Welcome to Scribd, the world's digital library. Read, publish, and share books and documents. See more
Standard view
Full view
of .
0 of .
Results for:
P. 1
Pattern Recognition Using Neural Network (Project Proposal for Image Processing)

# Pattern Recognition Using Neural Network (Project Proposal for Image Processing)

Ratings: (0)|Views: 865|Likes:
My project proposal that i have submitted to my Image Processing teacher as partial fulfillment of Image Processing subject @ PMC.
My project proposal that i have submitted to my Image Processing teacher as partial fulfillment of Image Processing subject @ PMC.

### Availability:

Read on Scribd mobile: iPhone, iPad and Android.
See more
See less

11/27/2012

pdf

text

original

Tribhuvan University
Patan Multiple Campus

Department of Computer Science and Information TechnologyPatan Dhoka, Lalitpur, Nepal
Project Proposal
PATTERN RECOGNITION USING NEURAL NETWORK
(Digit Recognition)
In partial fulfillment of the Image Processing
Date: 4/10/2011

Submitted By:

Rosa Kiran Basukala

2

Abstract
An
Artificial Neural Network (ANN),
often just called a "neural network" (NN), isa mathematical model or computational model based on biological neural networks. It consistsof an interconnected group of artificial neurons and processes information using aconnectionist approach to computation. In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through thenetwork during the learning phase. In more practical terms neural networks are
non‐linear
statistical data modeling tools. They can be used to model complex relationships between inputs and outputs or to find patterns in data.A
Feed Forward Neural Network
is an artificial neural network where connections between theunits do not form a directed cycle. This is different from recurrent neural networks. Thefeed forward neural network was the first and arguably simplest type of artificial neuralnetwork devised. In this network, the information moves in only one direction, forward,from the input nodes, through the hidden nodes (if any) and to the output nodes. There are no cycles or loops in the network.The
Back Propagation Algorithm
is a common way of teaching artificial neural networkshow to perform a given task. It requires a teacher that knows, or can calculate, the desired output for any given input. It is most useful for
feed‐forward
networks. Back propagation algorithmlearns the weights for a multilayer network, given a network with a fixed set of units and interconnections. It employs gradient descendent rule to attempt to minimize the squared error between thenetwork output values and the target values for these outputs. [1]
Fig 1: Simple Neural Networks having 3 Layers (Input layer, hidden layer and output layer)
Problem considered in NN:
Pattern recognition has become much important and interesting application industry.
I’m
planning to apply Neural Network for recognizing characters, initially digits. My searchfrom internet and other materials made me feel that Neural Network would be a goodoption to recognize character.
I’m
much interested in learning
“How
Neural Network canbe applied to a particular problem domain (in this case
“Character

Recognition”)
and why NN is worth of
applying.”

3

Objectives
I propose to know the details of how the neural network can be applied for pattern recognition onimage processing. In this project work I will achieve the following two goals:1.

To know the working principle of an ANN for pattern recognition.2.

To know how the efficiency of pattern recognition can be improved using ANN.
The learning task here involves recognizing characters (digits considered in the beginning). Thetarget function is to classify the given character image to a particular digit set early as target.
Initial Input Encoding:
There should be a drawing panel where digits should be drawn and then can be used for eithertraining or test. These drawing should be converted into a matrix of size of 5 by 5 i.e 25 pixels.
Initial Output Encoding:
I will use 10 distinct output units since we need
to classify 10 digits [0,1,…,9], each of
whichcorrespond to one of the possible digits that might be considered.
Initial Network Structure:
To represent 25 matrix pixels I will use 25 input layer units and 10 outputs layer units for distinct
10 digits. For hidden layer, I’m
planning to start with four units as I think 3 will be enough to map8(2
3
) output, so 4 hidden units would be fine for 10 outputs units. I shall change the number of hidden layer units in case I feel it is required for better performance while testing the system.c) Target
0 0 1 1 10 0 0 0 10 0 0 0 10 0 0 0 10 0 0 1 10 0 0 0 10 0 0 0 10 0 0 0 10 0 0 0 10 0 0 0 1
Fig 2: a) Input Fig 2: a) Input

b) Converted Matrix

## Activity (5)

You've already reviewed this. Edit your review.