Face Detection Through Neural Analysis

[rakesh nath]

Face Detection Through Neural Analysis
Akhil G S, Gibu George
S4 Mechanical Engineering,
Muslim Association College Of Engineering, Venjaramoodu

[attachment=10143]

Abstract
The aim of this paper is to implement an effective system to locate upright frontal faces on monochromatic images
with use of a neural network-based classifier. In this paper, A new approach to reduce the computation time taken
by fast neural nets for the searching process is presented. The principle of divide and conquer strategy is applied
through image decomposition. Each image is divided into small in size sub - images and then each one is tested
separately using a fast neural network. Compared to conventional and fast neural networks, experimental results
show that a speed up ratio is achieved when applying this technique to locate human faces in automatically in
cluttered scenes. Furthermore, faster face detection is obtained by using parallel processing techniques to test the
resulted sub-images at the same time using the same number of fast neural networks. Moreover, the problem of sub
image centring and normalization in the Fourier space is solved

Introduction
An artificial neural network (ANN), also called a simulated
neural network (SNN) or commonly just neural network (NN)
is an interconnected group of artificial neurons that uses a
mathematical or computational model for information
processing based on a connectionist approach to computation.
A NN is a massively parallel distributed processing system
made up of highly interconnected neural computing elements.
It has the ability to learn and thereby acquire Knowledge and
make it available for use. The Neural Network is the imitation
of the Central nervous system

By applying Sobel masks on the given image the system
retrieves an appropriate edge image. Since at each iteration,
only 20x20 pixel faces are intended to be detected, the system
removes all edges that are quite large with the assumption that
they represent large objects which belong to the images
background or large faces which, would be detected at latter
iterations. Of course there exists the risk of removing objects
which are in fact faces, however experiments have shown that
this case just can be treated as an exception. By involving this
module the system avoids analysing all possible 20x20 pixel
windows at each location (pixel after pixel), what is a quite
time consuming task. The number of remained 20x20 pixel
windows needed to be individually analysed by the detector in
the latter steps is only about 20 percent of the whole.

Bootstrapping
Generating a training set for the SVM /neural network is a
challenging task because of the difficulty in placing
characteristic non-face images in a the training set. To get a
representative sample of face images is not much of a
problem; however, to Choose the right combination of non-
face images from the immensely large set of such images, is a
complicated task. For this purpose, after each training session,
non-faces incorrectly detected as faces are placed in the
training set for the next session. This bootstrap method
overcomes the problem of using a huge set of non face images
in the training set, many of which may not influence the
training. database and a database of Indian faces generated
here. In each image to be placed in the training set the eyes,
nose and left, right and centre of the mouth were marked.
With these markings, the face was transformed into a 20x20
window with the marked features at predetermined positions.
The training set was subsequently enhanced with
bootstrapping of scenery and false-detected images. To make
the system somewhat invariant to changes such as rotation of
the face random transformations (rotation by 15 degrees,
mirroring) were Initially, for negative samples, random
images were created and added to applied to images in the
training set. The last used training set (including
bootstrapping) had 8982 input vectors.
Multi-layer networks use a variety of learning techniques, 4
the most popular being back propagation. Here the output
values are compared with the correct answer to compute the
value of some predefined error-function. By various
techniques the error is then fed back through the network.
Using this information, the algorithm adjusts the weights of
each connection in order to reduce the value of the error
function by some small amount. After repeating this process
for a sufficiently large number of training cycles the network
will usually converge to some state where the error of the
calculations is small. In this case one says that the network has
learned a certain target function. To adjust weights properly
one applies a general method for non-linear optimization. task
that is called gradient descent. For this, the derivative of the
error function with respect to the network weights is
calculated and the eights are then changed such that the error
decreases (thus going downhill on the surface of the error
function). For this reason back-propagation can only be
applied on networks with differentiable activation functions.

Network Structure
This implementation is a crude version of the system
described in [rowley98]. Arbitration amongst multiple
networks and the size of the training set used was significantly
smaller and this is not implemented.
The neural network is a two-layer (one hidden, one output)
feed-forward network. There are 400 input neurons, 26 hidden
neurons and 1 output neurons. Each hidden neuron is not
connected to ALL the input neurons
Results For Standard Pictures Of
Other Species
Here we have shown some images of animal faces to see if
the network learnt to recognize faces in general (two eyes, a
nose and a mouth) or was able to detect something unique
about human faces. Do note that none of these animal faces
were in the training set. Some interesting results obtained
were: The application screenshots above) didn t draw
rectangle around the chimp, so it didn t think it was a face.
However, when inspected more closely, we say that this
chimp and some others too had a network output quite close
to 0.5 (the demarcating limit we used between a face and a
non face). This dog s face was detected by the network. The
region after all does have two eyes; the fur of the dog is dark n
the middle which makes it appear somewhat like a nose.
However, many other dog faces were categorically rejected by
the system.