Face Verification With Local Sparse Representation

lovethreewayΤεχνίτη Νοημοσύνη και Ρομποτική

20 Οκτ 2013 (πριν από 3 χρόνια και 9 μήνες)

46 εμφανίσεις

Face Verification With Local Sparse
Representation

Abstract:

Human face recognition has drawn considerable attention from the
researchers in recent years.

An automatic face recognition system will find many
applications in areas such as human
-
computer interfaces, model
-
based video
coding and security control systems.


A
facial recognition system

is a
computer application

for
automatically
identifying

or
verifying

a
person

from a
digital im
age

or a
video
frame

from a
video

source.

It is typically used in
security systems
.

In this work I used EmguCV cross platform .Net wrapper to the OpenCV
image processing library and C# .Net, these library’s allow me capture and process
image of a capture device in real time. The main goal of this p
roject is show and
explains the easiest way how implement a face detector and recognizer in real time
for multiple persons using
Principal Component Analysis (PCA) with eigenface

for implement it in multiple fields.


I used mathematical and matricial techn
iques, these get the image in raster
mode(digital format) and then process and compare pixel by pixel using different
methods for obtain a faster and reliable results, obviously these results depend of
the machine use to process this due to the huge comput
ational power that these
algorithms, functions and routines requires, these are the most popular techniques
used for solve this modern problem


Existing System:

Neural network



Neural network is used to create the face database and recognize the face.A
separate network
is built

for each person. The input
face is projected onto
the eigenface space first and gets

a new descriptor.



Neural networks cannot be retrained. If you add dat
a later, this is almost
impossible to add to an existing network.
Handling of time series data in
neural networks is a very complicated.

They require a large diversity of
training for real
-
world operation.

FERET (face recognition technology)



2D recognition
is affected by changes in lighting, the person’s hair, the age,
and if the person wear glasses.






L
DA
Linear discriminant analysis



Over fitting

problem when performing facerecognition on a large face
dataset but with very few training face images available per class. The
Problem of Overfitting Data
-
Overfitting generally occurs when a model is
excessively complex, such as having too many paramete
rs relative to the
number of observations. In order to avoid overfitting, it is necessary to use
additional techniques


e.g.

cro
ss
-
validation, regularization,

pruning.


Proposed System
:




In Proposed System we used Principal Component Analysis (PCA) with
eigenface;

PCA is first applied to the data set to reduce its
dimensionality.Find bases which has high variance in data.



The
pruning

algorithm is a technique used in
digital image processing

based
on
mathematical morphology
. It is used as a complement to the
skeleton

and
thinning algorithms to remove unwanted parasitic components.



EmguCV Net wrapper to the OpenCV image processing library and C# .Net



Eigen faces for recognition” focused on detecting individual facial featu
res
and categorizing different faces by the position, size, and relationship of
these features.



PCA
-

do multiple comparisons and matches between a face detected and the
trained images stored in binary database for this reason And for improve the
accurate o
f recognition you should add several images of the same person in
different angles, positions and luminance conditions, this training do this
prototype solid and very accurate.


Advantages:



This system performs face recognition in real time and also uses

this
method along with motion cues to segment faces out of images by
discarding squares that are classified as non
-
face images.



Hardware Requirements



Processor




:

Pentium IV 2.4 GHz



H
ard

D
isk




:

80

GB



RAM





:

512

MB


Software Requirements



Operating system



:

Windows Xp3/
Windows 7




Front End






:

Visual Studio 2010



Programming

Language


:

C#.net