SlideShare a Scribd company logo
Rajesh Reddy N et al Int. Journal of Engineering Research and Applications
ISSN : 2248-9622, Vol. 4, Issue 1( Version 2), January 2014, pp.207-210

RESEARCH ARTICLE

www.ijera.com

OPEN ACCESS

Automated Image Segmentation And Characterization Technique
For Effective Isolation And Representation Of Human Face
*Rajesh Reddy N, *Mohana Vamshi Komandla, *Ganesh NVSL, **Nandhitha
N.M, **Logashanmugam E
*(IV Year, Department of ECE, Sathyabama University, Jeppiaar Nagar, Old Mamallapuram Road, Chennai
600 119, India)
** (Professor, Department of ECE, Sathyabama University, Jeppiaar Nagar, Old Mamallapuram Road, Chennai
600 119, India)

ABSTRACT
In areas such as defense and forensics, it is necessary to identify the face of the criminals from the already
available database. Automated face recognition system involves face isolation, feature extraction and
classification technique. Challenges in face recognition system are isolating the face effectively as it may be
affected by illumination, posture and variation in skin color. Hence it is necessary to develop an effective
algorithm that isolates face from the image. In this paper, advanced face isolation technique and feature
extraction technique has been proposed.
Keywords - Face, Erosion, YCbCr, DCT, Eigen Values and Eigen vectors.

I.

INTRODUCTION

With the computerization of defense,
forensics, and surveillance departments, the paradigm
has shifted to automatic face recognition system.
However as it is a real time system and is affected by
illumination, pose and noise, it is necessary to isolate
face from the image. After isolating the face, it is
necessary to extract unique features that could
distinguish each face from the other. Once these
features are determined, then using an appropriate
classifier, face can be recognized. Though
considerable research is already carried out in this
area, identifying the face itself is a major challenge. In
the proposed approach, an automatic face isolation
system is developed using morphological operators to
perform face isolation and feature extraction.
This paper is organized as follows: Section II
describes the related work. Section III provides the
methodology used in the proposed work. Section IV
describes the results and discussion. Section V
concludes the work.

II.

RELATED WORK

Wadkar and Wankhade (2012) proposed the
use of Haar Wavelet Transform on the test images to
perform averaging and differencing process. Biorthogonal filters of lengths 9 and 7 and a superset of
9/7 pair is used for face recognition. Euclidean
distance method is used to identify the distance
between query image and the database image. The
results were tested on an ORL database.
Madiafi and Bouroumi (2012) proposed a
neuro fuzzy based robust face recognition system
www.ijera.com

which uses Fuzzy based competitive rules for training
the Kohonen Self Organizing map based classifier. A
set of 200 images each of individuals where each
individual is represented by a sample of 10 images is
taken in the dataset in bmp format with a resolution of
180X200. The proposed approach worked well for
even an untrained dataset.
M.Meenakshi (2012) used Discrete Cosine
Transform (DCT) and Principal Component Analysis
(PCA) for automatic face recognition. PCA includes
two phases, training and testing phases where weights
of each image are found and classification of one
image from other is done respectively. The neural
networks are trained using the features obtained from
training set. Then PCA analysis is done by comparing
mean image with reconstructed image.
Prasanna and Hegde (2013) proposed a
method for recognizing the faces with varied pose and
illumination through Active Appearance Model
(AAM) and lazy classification. The proposed model
comprises of two stages; developing a feature library
and recognition stage. AAM is used for manual
intervention in developing the feature library to extract
the shape and appearance models. The recognition
process includes lazy classification. This lazy
classification does not require training and the
proposed method was tested for various factors like
accuracy, sensitivity, False Positive Rate (FPR),
Positive Predictive Value (PPV), Negative Predictive
Value (NPV), False Discovery Rate (FDR) and
Mathew correlation coefficients. The results were
better compared to conventional methods.

207 | P a g e
Rajesh Reddy N et al Int. Journal of Engineering Research and Applications
ISSN : 2248-9622, Vol. 4, Issue 1( Version 2), January 2014, pp.207-210
Tayal et.al. (2012) proposed a novel method of face
recognition system based on color segmentation. Skin
color and the segmentation of the skin region in a
group picture are observed to be a robust cue for the
face recognition and tracking systems. This method is
invariant of the size of the face and its orientation. The
HSV (hue, saturation and value) color model is used
in the detection and the segmentation of the skin
regions in a random picture. For regions classified as
faces, it uses the height and width of the region to
draw a rectangular box with the region’s centroid as
its centre. The algorithm is tested are random images
taken in uncontrolled conditions and the efficiency of
the face detection was found to be 73.68%.

III.

www.ijera.com

RGB input image

Convert RGB to
grayscale image
format

Convert RGB to YCbCr
image format
Perform lightening
compensation taking Y
component
Extract the Skin Region
taking Cr component

Methodology

Initially a database is created with images of
20 persons and is stored in ‘.jpeg’ format. The spatial
resolution of the images is 413X531 with 8 bits used
for representing each pixel. Initially lighting
compensation and skin region detection is performed.
Then the following steps are involved in order to
isolate the face from the image; Erosion is performed
to remove the undesirable regions similar to the skin
region with diamond as the structuring element of size
3. For every row, the columns with white pixels are
identified and are stored in an array for identifying the
face region. Also the number of white pixels in each
row is counted and is stored in an array. From the gray
scale image all the pixels corresponding to the above
identified columns are retained, by zeroing the
remaining pixels. However the neck of the person is
also visible in the output image. Hence it is necessary
to remove that region.
In order to perform that, the row
corresponding to maximum count is identified and n
rows above and below that. In order to represent the
features, Eigen values are calculated and the
corresponding Eigen vectors are also determined. The
flowchart of the proposed work is shown in Fig.1.

www.ijera.com

Noise Removal and
Erosion
Match the grayscale
values for the eroded
image
Detected face region
Fig.1: Flowchart for the proposed work

IV.

Results and discussion

The set of input images used in the proposed
work are shown in Figure 2. These color images are
then converted into grayscale images as in Figure 3.
The color images are then converted to YCbCr and the
luminance component is used to perform lighting
compensation which is represented in Figure 4. Skin
region is found by taking the chrominance component
values the corresponding output images are shown in
Figure 5. Unwanted noise elements are removed and
the corresponding output images are shown in Figures
6 and 7 respectively. Corresponding face images are
shown in Figure 8 and the final output images without
neck region are shown in Figure 9. Features extracted
from the isolated images by determining the Eigen
values. Mean and standard deviation are calculated for
approximation, horizontal and vertical co-efficients
are tabulated in Table 1. From table 1 it is clear that
every face has a unique Eigen value.

208 | P a g e
Rajesh Reddy N et al Int. Journal of Engineering Research and Applications
ISSN : 2248-9622, Vol. 4, Issue 1( Version 2), January 2014, pp.207-210

www.ijera.com

Fig.2: RGB color images

Fig.5: Skin Region

Fig.3: Grayscale image

Fig.6: Noise Removed from the skin region

Fig.4: Lighting Compensation

Fig.7: Performing Erosion
www.ijera.com

209 | P a g e
Rajesh Reddy N et al Int. Journal of Engineering Research and Applications
ISSN : 2248-9622, Vol. 4, Issue 1( Version 2), January 2014, pp.207-210
V.

www.ijera.com
Conclusion

In this paper an effective image processing
based technique for detecting face from the input
image has been proposed successfully. It works well
on all the test images irrespective of skin color and
background. However the proposed technique
involves morphological image processing operators
which indeed are dependent on the shape and size of
the structuring element. Also in certain cases a small
portion of the neck region is present. Hence in future
the algorithm has to be modified so that the neck
region is removed. This paper ends with describing the
face image using Eigen values. In future face
recognition system has to be developed with Eigen
values and other descriptors as input parameters.

REFERENCES
[1]
Fig.8: Face Region

[2]

[3]

[4]

[5]
Fig.9: Final face image
Table 1: Eigen values and statistical parameters for
face image
I Max. Approxim
Horizontal
Vertical
m Eige
ation
coefficients coefficients
a
n
coefficient
g valu
s
e
e
Me Std. Mean Std. Mean Std.
an
1 92.6 0.8 0.0 0.001 0.0 0.000 0.0
7
00
86
7
16
4
26
2 111. 0.0 0.0
0.0 0.000 0.0
9
82
63 0.001 12
4
25
5
3 74.8 0.6 0.0
0.0
0.0
1
92
76 0.001 11 0.000 19
4
6
4 84.1 0.7 0.0 0.002 0.0 0.000 0.0
9
46
02
0
18
1
23

www.ijera.com

Mahesh Prasanna K, Nagaratna Hegde, A
Fast Recognition Method for Pose and
Illumination Variant Faces on Video
Sequences, IOSR Journal of Computer
Engineering (IOSR-JCE), Volume 10, Issue
1, 2013.
Pallavi D.Wadkar, Megha Wankhade, Face
Recognition Using Discrete Wavelet
Transform, IJAET, Vol. III, Issue I, JanuaryMarch, 2012.
Mohammed Madiafi, A Neuro-Fuzzy
Approach for Automatic Face Recognition,
Applied Mathematical Sciences, Vol. 6, 2012.
M.Meenakshi, Real-Time Facial Recognition
System—Design,
Implementation
and
Validation, Journal of Signal Processing
Theory and Applications 2013 1: 1-18.
Yogesh Tayal, Ruchika Lamba, Subhransu
Padhee, Automatic Face Detection Using
Color Based Segmentation, International
Journal of Scientific and Research
Publications, Volume 2, Issue 6, June 2012.

210 | P a g e

More Related Content

What's hot

A Novel Mathematical Based Method for Generating Virtual Samples from a Front...
A Novel Mathematical Based Method for Generating Virtual Samples from a Front...A Novel Mathematical Based Method for Generating Virtual Samples from a Front...
A Novel Mathematical Based Method for Generating Virtual Samples from a Front...
CSCJournals
 
Face detection for video summary using enhancement based fusion strategy
Face detection for video summary using enhancement based fusion strategyFace detection for video summary using enhancement based fusion strategy
Face detection for video summary using enhancement based fusion strategy
eSAT Publishing House
 
Face Detection in Digital Image: A Technical Review
Face Detection in Digital Image: A Technical ReviewFace Detection in Digital Image: A Technical Review
Face Detection in Digital Image: A Technical Review
IJERA Editor
 
A novel approach for performance parameter estimation of face recognition bas...
A novel approach for performance parameter estimation of face recognition bas...A novel approach for performance parameter estimation of face recognition bas...
A novel approach for performance parameter estimation of face recognition bas...
IJMER
 
A FACE RECOGNITION USING LINEAR-DIAGONAL BINARY GRAPH PATTERN FEATURE EXTRACT...
A FACE RECOGNITION USING LINEAR-DIAGONAL BINARY GRAPH PATTERN FEATURE EXTRACT...A FACE RECOGNITION USING LINEAR-DIAGONAL BINARY GRAPH PATTERN FEATURE EXTRACT...
A FACE RECOGNITION USING LINEAR-DIAGONAL BINARY GRAPH PATTERN FEATURE EXTRACT...
ijfcstjournal
 
Ck36515520
Ck36515520Ck36515520
Ck36515520
IJERA Editor
 
IRJET - Facial Recognition based Attendance System with LBPH
IRJET -  	  Facial Recognition based Attendance System with LBPHIRJET -  	  Facial Recognition based Attendance System with LBPH
IRJET - Facial Recognition based Attendance System with LBPH
IRJET Journal
 
2. 7698 8113-1-pb
2. 7698 8113-1-pb2. 7698 8113-1-pb
2. 7698 8113-1-pb
IAESIJEECS
 
Implementation of Face Recognition in Cloud Vision Using Eigen Faces
Implementation of Face Recognition in Cloud Vision Using Eigen FacesImplementation of Face Recognition in Cloud Vision Using Eigen Faces
Implementation of Face Recognition in Cloud Vision Using Eigen Faces
IJERA Editor
 
LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...
LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...
LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...
csijjournal
 
Skin segmentation using different integrated color model approaches for face ...
Skin segmentation using different integrated color model approaches for face ...Skin segmentation using different integrated color model approaches for face ...
Skin segmentation using different integrated color model approaches for face ...
eSAT Publishing House
 
50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...
50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...
50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...
idescitation
 
Independent Component Analysis of Edge Information for Face Recognition
Independent Component Analysis of Edge Information for Face RecognitionIndependent Component Analysis of Edge Information for Face Recognition
Independent Component Analysis of Edge Information for Face Recognition
CSCJournals
 
Data Mining Based Skin Pixel Detection Applied On Human Images: A Study Paper
Data Mining Based Skin Pixel Detection Applied On Human Images: A Study PaperData Mining Based Skin Pixel Detection Applied On Human Images: A Study Paper
Data Mining Based Skin Pixel Detection Applied On Human Images: A Study Paper
IJERA Editor
 
MSB based Face Recognition Using Compression and Dual Matching Techniques
MSB based Face Recognition Using Compression and Dual Matching TechniquesMSB based Face Recognition Using Compression and Dual Matching Techniques
MSB based Face Recognition Using Compression and Dual Matching Techniques
CSCJournals
 
EV-SIFT - An Extended Scale Invariant Face Recognition for Plastic Surgery Fa...
EV-SIFT - An Extended Scale Invariant Face Recognition for Plastic Surgery Fa...EV-SIFT - An Extended Scale Invariant Face Recognition for Plastic Surgery Fa...
EV-SIFT - An Extended Scale Invariant Face Recognition for Plastic Surgery Fa...
IJECEIAES
 
Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...
Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...
Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...
inventionjournals
 
FPGA ARCHITECTURE FOR FACIAL-FEATURES AND COMPONENTS EXTRACTION
FPGA ARCHITECTURE FOR FACIAL-FEATURES AND COMPONENTS EXTRACTIONFPGA ARCHITECTURE FOR FACIAL-FEATURES AND COMPONENTS EXTRACTION
FPGA ARCHITECTURE FOR FACIAL-FEATURES AND COMPONENTS EXTRACTION
ijcseit
 

What's hot (18)

A Novel Mathematical Based Method for Generating Virtual Samples from a Front...
A Novel Mathematical Based Method for Generating Virtual Samples from a Front...A Novel Mathematical Based Method for Generating Virtual Samples from a Front...
A Novel Mathematical Based Method for Generating Virtual Samples from a Front...
 
Face detection for video summary using enhancement based fusion strategy
Face detection for video summary using enhancement based fusion strategyFace detection for video summary using enhancement based fusion strategy
Face detection for video summary using enhancement based fusion strategy
 
Face Detection in Digital Image: A Technical Review
Face Detection in Digital Image: A Technical ReviewFace Detection in Digital Image: A Technical Review
Face Detection in Digital Image: A Technical Review
 
A novel approach for performance parameter estimation of face recognition bas...
A novel approach for performance parameter estimation of face recognition bas...A novel approach for performance parameter estimation of face recognition bas...
A novel approach for performance parameter estimation of face recognition bas...
 
A FACE RECOGNITION USING LINEAR-DIAGONAL BINARY GRAPH PATTERN FEATURE EXTRACT...
A FACE RECOGNITION USING LINEAR-DIAGONAL BINARY GRAPH PATTERN FEATURE EXTRACT...A FACE RECOGNITION USING LINEAR-DIAGONAL BINARY GRAPH PATTERN FEATURE EXTRACT...
A FACE RECOGNITION USING LINEAR-DIAGONAL BINARY GRAPH PATTERN FEATURE EXTRACT...
 
Ck36515520
Ck36515520Ck36515520
Ck36515520
 
IRJET - Facial Recognition based Attendance System with LBPH
IRJET -  	  Facial Recognition based Attendance System with LBPHIRJET -  	  Facial Recognition based Attendance System with LBPH
IRJET - Facial Recognition based Attendance System with LBPH
 
2. 7698 8113-1-pb
2. 7698 8113-1-pb2. 7698 8113-1-pb
2. 7698 8113-1-pb
 
Implementation of Face Recognition in Cloud Vision Using Eigen Faces
Implementation of Face Recognition in Cloud Vision Using Eigen FacesImplementation of Face Recognition in Cloud Vision Using Eigen Faces
Implementation of Face Recognition in Cloud Vision Using Eigen Faces
 
LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...
LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...
LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETE...
 
Skin segmentation using different integrated color model approaches for face ...
Skin segmentation using different integrated color model approaches for face ...Skin segmentation using different integrated color model approaches for face ...
Skin segmentation using different integrated color model approaches for face ...
 
50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...
50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...
50Combining Color Spaces for Human Skin Detection in Color Images using Skin ...
 
Independent Component Analysis of Edge Information for Face Recognition
Independent Component Analysis of Edge Information for Face RecognitionIndependent Component Analysis of Edge Information for Face Recognition
Independent Component Analysis of Edge Information for Face Recognition
 
Data Mining Based Skin Pixel Detection Applied On Human Images: A Study Paper
Data Mining Based Skin Pixel Detection Applied On Human Images: A Study PaperData Mining Based Skin Pixel Detection Applied On Human Images: A Study Paper
Data Mining Based Skin Pixel Detection Applied On Human Images: A Study Paper
 
MSB based Face Recognition Using Compression and Dual Matching Techniques
MSB based Face Recognition Using Compression and Dual Matching TechniquesMSB based Face Recognition Using Compression and Dual Matching Techniques
MSB based Face Recognition Using Compression and Dual Matching Techniques
 
EV-SIFT - An Extended Scale Invariant Face Recognition for Plastic Surgery Fa...
EV-SIFT - An Extended Scale Invariant Face Recognition for Plastic Surgery Fa...EV-SIFT - An Extended Scale Invariant Face Recognition for Plastic Surgery Fa...
EV-SIFT - An Extended Scale Invariant Face Recognition for Plastic Surgery Fa...
 
Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...
Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...
Face Recognition System Using Local Ternary Pattern and Signed Number Multipl...
 
FPGA ARCHITECTURE FOR FACIAL-FEATURES AND COMPONENTS EXTRACTION
FPGA ARCHITECTURE FOR FACIAL-FEATURES AND COMPONENTS EXTRACTIONFPGA ARCHITECTURE FOR FACIAL-FEATURES AND COMPONENTS EXTRACTION
FPGA ARCHITECTURE FOR FACIAL-FEATURES AND COMPONENTS EXTRACTION
 

Similar to Aa4102207210

A study of techniques for facial detection and expression classification
A study of techniques for facial detection and expression classificationA study of techniques for facial detection and expression classification
A study of techniques for facial detection and expression classification
IJCSES Journal
 
Lc3420022006
Lc3420022006Lc3420022006
Lc3420022006
IJERA Editor
 
Face Recognition based on STWT and DTCWT using two dimensional Q-shift Filters
Face Recognition based on STWT and DTCWT using two dimensional Q-shift Filters Face Recognition based on STWT and DTCWT using two dimensional Q-shift Filters
Face Recognition based on STWT and DTCWT using two dimensional Q-shift Filters
IJERA Editor
 
International Journal of Computer Science, Engineering and Information Techno...
International Journal of Computer Science, Engineering and Information Techno...International Journal of Computer Science, Engineering and Information Techno...
International Journal of Computer Science, Engineering and Information Techno...
IJCSEIT Journal
 
Model Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point CloudsModel Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point Clouds
Lakshmi Sarvani Videla
 
Critical evaluation of frontal image based gender classification techniques
Critical evaluation of frontal image based gender classification techniquesCritical evaluation of frontal image based gender classification techniques
Critical evaluation of frontal image based gender classification techniques
Salam Shah
 
Volume 2-issue-6-2108-2113
Volume 2-issue-6-2108-2113Volume 2-issue-6-2108-2113
Volume 2-issue-6-2108-2113Editor IJARCET
 
Facial expression recongnition Techniques, Database and Classifiers
Facial expression recongnition Techniques, Database and Classifiers Facial expression recongnition Techniques, Database and Classifiers
Facial expression recongnition Techniques, Database and Classifiers Rupinder Saini
 
IRJET- Prediction of Facial Attribute without Landmark Information
IRJET-  	  Prediction of Facial Attribute without Landmark InformationIRJET-  	  Prediction of Facial Attribute without Landmark Information
IRJET- Prediction of Facial Attribute without Landmark Information
IRJET Journal
 
Extracted features based multi-class classification of orthodontic images
Extracted features based multi-class classification of orthodontic images Extracted features based multi-class classification of orthodontic images
Extracted features based multi-class classification of orthodontic images
IJECEIAES
 
COMPRESSION BASED FACE RECOGNITION USING TRANSFORM DOMAIN FEATURES FUSED AT M...
COMPRESSION BASED FACE RECOGNITION USING TRANSFORM DOMAIN FEATURES FUSED AT M...COMPRESSION BASED FACE RECOGNITION USING TRANSFORM DOMAIN FEATURES FUSED AT M...
COMPRESSION BASED FACE RECOGNITION USING TRANSFORM DOMAIN FEATURES FUSED AT M...
sipij
 
IRJET-Facial Expression Recognition using Efficient LBP and CNN
IRJET-Facial Expression Recognition using Efficient LBP and CNNIRJET-Facial Expression Recognition using Efficient LBP and CNN
IRJET-Facial Expression Recognition using Efficient LBP and CNN
IRJET Journal
 
IRJET- A Review on Various Techniques for Face Detection
IRJET- A Review on Various Techniques for Face DetectionIRJET- A Review on Various Techniques for Face Detection
IRJET- A Review on Various Techniques for Face Detection
IRJET Journal
 
Multi modal face recognition using block based curvelet features
Multi modal face recognition using block based curvelet featuresMulti modal face recognition using block based curvelet features
Multi modal face recognition using block based curvelet features
ijcga
 
Multimodal Approach for Face Recognition using 3D-2D Face Feature Fusion
Multimodal Approach for Face Recognition using 3D-2D Face Feature FusionMultimodal Approach for Face Recognition using 3D-2D Face Feature Fusion
Multimodal Approach for Face Recognition using 3D-2D Face Feature Fusion
CSCJournals
 
Region based elimination of noise pixels towards optimized classifier models ...
Region based elimination of noise pixels towards optimized classifier models ...Region based elimination of noise pixels towards optimized classifier models ...
Region based elimination of noise pixels towards optimized classifier models ...
IJERA Editor
 
Face Recognition Using Gabor features And PCA
Face Recognition Using Gabor features And PCAFace Recognition Using Gabor features And PCA
Face Recognition Using Gabor features And PCA
IOSR Journals
 
ZERNIKE MOMENT-BASED FEATURE EXTRACTION FOR FACIAL RECOGNITION OF IDENTICAL T...
ZERNIKE MOMENT-BASED FEATURE EXTRACTION FOR FACIAL RECOGNITION OF IDENTICAL T...ZERNIKE MOMENT-BASED FEATURE EXTRACTION FOR FACIAL RECOGNITION OF IDENTICAL T...
ZERNIKE MOMENT-BASED FEATURE EXTRACTION FOR FACIAL RECOGNITION OF IDENTICAL T...
ijcseit
 
IRJET - A Review on Face Recognition using Deep Learning Algorithm
IRJET -  	  A Review on Face Recognition using Deep Learning AlgorithmIRJET -  	  A Review on Face Recognition using Deep Learning Algorithm
IRJET - A Review on Face Recognition using Deep Learning Algorithm
IRJET Journal
 
Fourier mellin transform based face recognition
Fourier mellin transform based face recognitionFourier mellin transform based face recognition
Fourier mellin transform based face recognitioniaemedu
 

Similar to Aa4102207210 (20)

A study of techniques for facial detection and expression classification
A study of techniques for facial detection and expression classificationA study of techniques for facial detection and expression classification
A study of techniques for facial detection and expression classification
 
Lc3420022006
Lc3420022006Lc3420022006
Lc3420022006
 
Face Recognition based on STWT and DTCWT using two dimensional Q-shift Filters
Face Recognition based on STWT and DTCWT using two dimensional Q-shift Filters Face Recognition based on STWT and DTCWT using two dimensional Q-shift Filters
Face Recognition based on STWT and DTCWT using two dimensional Q-shift Filters
 
International Journal of Computer Science, Engineering and Information Techno...
International Journal of Computer Science, Engineering and Information Techno...International Journal of Computer Science, Engineering and Information Techno...
International Journal of Computer Science, Engineering and Information Techno...
 
Model Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point CloudsModel Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point Clouds
 
Critical evaluation of frontal image based gender classification techniques
Critical evaluation of frontal image based gender classification techniquesCritical evaluation of frontal image based gender classification techniques
Critical evaluation of frontal image based gender classification techniques
 
Volume 2-issue-6-2108-2113
Volume 2-issue-6-2108-2113Volume 2-issue-6-2108-2113
Volume 2-issue-6-2108-2113
 
Facial expression recongnition Techniques, Database and Classifiers
Facial expression recongnition Techniques, Database and Classifiers Facial expression recongnition Techniques, Database and Classifiers
Facial expression recongnition Techniques, Database and Classifiers
 
IRJET- Prediction of Facial Attribute without Landmark Information
IRJET-  	  Prediction of Facial Attribute without Landmark InformationIRJET-  	  Prediction of Facial Attribute without Landmark Information
IRJET- Prediction of Facial Attribute without Landmark Information
 
Extracted features based multi-class classification of orthodontic images
Extracted features based multi-class classification of orthodontic images Extracted features based multi-class classification of orthodontic images
Extracted features based multi-class classification of orthodontic images
 
COMPRESSION BASED FACE RECOGNITION USING TRANSFORM DOMAIN FEATURES FUSED AT M...
COMPRESSION BASED FACE RECOGNITION USING TRANSFORM DOMAIN FEATURES FUSED AT M...COMPRESSION BASED FACE RECOGNITION USING TRANSFORM DOMAIN FEATURES FUSED AT M...
COMPRESSION BASED FACE RECOGNITION USING TRANSFORM DOMAIN FEATURES FUSED AT M...
 
IRJET-Facial Expression Recognition using Efficient LBP and CNN
IRJET-Facial Expression Recognition using Efficient LBP and CNNIRJET-Facial Expression Recognition using Efficient LBP and CNN
IRJET-Facial Expression Recognition using Efficient LBP and CNN
 
IRJET- A Review on Various Techniques for Face Detection
IRJET- A Review on Various Techniques for Face DetectionIRJET- A Review on Various Techniques for Face Detection
IRJET- A Review on Various Techniques for Face Detection
 
Multi modal face recognition using block based curvelet features
Multi modal face recognition using block based curvelet featuresMulti modal face recognition using block based curvelet features
Multi modal face recognition using block based curvelet features
 
Multimodal Approach for Face Recognition using 3D-2D Face Feature Fusion
Multimodal Approach for Face Recognition using 3D-2D Face Feature FusionMultimodal Approach for Face Recognition using 3D-2D Face Feature Fusion
Multimodal Approach for Face Recognition using 3D-2D Face Feature Fusion
 
Region based elimination of noise pixels towards optimized classifier models ...
Region based elimination of noise pixels towards optimized classifier models ...Region based elimination of noise pixels towards optimized classifier models ...
Region based elimination of noise pixels towards optimized classifier models ...
 
Face Recognition Using Gabor features And PCA
Face Recognition Using Gabor features And PCAFace Recognition Using Gabor features And PCA
Face Recognition Using Gabor features And PCA
 
ZERNIKE MOMENT-BASED FEATURE EXTRACTION FOR FACIAL RECOGNITION OF IDENTICAL T...
ZERNIKE MOMENT-BASED FEATURE EXTRACTION FOR FACIAL RECOGNITION OF IDENTICAL T...ZERNIKE MOMENT-BASED FEATURE EXTRACTION FOR FACIAL RECOGNITION OF IDENTICAL T...
ZERNIKE MOMENT-BASED FEATURE EXTRACTION FOR FACIAL RECOGNITION OF IDENTICAL T...
 
IRJET - A Review on Face Recognition using Deep Learning Algorithm
IRJET -  	  A Review on Face Recognition using Deep Learning AlgorithmIRJET -  	  A Review on Face Recognition using Deep Learning Algorithm
IRJET - A Review on Face Recognition using Deep Learning Algorithm
 
Fourier mellin transform based face recognition
Fourier mellin transform based face recognitionFourier mellin transform based face recognition
Fourier mellin transform based face recognition
 

Recently uploaded

Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
Alan Dix
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Jeffrey Haguewood
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Thierry Lestable
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Tobias Schneck
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
BookNet Canada
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
DianaGray10
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptxIOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
Abida Shariff
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
Cheryl Hung
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Inflectra
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
Product School
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
DanBrown980551
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
Product School
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Product School
 

Recently uploaded (20)

Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptxIOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
 

Aa4102207210

  • 1. Rajesh Reddy N et al Int. Journal of Engineering Research and Applications ISSN : 2248-9622, Vol. 4, Issue 1( Version 2), January 2014, pp.207-210 RESEARCH ARTICLE www.ijera.com OPEN ACCESS Automated Image Segmentation And Characterization Technique For Effective Isolation And Representation Of Human Face *Rajesh Reddy N, *Mohana Vamshi Komandla, *Ganesh NVSL, **Nandhitha N.M, **Logashanmugam E *(IV Year, Department of ECE, Sathyabama University, Jeppiaar Nagar, Old Mamallapuram Road, Chennai 600 119, India) ** (Professor, Department of ECE, Sathyabama University, Jeppiaar Nagar, Old Mamallapuram Road, Chennai 600 119, India) ABSTRACT In areas such as defense and forensics, it is necessary to identify the face of the criminals from the already available database. Automated face recognition system involves face isolation, feature extraction and classification technique. Challenges in face recognition system are isolating the face effectively as it may be affected by illumination, posture and variation in skin color. Hence it is necessary to develop an effective algorithm that isolates face from the image. In this paper, advanced face isolation technique and feature extraction technique has been proposed. Keywords - Face, Erosion, YCbCr, DCT, Eigen Values and Eigen vectors. I. INTRODUCTION With the computerization of defense, forensics, and surveillance departments, the paradigm has shifted to automatic face recognition system. However as it is a real time system and is affected by illumination, pose and noise, it is necessary to isolate face from the image. After isolating the face, it is necessary to extract unique features that could distinguish each face from the other. Once these features are determined, then using an appropriate classifier, face can be recognized. Though considerable research is already carried out in this area, identifying the face itself is a major challenge. In the proposed approach, an automatic face isolation system is developed using morphological operators to perform face isolation and feature extraction. This paper is organized as follows: Section II describes the related work. Section III provides the methodology used in the proposed work. Section IV describes the results and discussion. Section V concludes the work. II. RELATED WORK Wadkar and Wankhade (2012) proposed the use of Haar Wavelet Transform on the test images to perform averaging and differencing process. Biorthogonal filters of lengths 9 and 7 and a superset of 9/7 pair is used for face recognition. Euclidean distance method is used to identify the distance between query image and the database image. The results were tested on an ORL database. Madiafi and Bouroumi (2012) proposed a neuro fuzzy based robust face recognition system www.ijera.com which uses Fuzzy based competitive rules for training the Kohonen Self Organizing map based classifier. A set of 200 images each of individuals where each individual is represented by a sample of 10 images is taken in the dataset in bmp format with a resolution of 180X200. The proposed approach worked well for even an untrained dataset. M.Meenakshi (2012) used Discrete Cosine Transform (DCT) and Principal Component Analysis (PCA) for automatic face recognition. PCA includes two phases, training and testing phases where weights of each image are found and classification of one image from other is done respectively. The neural networks are trained using the features obtained from training set. Then PCA analysis is done by comparing mean image with reconstructed image. Prasanna and Hegde (2013) proposed a method for recognizing the faces with varied pose and illumination through Active Appearance Model (AAM) and lazy classification. The proposed model comprises of two stages; developing a feature library and recognition stage. AAM is used for manual intervention in developing the feature library to extract the shape and appearance models. The recognition process includes lazy classification. This lazy classification does not require training and the proposed method was tested for various factors like accuracy, sensitivity, False Positive Rate (FPR), Positive Predictive Value (PPV), Negative Predictive Value (NPV), False Discovery Rate (FDR) and Mathew correlation coefficients. The results were better compared to conventional methods. 207 | P a g e
  • 2. Rajesh Reddy N et al Int. Journal of Engineering Research and Applications ISSN : 2248-9622, Vol. 4, Issue 1( Version 2), January 2014, pp.207-210 Tayal et.al. (2012) proposed a novel method of face recognition system based on color segmentation. Skin color and the segmentation of the skin region in a group picture are observed to be a robust cue for the face recognition and tracking systems. This method is invariant of the size of the face and its orientation. The HSV (hue, saturation and value) color model is used in the detection and the segmentation of the skin regions in a random picture. For regions classified as faces, it uses the height and width of the region to draw a rectangular box with the region’s centroid as its centre. The algorithm is tested are random images taken in uncontrolled conditions and the efficiency of the face detection was found to be 73.68%. III. www.ijera.com RGB input image Convert RGB to grayscale image format Convert RGB to YCbCr image format Perform lightening compensation taking Y component Extract the Skin Region taking Cr component Methodology Initially a database is created with images of 20 persons and is stored in ‘.jpeg’ format. The spatial resolution of the images is 413X531 with 8 bits used for representing each pixel. Initially lighting compensation and skin region detection is performed. Then the following steps are involved in order to isolate the face from the image; Erosion is performed to remove the undesirable regions similar to the skin region with diamond as the structuring element of size 3. For every row, the columns with white pixels are identified and are stored in an array for identifying the face region. Also the number of white pixels in each row is counted and is stored in an array. From the gray scale image all the pixels corresponding to the above identified columns are retained, by zeroing the remaining pixels. However the neck of the person is also visible in the output image. Hence it is necessary to remove that region. In order to perform that, the row corresponding to maximum count is identified and n rows above and below that. In order to represent the features, Eigen values are calculated and the corresponding Eigen vectors are also determined. The flowchart of the proposed work is shown in Fig.1. www.ijera.com Noise Removal and Erosion Match the grayscale values for the eroded image Detected face region Fig.1: Flowchart for the proposed work IV. Results and discussion The set of input images used in the proposed work are shown in Figure 2. These color images are then converted into grayscale images as in Figure 3. The color images are then converted to YCbCr and the luminance component is used to perform lighting compensation which is represented in Figure 4. Skin region is found by taking the chrominance component values the corresponding output images are shown in Figure 5. Unwanted noise elements are removed and the corresponding output images are shown in Figures 6 and 7 respectively. Corresponding face images are shown in Figure 8 and the final output images without neck region are shown in Figure 9. Features extracted from the isolated images by determining the Eigen values. Mean and standard deviation are calculated for approximation, horizontal and vertical co-efficients are tabulated in Table 1. From table 1 it is clear that every face has a unique Eigen value. 208 | P a g e
  • 3. Rajesh Reddy N et al Int. Journal of Engineering Research and Applications ISSN : 2248-9622, Vol. 4, Issue 1( Version 2), January 2014, pp.207-210 www.ijera.com Fig.2: RGB color images Fig.5: Skin Region Fig.3: Grayscale image Fig.6: Noise Removed from the skin region Fig.4: Lighting Compensation Fig.7: Performing Erosion www.ijera.com 209 | P a g e
  • 4. Rajesh Reddy N et al Int. Journal of Engineering Research and Applications ISSN : 2248-9622, Vol. 4, Issue 1( Version 2), January 2014, pp.207-210 V. www.ijera.com Conclusion In this paper an effective image processing based technique for detecting face from the input image has been proposed successfully. It works well on all the test images irrespective of skin color and background. However the proposed technique involves morphological image processing operators which indeed are dependent on the shape and size of the structuring element. Also in certain cases a small portion of the neck region is present. Hence in future the algorithm has to be modified so that the neck region is removed. This paper ends with describing the face image using Eigen values. In future face recognition system has to be developed with Eigen values and other descriptors as input parameters. REFERENCES [1] Fig.8: Face Region [2] [3] [4] [5] Fig.9: Final face image Table 1: Eigen values and statistical parameters for face image I Max. Approxim Horizontal Vertical m Eige ation coefficients coefficients a n coefficient g valu s e e Me Std. Mean Std. Mean Std. an 1 92.6 0.8 0.0 0.001 0.0 0.000 0.0 7 00 86 7 16 4 26 2 111. 0.0 0.0 0.0 0.000 0.0 9 82 63 0.001 12 4 25 5 3 74.8 0.6 0.0 0.0 0.0 1 92 76 0.001 11 0.000 19 4 6 4 84.1 0.7 0.0 0.002 0.0 0.000 0.0 9 46 02 0 18 1 23 www.ijera.com Mahesh Prasanna K, Nagaratna Hegde, A Fast Recognition Method for Pose and Illumination Variant Faces on Video Sequences, IOSR Journal of Computer Engineering (IOSR-JCE), Volume 10, Issue 1, 2013. Pallavi D.Wadkar, Megha Wankhade, Face Recognition Using Discrete Wavelet Transform, IJAET, Vol. III, Issue I, JanuaryMarch, 2012. Mohammed Madiafi, A Neuro-Fuzzy Approach for Automatic Face Recognition, Applied Mathematical Sciences, Vol. 6, 2012. M.Meenakshi, Real-Time Facial Recognition System—Design, Implementation and Validation, Journal of Signal Processing Theory and Applications 2013 1: 1-18. Yogesh Tayal, Ruchika Lamba, Subhransu Padhee, Automatic Face Detection Using Color Based Segmentation, International Journal of Scientific and Research Publications, Volume 2, Issue 6, June 2012. 210 | P a g e