Sie sind auf Seite 1von 11

FACE RECOGNITION USING PCA AND

NEURAL NETWORK MODEL

Submitted by
AADARSH KUMAR
(15MIS0374)
ABSTRACT

 Over the past few decades, face recognition has become a most used application in the
surveillance and in security. Recently face recognition is attracting much attention in the
society of network multimedia information access. Areas such as network security, content
indexing and retrieval, and video compression benefits from face recognition technology
because "people" are the center of attention in a lot of video.
 Network access control via face recognition not only makes hackers virtually impossible to
steal one's "password", but also increases the user-friendliness in human-computer
interaction. Face recognition is one of the most challenging aspect in the field of image
analysis because every person has different facial feature.
 For the applications of videophone and teleconferencing, the assistance of face
recognition also provides a more efficient coding scheme. Face recognition is one of the
most challenging aspect in the field of image analysis because every person has different
facial feature.
 Face detection and recognition is challenging due to the Wide variety of faces and the
complexity of noises and image backgrounds. One of the major limitations in visible light
face recognition is illumination dependency which is vary in outdoor and night vision
applications.
 Face recognition pipeline consists of four modules: face detection, face
alignment, face representation and face matching. Face detection is the first
step in any face recognition framework where the facial region is segmented
from its background before further processing. face alignment aims to detect
facial feature points. Accurate detection of these points is crucial to the
success of the later stages of the pipeline. Face representation is the most
important step in face recognition pipeline where the extraction of
distinguish feature vector for the person is required. This step is challenging
from low resolution face images.
EXISTING SYSTEM
 Facial Recognition
 In the last twenty years, the computer-based facial recognition field has expanded rapidly.
Several algorithms have been introduced and improved to the point where computers can
rival humans in accuracy of facial recognition. In order to develop our product, we need to
understand how we identify faces, and to understand and evaluate the different existing
facial recognition algorithms and examine existing applications of this technology.
 Sinha, Balas, Ostrovsky, and Russell outline nineteen basic results regarding human facial
recognition, including many of the methods that humans use to identify faces. They show that
the study of human processes involved in facial recognition and the artificial algorithms being
used for facial recognition systems are inseparably linked together.
 The human brain can recognize faces in 120 milliseconds (MS). In order to achieve a useful
system, the algorithm we choose must have near real-time feedback. Several real time
algorithms have been developed in recent years. Ross bev-8 eridge of the Colorado State
University evaluated the efficiency and accuracy of the algorithms, Principle Component
analysis, Linear discriminant analysis, Elastic Graph Matching and Bayesian
Intrapersonal/Extra personal Image difference Classifier.
 A study by Krishna, Little, Black, and Panchanathan also evaluated these
algorithms with respect to changes in illumination and pose. The LDA and PCA
algorithms were found to be superior. LDA was fastest while PCA was the most
accurate. Another algorithm recently developed is Luxands FaceSDK, a facial
recognition system that supports recognition for still images and real time
video streams.
PROPOSED METHOD
 In our proposed system there are several modules. We will discuss them one
by one.
1. Eigen face computation
This module is used to compute the face space used for face recognition. The
recognition is carried out in the face bundle object. But the preparation of
such objects requires doing lots of computation. The steps are
 Compute an average face.
 Build a covariance matrix.
 Compute eigen values and eigen vector.
 Select only sixteen largest eigen values and its corresponding eigen vectors
 Compute the faces using our eigen vectors.
 Compute eigenspace for our given images.
 Identification
This module does the functionality to take the image from the above module and it compares or searches with the
images there in database. If any image is matched then a success message is shown to the user.
 Creating Database
In this module the input images feature as templates were store in the database and these templates were used
for future identification
 Input image
In this Module the image of the subject will be taken using camera or from the store folder for verification and
validation. It also used for storing the image of subject in database.
 Train the Database
This module used to take the store templates from database to temporary memory or resister by this the system
will work fast.
 Pre-Processing of image
In this module it improves the image data that suppresses unwilling distortions or enhances some image features
important for further processing, although geometric transformations of images.
 Neural network
Neural network is very powerful technique used to predicting unknown and know data. It works for both linear
and non-linear dataset. Nodes are connected to each other and strength of connections is assigned a value based
on their strength: inhibition or excitation. In this we put the dataset in network and check the error rate.
 Decision or Result
In this module it will show the result by completing all the work.
ARCHITECTURE
ALGORITHM

 Step 1: Prepare the data-training set of faces.


 Step 2: Original faces transformed in to Eigenfaces.
 Step 3: Eigenfaces are calculated for each image of the training set and
stored in the set W.
 Step 4: Calculate the covariance matrix, eigenvectors And Eigen values of the
covariance matrix.
 Step 5: Select the Principal components.
 Step 6: Classification of image.
CONCLUSION

 In this we have seen different approach, algorithms, methods for face recognition
and for face recognition we used PCA and neural network techniques. This result
that that it the better technique compare to other. We can say that face
recognition system is better for user authentication.

Das könnte Ihnen auch gefallen