real-time efficient parallel thermal and visual face recognition fusion

19
1 Real-Time Efficient Parallel Thermal and Visual Face Recognition Fusion 2009/12/24 陳陳陳

Upload: berget

Post on 06-Jan-2016

26 views

Category:

Documents


0 download

DESCRIPTION

Real-Time Efficient Parallel Thermal and Visual Face Recognition Fusion. 2009/12/24 陳冠宇. Outline. I ntroduction G abor F iltering F or F ace Recognition -Feature point calculation 、 selection 、 Feature vector generation -Similarity calculations - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

1

Real-Time Efficient Parallel Thermal and

Visual Face Recognition Fusion

2009/12/24

陳冠宇

Page 2: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

2

Outline

Introduction Gabor Filtering For Face Recognition

-Feature point calculation 、 selection 、 Feature vector generation

-Similarity calculations

Parallel Architecture For Face Recognition Limitations And Benefits Conclusions

Page 3: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

3

Introduction

Computer vision has long fascinated applications in psychology, neural science, computer science, and engineering.

A simple feature extraction algorithm may require thousands of basic operations per pixel.

As you can see, parallel computing is essential to solving such a problem.

Page 4: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

4

Introduction

This paper would discuss Task Parallel processing for fast face recognition system based on Gabor Filtering technique.

Page 5: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

5

Related work in Face Recognition

Images taken from visual band are formed due to

reflectance.

Recently, face recognition on thermal/infrared

spectrum has gained popularity because thermal

images are formed due to emission not reflection.

Page 6: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

6

Related work in Face Recognition

Some of the commonly used face recognition techniques are Principal Component Analysis (PCA) , Linear Discriminate Analysis (LDA) and Gabor Filtering technique.

Page 7: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

7

Gabor Filtering For Face Recognition 1.Feature point calculation

For point (X, Y), filter response denoted as

R is defined as

Page 8: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

8

Feature point calculation

Where σX and σY are the standard deviation of the Gaussian envelop along the x and y dimensions respectively.λ, θ and n are the wavelength, orientation and no oforientations respectively.

Page 9: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

9

2.Feature point selection

In a particular window of size SxT around

which the behavior or response of Gabor filter

kernel is maximum, as feature point.

Page 10: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

10

Feature point selection

Feature point located at any point can be evaluated as

Where Rj is the response of the image to the jth Gabor filter and C is any window.

Page 11: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

11

3.Feature vector generation

Feature vectors are generated at feature points as

discussed in previous sections. pth feature vector

of ith reference face is defined as:

Page 12: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

12

Decision Fusion Architectures

where Wv and WT denote weight factors for the matching scores of visual and thermal modules.

In this paper, Wv=WT=0.5

Page 13: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

13

Page 14: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

14

Parallel Architecture For Face Recognition

As same face recognition steps are repeated for

visual, thermal and fused image. So it is proposed

that three individual face recognition processes for

each data be carried out on different slave computers.

Page 15: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

15

Parallel Architecture For Face Recognition

Page 16: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

16

Limitations And Benefits

Complexity Resource Requirements Speedups Portability

Page 17: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

17

Conclusions

Page 18: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

18

Conclusions

This paper briefly described a parallel design

framework for efficient and real-time face

recognition system. It defines new frontiers for

fast and efficient recognition system.

With our design framework, the realtime performance

can be achieved on regular computers,such as those

found in a student cluster.

Page 19: Real-Time Efficient Parallel Thermal and  Visual Face Recognition Fusion

19

Thank you