lie detection system using micro-expressions
DESCRIPTION
Lie Detection System Using Micro-Expressions. Nathan de la Cruz Supervisor: Mehrdad Ghaziasgar MENTORS: Dane Brown AND Diego Mushfieldt. A Quick Recap …. Background People are lied to constantly. Research has found: 31% of people admit to lying on their CV’s . - PowerPoint PPT PresentationTRANSCRIPT
NATHAN DE LA CRUZ
SUPERVISOR: MEHRDAD GHAZIASGAR
MENTORS: DANE BROWN AND DIEGO MUSHFIELDT
Lie Detection System Using Micro-Expressions
A Quick Recap …
Background People are lied to constantly. Research has found:
31% of people admit to lying on their CV’s.60% of people lie at least once during a 10 minute
conversation and on average tell 2 to 3 lies.
Proposed Solution Create an interactive system that will detect a lie
using micro-expressions.
Project Design and Development
• User Interface Specification (UIS)• High Level Design (HLD)• Low Level Design (LLD)• Prototype (Demo)
User Interface Specification
The user interface as seen by the User
User Interface Specification
User interacts with the system via a mouse
How the User Interface behaves
Project Design and Development
• User Interface Specification (UIS)• High Level Design (HLD)• Low Level Design (LLD)• Prototype (Demo)
High Level Design (HLD)
Input
Image Processing
Classification Output
Capture
EventButton
Capture
EventButton
High Level Design (HLD)
Input
Video feed
Capture Images
Capture Event Button
Image Processing
Crop face
Convert to greyscale
Convert to Local Binary
Pattern Image
Classification
Support Vector
Machine (SVM)
Output
Display Text in Window
Project Design and Development
• User Interface Specification (UIS)• High Level Design (HLD)• Low Level Design (LLD)• Prototype (Demo)
Low Level Design (LLD)
Input –Video Feed
Capture from camera:
cvCaptureFromCAM();
Low Level Design (LLD)
Get Consecutive frames
Capture frame:
cvQueryFrame();
Low Level Design (LLD)
User Clicks on Button
cvSetMouseCallback ( );
Low Level Design (LLD)
Image Processing Width of eye pair x Height of face
Detect Face:
face_cascade.detectMultiScale();
Detect eyes:
eyes_cascade.detectMultiScale();
Low Level Design (LLD)
Image Processing Color Image to Greyscale Image
cvCvtColor(CV_RGB2GRAY)
Low Level Design (LLD)
Local Binary Patterns
OUTPUT
Low Level Design (LLD)
Output Display output in window
cvShowImage (“window”);
OR
Project Design and Development
• User Interface Specification (UIS)• High Level Design (HLD)• Low Level Design (LLD)• Prototype (Demo)
Prototype (Demo)
In this Demo I will:
Detect 2 Macro-Expressions i.e. Anger And Happy Detect 2 Micro-Expressions That are associated with
lying and fall under the category of Anger i.e. Narrowed Lips And Furrowed Brow
References
1. Paul Ekman Group, LLC. 2013. Paul Ekman Group, LLC. [ONLINE] Available at: http://www.paulekman.com. [Accessed 27 May 2013].
2. Micro Expressions - Research, Theory & Lying | Human Behaviour, Forensic Psychology | Blifaloo.com. 2013. Micro Expressions - Research, Theory & Lying | Human Behaviour, Forensic Psychology | Blifaloo.com. [ONLINE] Available at: http://www.blifaloo.com/info/microexpressions.php. [Accessed 27 May 2013].
3. Paul Ekman, 2007. Emotions Revealed, Second Edition: Recognizing Faces and Feelings to Improve Communication and Emotional Life. 2nd Edition. Holt Paperbacks.
Project Plan
Goal Due date• Learn to use OpenCV functions/tools to manipulate
images and videos• Requirements Gathering
End of Term1 (Completed)
Design and Development• Creating User Interface Specification• Designing structure of code• Identifying 2 micro-expressions and 2 macro-expression
End of Term2 (Completed)
Implementation• Training SVM to identify more micro-expressions• Optimizing LBP by altering the smoothing function
End of Term3
Testing and Evaluating• Collect more training data for SVM• Collect more test data for SVM End of Term4