Engineering Design (Part 6): Test and Evaluate
 
Testing throughout the software life cycle - Testing & Implementation
Testing throughout the software life cycle - Testing & ImplementationTesting throughout the software life cycle - Testing & Implementation
Testing throughout the software life cycle - Testing & Implementation
 
Testing throughout the software life cycle 2
Testing throughout the software life cycle 2Testing throughout the software life cycle 2
Testing throughout the software life cycle 2
 
Agile methodology
Agile methodologyAgile methodology
Agile methodology
 
4.6 Evaluation
4.6 Evaluation4.6 Evaluation
4.6 Evaluation
 
02. testing throughout the software life cycle
02. testing throughout the software life cycle02. testing throughout the software life cycle
02. testing throughout the software life cycle
 
Static analysis and reliability testing (CS 5032 2012)
Static analysis and reliability testing (CS 5032 2012)Static analysis and reliability testing (CS 5032 2012)
Static analysis and reliability testing (CS 5032 2012)
 
Testing throughout the software life cycle
Testing throughout the software life cycleTesting throughout the software life cycle
Testing throughout the software life cycle
 
Requirements & system modelling for verification
Requirements & system modelling for verificationRequirements & system modelling for verification
Requirements & system modelling for verification
 

Recently uploaded

Model Attribute Check Company Auto Property
Model Attribute  Check Company Auto PropertyModel Attribute  Check Company Auto Property
Model Attribute Check Company Auto Property
Celine George
 
1.4 modern child centered education - mahatma gandhi-2.pptx
1.4 modern child centered education - mahatma gandhi-2.pptx1.4 modern child centered education - mahatma gandhi-2.pptx
1.4 modern child centered education - mahatma gandhi-2.pptx
JosvitaDsouza2
 
Home assignment II on Spectroscopy 2024 Answers.pdf
Home assignment II on Spectroscopy 2024 Answers.pdfHome assignment II on Spectroscopy 2024 Answers.pdf
Home assignment II on Spectroscopy 2024 Answers.pdf
Tamralipta Mahavidyalaya
 
Unit 8 - Information and Communication Technology (Paper I).pdf
Unit 8 - Information and Communication Technology (Paper I).pdfUnit 8 - Information and Communication Technology (Paper I).pdf
Unit 8 - Information and Communication Technology (Paper I).pdf
Thiyagu K
 
Synthetic Fiber Construction in lab .pptx
Synthetic Fiber Construction in lab .pptxSynthetic Fiber Construction in lab .pptx
Synthetic Fiber Construction in lab .pptx
Pavel ( NSTU)
 
Additional Benefits for Employee Website.pdf
Additional Benefits for Employee Website.pdfAdditional Benefits for Employee Website.pdf
Additional Benefits for Employee Website.pdf
joachimlavalley1
 
special B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdfspecial B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdf
Special education needs
 
Welcome to TechSoup New Member Orientation and Q&A (May 2024).pdf
Welcome to TechSoup   New Member Orientation and Q&A (May 2024).pdfWelcome to TechSoup   New Member Orientation and Q&A (May 2024).pdf
Welcome to TechSoup New Member Orientation and Q&A (May 2024).pdf
TechSoup
 
aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
siemaillard
 
The geography of Taylor Swift - some ideas
The geography of Taylor Swift - some ideasThe geography of Taylor Swift - some ideas
The geography of Taylor Swift - some ideas
GeoBlogs
 
How to Make a Field invisible in Odoo 17
How to Make a Field invisible in Odoo 17How to Make a Field invisible in Odoo 17
How to Make a Field invisible in Odoo 17
Celine George
 
Digital Tools and AI for Teaching Learning and Research
Digital Tools and AI for Teaching Learning and ResearchDigital Tools and AI for Teaching Learning and Research
Digital Tools and AI for Teaching Learning and Research
Vikramjit Singh
 
Introduction to AI for Nonprofits with Tapp Network
Introduction to AI for Nonprofits with Tapp NetworkIntroduction to AI for Nonprofits with Tapp Network
Introduction to AI for Nonprofits with Tapp Network
TechSoup
 
Guidance_and_Counselling.pdf B.Ed. 4th Semester
Guidance_and_Counselling.pdf B.Ed. 4th SemesterGuidance_and_Counselling.pdf B.Ed. 4th Semester
Guidance_and_Counselling.pdf B.Ed. 4th Semester
Atul Kumar Singh
 
CACJapan - GROUP Presentation 1- Wk 4.pdf
CACJapan - GROUP Presentation 1- Wk 4.pdfCACJapan - GROUP Presentation 1- Wk 4.pdf
CACJapan - GROUP Presentation 1- Wk 4.pdf
camakaiclarkmusic
 
Operation Blue Star - Saka Neela Tara
Operation Blue Star   -  Saka Neela TaraOperation Blue Star   -  Saka Neela Tara
Operation Blue Star - Saka Neela Tara
Balvir Singh
 
Embracing GenAI - A Strategic Imperative
Embracing GenAI - A Strategic ImperativeEmbracing GenAI - A Strategic Imperative
Embracing GenAI - A Strategic Imperative
Peter Windle
 
Language Across the Curriculm LAC B.Ed.
Language Across the  Curriculm LAC B.Ed.Language Across the  Curriculm LAC B.Ed.
Language Across the Curriculm LAC B.Ed.
Atul Kumar Singh
 
"Protectable subject matters, Protection in biotechnology, Protection of othe...
"Protectable subject matters, Protection in biotechnology, Protection of othe..."Protectable subject matters, Protection in biotechnology, Protection of othe...
"Protectable subject matters, Protection in biotechnology, Protection of othe...
SACHIN R KONDAGURI
 
A Strategic Approach: GenAI in Education
A Strategic Approach: GenAI in EducationA Strategic Approach: GenAI in Education
A Strategic Approach: GenAI in Education
Peter Windle
 

Recently uploaded (20)

Model Attribute Check Company Auto Property
Model Attribute  Check Company Auto PropertyModel Attribute  Check Company Auto Property
Model Attribute Check Company Auto Property
 
1.4 modern child centered education - mahatma gandhi-2.pptx
1.4 modern child centered education - mahatma gandhi-2.pptx1.4 modern child centered education - mahatma gandhi-2.pptx
1.4 modern child centered education - mahatma gandhi-2.pptx
 
Home assignment II on Spectroscopy 2024 Answers.pdf
Home assignment II on Spectroscopy 2024 Answers.pdfHome assignment II on Spectroscopy 2024 Answers.pdf
Home assignment II on Spectroscopy 2024 Answers.pdf
 
Unit 8 - Information and Communication Technology (Paper I).pdf
Unit 8 - Information and Communication Technology (Paper I).pdfUnit 8 - Information and Communication Technology (Paper I).pdf
Unit 8 - Information and Communication Technology (Paper I).pdf
 
Synthetic Fiber Construction in lab .pptx
Synthetic Fiber Construction in lab .pptxSynthetic Fiber Construction in lab .pptx
Synthetic Fiber Construction in lab .pptx
 
Additional Benefits for Employee Website.pdf
Additional Benefits for Employee Website.pdfAdditional Benefits for Employee Website.pdf
Additional Benefits for Employee Website.pdf
 
special B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdfspecial B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdf
 
Welcome to TechSoup New Member Orientation and Q&A (May 2024).pdf
Welcome to TechSoup   New Member Orientation and Q&A (May 2024).pdfWelcome to TechSoup   New Member Orientation and Q&A (May 2024).pdf
Welcome to TechSoup New Member Orientation and Q&A (May 2024).pdf
 
aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
 
The geography of Taylor Swift - some ideas
The geography of Taylor Swift - some ideasThe geography of Taylor Swift - some ideas
The geography of Taylor Swift - some ideas
 
How to Make a Field invisible in Odoo 17
How to Make a Field invisible in Odoo 17How to Make a Field invisible in Odoo 17
How to Make a Field invisible in Odoo 17
 
Digital Tools and AI for Teaching Learning and Research
Digital Tools and AI for Teaching Learning and ResearchDigital Tools and AI for Teaching Learning and Research
Digital Tools and AI for Teaching Learning and Research
 
Introduction to AI for Nonprofits with Tapp Network
Introduction to AI for Nonprofits with Tapp NetworkIntroduction to AI for Nonprofits with Tapp Network
Introduction to AI for Nonprofits with Tapp Network
 
Guidance_and_Counselling.pdf B.Ed. 4th Semester
Guidance_and_Counselling.pdf B.Ed. 4th SemesterGuidance_and_Counselling.pdf B.Ed. 4th Semester
Guidance_and_Counselling.pdf B.Ed. 4th Semester
 
CACJapan - GROUP Presentation 1- Wk 4.pdf
CACJapan - GROUP Presentation 1- Wk 4.pdfCACJapan - GROUP Presentation 1- Wk 4.pdf
CACJapan - GROUP Presentation 1- Wk 4.pdf
 
Operation Blue Star - Saka Neela Tara
Operation Blue Star   -  Saka Neela TaraOperation Blue Star   -  Saka Neela Tara
Operation Blue Star - Saka Neela Tara
 
Embracing GenAI - A Strategic Imperative
Embracing GenAI - A Strategic ImperativeEmbracing GenAI - A Strategic Imperative
Embracing GenAI - A Strategic Imperative
 
Language Across the Curriculm LAC B.Ed.
Language Across the  Curriculm LAC B.Ed.Language Across the  Curriculm LAC B.Ed.
Language Across the Curriculm LAC B.Ed.
 
"Protectable subject matters, Protection in biotechnology, Protection of othe...
"Protectable subject matters, Protection in biotechnology, Protection of othe..."Protectable subject matters, Protection in biotechnology, Protection of othe...
"Protectable subject matters, Protection in biotechnology, Protection of othe...
 
A Strategic Approach: GenAI in Education
A Strategic Approach: GenAI in EducationA Strategic Approach: GenAI in Education
A Strategic Approach: GenAI in Education
 

Self adaptive biometric systems

  • 1. Self Adaptive Systems: An Experimental Analysis of the Performance Over Time Ajita Rattani, Gian Luca Marcialis, Fabio Roli
  • 2. Biometric Verification Systems They operate in two distinct stages: Image is acquired for each user (gallery) in controlled environment 1) The enrolment stage (for instance ISO/ IEC FCD 19794-5 standard) 2) The verification stage. “Template” is created and identity labels assigned The performance of biometric systems degrades quickly when input images exhibit substantial variations compared to the enrolled “templates”  Some face examples showing intra-class variations in input data un- represented by enrolled template TEMPLATE QUERY IMAGES 2
  • 3. Initial Attempts to Increase Template Representativeness • Re-enrollment • Multibiometrics (Handbook of Multi-biometrics, 2006) • Virtual biometric template synthesis (pose correction, illumination correction, de-ageing transformations) (Wang et al. 2006, Geng et al. 2007) 3
  • 4. Recent Introduction- Template update Methods • Characteristics: – Adapt themselves to the intra-class variation of the input data. – Minimizing performance loss due to unrepresentative and outdated templates • Commonly adopted is self-adaptive systems. 4
  • 5. Self-Adaptive Systems • Highly confidently classified samples are used for adaptation • In order to avoid impostor introduction • Claimed to be robust against short and medium term intra- class variations
  • 6.
  • 7. State-of-the-art Reference Modality Impostor Database X. Jiang Finger No 100x8 and W. Ser 12x200 Roli et al Face No 100x8 Ryu et al. Finger No 41x100 Pavani et Face No 5 months al. Till date: No paper has shown the performance robustness over time Reason: Unavailability of large number of samples collected over a period of time, per user basis Assumption of absence of impostor No theoretical explanation of the functioning
  • 8. Contributions – This is the first study evaluating the performance of self-adaptive systems, on the input batch of samples as available over time – The conceptual explanation of the functioning of self-adaptive systems, supported by experimental validations – DIEE multimodal database has been explicitly collected for this aim, over a span of 1.5 years
  • 9. Conceptual representation A hypothetical diagram showing the The representational capability of each initial condition where the enrolled template in the updated set on template is shown with the help of star adaptation using samples 1, 2 and 3 and encircled in its representation region
  • 10. Contd... As a result overall genuine region In the real time environment impostor expands samples may also be present
  • 11. Experimental Validations • Dataset: DIEE Multimodal database – 49 subjects with 50 samples per subject acquired in five sessions with 10 samples per session – Acquired in a time span of 1.5 years – Containing temporal as well as other intra-class variations Example facial images taken from two different sessions for a randomnly choosen user
  • 12. Experimental Protocol • Training: 2 enrolled images per person from the batch b_1 • Updating: batches two to four • Performance evaluation:On updating using batch b_i performance is evaluated for batch b_i+1and EER_i computed
  • 13. Experiment #1 • Aim: to evaluate the performance of self adaptive systems over time • Assumption of absence of impostor’s access. • Updating threshold: 0.01 % FAR
  • 14. Results Performance enhancement and stability can be attained over time Performance of self-adaptive systems for index and thumbprint biometrics in comparison to baseline classifier
  • 15. At varying threshold conditions Large variation in the performance from one updating cycle to another as a result of representation region expansion significantly Performance of self-adaptive face recognition system at varying thresholds from stringent to relaxed for face biometrics
  • 16. Table: showing percentage of samples gradually added to the user’s gallery for face biometrics Threshold (%) Cycle 1 (%) Cycle 2 (%) Cycle 3 (%) Cycle 4 at % FAR 0.00001 % 31.17 21.60 19.75 19.36 0.00001 % 33.3 26.54 26.95 27.70 0.01 % 52.16 55.86 61.83 65.74 0.1 % 56.79 62.03 68.31 70.98 1% 60.8 68.51 73.66 75.30
  • 17. Further confirmation:- representation region expansion The scores obtained on fifth batch using the The scores obtained on fifth batch using the baseline matcher enrolled with two templates self-adaptive system updated using 1 to 4 from a random user for thumb biometric batches for a random user for thumb biometric
  • 18. Experiment #2 • Aim: is to evaluate the performance of self adaptive systems over time on the assumption of presence of impostor’s access. • Assumption: Presence of impostors, enabling the evaluation of impostor’s intrusion over time • Updating Threshold: 0.001 % FAR
  • 19. •Performance strongly suffers from the operation at stringent threshold •However, the stability can be obtained over time •Different biometrics show difference trend in performance improvement Performance of self adaptive thumb and index fingerprint system under the assumption of impostor presence
  • 20. Conclusions and Future work • Self-adaptive systems can result in performance enhancement and classifier’s stability over time • The obtained performance enhancement is very much dependent on the set updating threshold • Different biometric may show different performance trend over time. • The possibility of presence and updating due to impostor is a serious and open issue. • Future work will rely on further development of the conceptual behaviour and significant in-depth analysis of impostor’s effect over time.