ECE 533 Final Project SIMPLE FACE RECOGNITION IMPLEMENTATION

Goal § Demonstrate the feasibility of computer authentication using facial recognition algorithms

What is facial recognition? § Every person’s face has a set of unique characteristics

What is computer-based facial recognition? § Programming a computer to use an algorithm to

Facial recognition algorithms § Various computer algorithms exist that can be used to recognize

Eigenfaces § Computer is trained with several pictures of the same face § Eyes

Embedded HMM for Face Recognition Model- - Face ROI partition

Face recognition using Hidden Markov Models l One person – one HMM l Stage

Running the Programs § The distribution came with the directory “Face. Recognition. Cap” and

Face. Recognition. Cap § Quicktime Java program, that requires Quicktime 6. 1 and a

Face. Recognition § Face. Recognition is the actual face recognition engine. Type the following

Conclusion § Facial recognition software is a new, advanced replacement for text passwords §

Slides: 13

Download presentation

ECE 533 Final Project SIMPLE FACE RECOGNITION IMPLEMENTATION FOR COMPUTER AUTHENTICATION Josh Easton - Tin-Yau Lo

Goal § Demonstrate the feasibility of computer authentication using facial recognition algorithms

What is facial recognition? § Every person’s face has a set of unique characteristics § Some examples are: § Distance between eyes § Location and size of nose § Distance from forehead to chin § Humans are able to easily recognize a face

What is computer-based facial recognition? § Programming a computer to use an algorithm to detect if two faces match

Facial recognition algorithms § Various computer algorithms exist that can be used to recognize faces § Eigenface analysis (AKA Principal Component Analysis) § Hidden Markov Models

Eigenfaces § Computer is trained with several pictures of the same face § Eyes are used as reference point between pictures § Various Eigenvectors are calculated to create a signature of the face

Eigenfaces

Embedded HMM for Face Recognition Model- - Face ROI partition

Face recognition using Hidden Markov Models l One person – one HMM l Stage 1 – Train every HMM 1 … l Stage 2 – Recognition i n Pi - probability Choose max(Pi)

Running the Programs § The distribution came with the directory “Face. Recognition. Cap” and “Face. Recognition”.

Face. Recognition. Cap § Quicktime Java program, that requires Quicktime 6. 1 and a compatible camera that support Quicktime on Windows with a simple recompilation. § It runs out of the box on Mac OS X by doubleclicking the “Face. Recognition. Cap” Icon. Push “Power” to initialize the Firewire bus, and click “Take Snapshot” to produce a 320 x 240 greyscale image suitable for “Face. Recognition”. The resultant capture file is “test. jpg”

Face. Recognition § Face. Recognition is the actual face recognition engine. Type the following at the “Face. Recognition” directory : java Face. Recognition trainedimages testing. jpg § A sample running such as the following will be produced : kenneth% java Face. Recognition trainedimages testing. jpg Constructing face-spaces from trainedimages. . . Comparing testing. jpg. . . Most closly reseambling: 15. jpg with 2. 108734631580217 distance. kenneth%

Conclusion § Facial recognition software is a new, advanced replacement for text passwords § We can look forward to seeing more facial authentication systems in the future