26
Dynamic Scalable Distributed Face Recognition System Security Framework by Konrad Rzeszutek B.S. University of New Orleans, 1999

Dynamic Scalable Distributed Face Recognition System Security Framework

  • Upload
    skah

  • View
    27

  • Download
    0

Embed Size (px)

DESCRIPTION

Dynamic Scalable Distributed Face Recognition System Security Framework. by Konrad Rzeszutek B.S. University of New Orleans, 1999. Overview. Purpose History of face recognition Problems Solution Apollo Components of Apollo Face recognition technology used Motion detection Future work. - PowerPoint PPT Presentation

Citation preview

Page 1: Dynamic Scalable Distributed Face Recognition System Security Framework

Dynamic Scalable Distributed Face Recognition System Security Framework

by Konrad Rzeszutek

B.S. University of New Orleans, 1999

Page 2: Dynamic Scalable Distributed Face Recognition System Security Framework

Overview

Purpose History of face recognition Problems Solution

Apollo Components of Apollo Face recognition technology used Motion detection

Future work

Page 3: Dynamic Scalable Distributed Face Recognition System Security Framework

Applications of face recognition Surveillance Systems Biomedical Systems (eye-

replacement) Military (anti-terrorist groups) Security (logon authorization) Autonomous vehicle navigation … many more

Page 4: Dynamic Scalable Distributed Face Recognition System Security Framework

History Sir Francis Galton (1888) – Automatic

method of classification of French prisoners. Called it mechanical selector.

Late 1960s started. In 1980 research picked up dramatically. Two branches of face recognition:

Geometric-features Template matching

Page 5: Dynamic Scalable Distributed Face Recognition System Security Framework

Geometric - profile Profile features.

8-100 control points

Six control points using B-spline

U.S. INS uses this one extensively.

Page 6: Dynamic Scalable Distributed Face Recognition System Security Framework

Geometric - frontal Frontal features

8-16 features Various distance

from right and left eye to nose, nose to chin, eye to eye, etc.

Nose width, chin radii, eyebrow thickness, etc

Page 7: Dynamic Scalable Distributed Face Recognition System Security Framework

Template matching Face images are

represented as vectors in an array (each image is identified as k)

Computations are carried on the model arrays resulting in hash values.

The matching image hash value is compared against the template images’ hash values.

Page 8: Dynamic Scalable Distributed Face Recognition System Security Framework

Template matching, part 2 The distance from

the training images hash value determines the match. Euclidian distance

mostly used.

Page 9: Dynamic Scalable Distributed Face Recognition System Security Framework

Principal Component Analysis Turk and Pentland

– Eigenface. Most simplest –

uses the whole image face as a template.

Variations of this use infrared images.

Page 10: Dynamic Scalable Distributed Face Recognition System Security Framework

Template matching .. more Isodensity line maps (brightness of

image viewed as height of the mountain; isodensity lines corresponds to contour lines of equal altitude).

Neural network – eye and mouth regions feed into multi-layer perception engine that carries of the classification

.. Other are mostly various combinations of these two branches of face-recognition technologies.

Page 11: Dynamic Scalable Distributed Face Recognition System Security Framework

Problems Work done on a very selective set

of face images, mostly: In upright position Lighting and background controlled Either in frontal or profile view Have no occlusions, facial hair Most test cases are white males

Page 12: Dynamic Scalable Distributed Face Recognition System Security Framework

Solution A distributed system capable of

handling large load of images, analyze them in near-real time, provide support for future enhancements and be scalable to the load. Separates the functionality of a security

system in three modules: recognition, notification, and replay.

Page 13: Dynamic Scalable Distributed Face Recognition System Security Framework

Apollo

Page 14: Dynamic Scalable Distributed Face Recognition System Security Framework

Components Ares - the thin-client providing

camera feed. Hermes – the police officer directing

traffic Demeter – the storage for later replay

of camera-feed Nemesis – the face recognition engine Mors – the notification event server

Page 15: Dynamic Scalable Distributed Face Recognition System Security Framework

Ares Passes the real-time camera feed

through a motion-detection engine. Transmits the feed to Nemesis for

face-recognition and Demeter for storage.

Uses Jini/RMI to localize required components.

Page 16: Dynamic Scalable Distributed Face Recognition System Security Framework

Hermes Collects information about load of

each components. Is queried for its knowledge

whenever a system in a pool requires another component.

Scalable – many of these system (Hermes) can coexist and provide the load information.

Page 17: Dynamic Scalable Distributed Face Recognition System Security Framework

Demeter Stores camera-feed for later replay

and for storing the camera-feed on a archive media (WORM).

Page 18: Dynamic Scalable Distributed Face Recognition System Security Framework

Nemesis Face recognition module. Uses

Eigenfaces technique to match images in near-real time.

Can be extended to use more algorithms and check image using many techniques.

If match found, an event is sent to Mors.

Page 19: Dynamic Scalable Distributed Face Recognition System Security Framework

Mors Receives events

which notify about a possible face match.

Centralized pool where humans can visually check results and carry out proper procedures.

Page 20: Dynamic Scalable Distributed Face Recognition System Security Framework

Face recognition - Nemesis Eigenfaces – algorithm finds the

PCA of faces, or eigenvectors of the covariance matrix. “Each eigenvalue can be thought as

an amount which, when subtracted from each diagonal matrix, makes the matrix singular. … Eigenvectors are characteristics vectors of the matrix” (from “Digital Image Processing by Castleman)

Page 21: Dynamic Scalable Distributed Face Recognition System Security Framework

Eigenvalues and Eigenvectors We are looking for (eigenvectors) and

(eigenvalues) defined as:

C =

Where C is our covariance matrix of the normalized face-vector =[1 2 … M ]

TM

nTnn M

C

1M1

1

Page 22: Dynamic Scalable Distributed Face Recognition System Security Framework

Weights After the computation of eigenvalues and

eigenvetors, we use M’ most significant eigenfaces (where each eigenface is the linear combination of eigenvalues and the face-image) to form a face subspace.

From the face subspace we calculate the weights (where T=[1 2 .. M’]) :

k= kT k = 1,2, …, M’

Page 23: Dynamic Scalable Distributed Face Recognition System Security Framework

Matching We use the calculated weights to

determine if the image is recognized. Usually we use Euclidian distance.

Page 24: Dynamic Scalable Distributed Face Recognition System Security Framework

Motion Detection Motion detection is used on the client

side – Ares. It saves bandwidth and saves only

frames that have content. Algorithm uses two threshold functions:

The first is used to accommodate for possible artifacts introduced by the camera.

Second determines the if there is motion depending on the count of “clusters” of pixels that changed.

Page 25: Dynamic Scalable Distributed Face Recognition System Security Framework

Motion Detection, .. more Red is the “cluster” count.

Page 26: Dynamic Scalable Distributed Face Recognition System Security Framework

Future work Use more face recognition technologies so

each can complement each other. Expand framework to include other

recognition technologies: iris, speech, etc. Improve motion detection engine. Face operations – automatically removing

background. Generate from one face a multitude of other

faces with different alternations – bear (or lack of it), long hair, etc to expand possibly match.