25-04-2012, 11:13 AM
Handwritten Character Recognition using Neural Network
researchpaper_Handwritten_Character_Recognition_Using_Neural_Network.pdf (Size: 110.3 KB / Downloads: 123)
INTRODUCTION
such software’s are useful when we want to convert
our Hard copies into soft copies. Such software’s reduces
almost 80% of the conversion work while still
some verification is always required.
Optical character recognition, usually abbreviated to
OCR, involves computer software designed to translate
images of typewritten text (usually captured by a scanner)
into machine-editable text, or to translate pictures of
characters into a standard encoding scheme representing
them in (ASCII or Unicode). OCR began as a field of research
in artificial intelligence and machine vision.
Though academic research in the field continues, the focus
on OCR has shifted to implementation of proven
techniques [4].
ARTIFICIAL NUERAL NETWORK
Pattern recognition is extremely difficult to automate.
Animals recognize various objects and make sense out of
large amount of visual information, apparently requiring
very little effort. Simulating the task performed by animals
to recognize to the extent allowed by physical limitations
will be enormously profitable for the system. This
necessitates study and simulation of Artificial Neural
Network.
Backpropogation
Backpropagation was created by generalizing the Widrow-
Hoff learning rule to multiple-layer networks and
nonlinear differentiable transfer functions. Input vectors
and the corresponding target vectors are used to train a
network until it can approximate a function, associate
input vectors with specific output vectors, or classify input
vectors in an appropriate way as defined by you.
Networks with biases, a sigmoid layer, and a linear output
layer are capable of approximating any function with
a finite number of discontinuities.
ANALYSIS
By analyzing the OCR we have found some parameter
which affects the accuracy of OCR system [1][5]. The parameters
listed in these papers are skewing, slanting,
thickening, cursive handwriting, joint characters. If all
these parameters are taken care in the preprocessing
phase then overall accuracy of the Neural Network
would increase.
DESIGN AND IMPLEMENTATION
Initially we are making the Algorithm of Character Extraction.
We are using MATLAB as tool for implementing
the algorithm. Then we design neural network, we need
to have a Neural Network that would give the optimum
results [2]. There is no specific way of finding the correct
model of Neural Network. It could only be found by trial
and error method. Take different models of Neural Network,
train it and note the output accuracy.
There are basically two main phases in our Paper:
Preprocessing and Character Recognition .
NUERAL NETWORK DESIGN
For training and simulating purposes we have scanned
certain documents. We have 2 types of documents train
documents and test documents. The train documents are
the images of the documents which we want to use for
training. Similarly test documents are the images of documents
which we want to use for test. According to the characters
in the documents we train the neural network and
apply the test documents.
CONCLUSION
The backpropagation neural network discussed and implemented
in this paper can also be used for almost any
general image recognition applications such as face detection
and fingerprint detection. The implementation of the
fully connected backpropagation network gave reasonable
results toward recognizing characters.
The most notable is the fact that it cannot handle major
variations in translation, rotation, or scale. While a few
pre-processing steps can be implemented in order to account
for these variances, as we did. In general they are
difficult to solve completely.