SEGMENTATION AND RECOGNITION OF
HANDWRITTEN DIGIT NUMERAL STRING USING A
MULTI LAYER PERCEPTRON NEURAL NETWORKS
N. Rao, and D. Babu. International Journal on Foundations of Computer Science & Technology (IJFCST), 6 (1):
17(January 2016)
DOI: 10.5121/ijfcst.2016.6104
Abstract
In this paper, the use of Multi-Layer Perceptron (MLP) Neural Network model is proposed for recognizing
unconstrained offline handwritten Numeral strings. The Numeral strings are segmented and isolated
numerals are obtained using a connected component labeling (CCL) algorithm approach. The structural
part of the models has been modeled using a Multilayer Perceptron Neural Network. This paper also
presents a new technique to remove slope and slant from handwritten numeral string and to normalize the
size of text images and classify with supervised learning methods. Experimental results on a database of
102 numeral string patterns written by 3 different people show that a recognition rate of 99.7% is obtained
on independent digits contained in the numeral string of digits includes both the skewed and slant data.
%0 Journal Article
%1 noauthororeditor
%A Rao, N. Venkateswara
%A Babu, Dr. B. Raveendra
%D 2016
%J International Journal on Foundations of Computer Science & Technology (IJFCST)
%K Components Connected Extraction Feature Handwritten Labeling Multi-Layer Networks Neural Perceptron Segmentation recognition
%N 1
%P 17
%R 10.5121/ijfcst.2016.6104
%T SEGMENTATION AND RECOGNITION OF
HANDWRITTEN DIGIT NUMERAL STRING USING A
MULTI LAYER PERCEPTRON NEURAL NETWORKS
%U https://wireilla.com/papers/ijfcst/V6N1/6116ijfcst04.pdf
%V 6
%X In this paper, the use of Multi-Layer Perceptron (MLP) Neural Network model is proposed for recognizing
unconstrained offline handwritten Numeral strings. The Numeral strings are segmented and isolated
numerals are obtained using a connected component labeling (CCL) algorithm approach. The structural
part of the models has been modeled using a Multilayer Perceptron Neural Network. This paper also
presents a new technique to remove slope and slant from handwritten numeral string and to normalize the
size of text images and classify with supervised learning methods. Experimental results on a database of
102 numeral string patterns written by 3 different people show that a recognition rate of 99.7% is obtained
on independent digits contained in the numeral string of digits includes both the skewed and slant data.
@article{noauthororeditor,
abstract = {In this paper, the use of Multi-Layer Perceptron (MLP) Neural Network model is proposed for recognizing
unconstrained offline handwritten Numeral strings. The Numeral strings are segmented and isolated
numerals are obtained using a connected component labeling (CCL) algorithm approach. The structural
part of the models has been modeled using a Multilayer Perceptron Neural Network. This paper also
presents a new technique to remove slope and slant from handwritten numeral string and to normalize the
size of text images and classify with supervised learning methods. Experimental results on a database of
102 numeral string patterns written by 3 different people show that a recognition rate of 99.7% is obtained
on independent digits contained in the numeral string of digits includes both the skewed and slant data. },
added-at = {2023-01-18T14:14:38.000+0100},
author = {Rao, N. Venkateswara and Babu, Dr. B. Raveendra},
biburl = {https://www.bibsonomy.org/bibtex/27a4573f7af6ea44e9c2a2a515fd59840/devino},
doi = {10.5121/ijfcst.2016.6104},
interhash = {16a333d44cf2c4a26ab78c0d79c2cab7},
intrahash = {7a4573f7af6ea44e9c2a2a515fd59840},
issn = {1839-7662},
journal = {International Journal on Foundations of Computer Science & Technology (IJFCST)},
keywords = {Components Connected Extraction Feature Handwritten Labeling Multi-Layer Networks Neural Perceptron Segmentation recognition},
month = jan,
number = 1,
pages = 17,
timestamp = {2023-01-18T14:14:38.000+0100},
title = {SEGMENTATION AND RECOGNITION OF
HANDWRITTEN DIGIT NUMERAL STRING USING A
MULTI LAYER PERCEPTRON NEURAL NETWORKS},
url = {https://wireilla.com/papers/ijfcst/V6N1/6116ijfcst04.pdf},
volume = 6,
year = 2016
}