ABSTRACT
An Artificial Neural Network (ANN) is an information processing paradigm
that is inspired by the way biological nervous systems, such as the brain,
process information. The key element of this paradigm is the novel structure of
the information processing system. It is composed of a large number of highly
interconnected processing elements (neurons) working in unison to solve
specific problems. ANNs, like people, learn by example. An ANN is configured
for a specific application, such as pattern recognition or data classification,
through a learning process. Learning in biological systems involves adjustments
to the synaptic connections that exist between the neurons.
This project deals with
developing an artificial neuron and creating a neural network using Microsoft
Visual C#, make it learn using some algorithm to identify face patterns. A
retinally connected neural network examines small windows of an image, and
decides whether each window contains a face. This is basically a windows
application which once learnt detects faces on supplied pictures.
Existing
System
Currently,
in the market there is no software that runs on both PC and PDA/Smart phone
which can detect the face in a picture with very
minimal changes. If we take desktop level applications that detect the face, the applications are based on some comparison
algorithm which runs on some standard logic whose pattern matching capabilities
and success rates are fixed. If the software needs a fine tuning, the logic has
to be modified and the code needs to be rebuilt which is again expensive.
Proposed
System
Proposed system is an application which
detects face on a picture supplied based on the
concept of neural networks. As it's built in .Net, it can be run on both
PC and PDA/Smart phone with very minimal changes. Because of the neural network
based detection technique, the application's detection rate can be fine tuned
by effective learning.
Software Requirements:
o
Microsoft .Net framework 2.0
o
Microsoft C#.Net language
o
Microsoft Visual Studio 2005 IDE
o
Microsoft Windows 2000 SP4 or higher
Hardware Requirements:
§
P4 Processor
§
512 MB RAM
§
Secondary memory of 20 – 50 MB
No comments:
Post a Comment