Optical character recognition in real environments using neural networks and k-nearest neighbor

Authors:
O. Matei;P. C. Pop;H. Vălean
Affiliations:
Dept. of Electrical Engineering, North University Center of Baia Mare, Technical University of Cluj-Napoca, Baia Mare, Romania 430083;Dept. of Mathematics and Computer Science, North University Center of Baia Mare, Technical University of Cluj-Napoca, Baia Mare, Romania 430122;Dept. of Automation, Technical University of Cluj-Napoca, Cluj-Napoca, Romania
Venue:
Applied Intelligence
Year:
2013

Citing 10
Cited 1

Handwritten digit recognition with a back-propagation network

Advances in neural information processing systems 2
Off-Line, Handwritten Numeral Recognition by Perturbation Method

IEEE Transactions on Pattern Analysis and Machine Intelligence
Representation and Recognition of Handwritten Digits Using Deformable Templates

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Connectionist Inductive Learning and Logic Programming System

Applied Intelligence
Scalable Techniques from Nonparametric Statistics for Real Time Robot Learning

Applied Intelligence
On the Performance of the HONG Network for Pattern Classification

IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 2 - Volume 2
A Grey-Based Nearest Neighbor Approach for Missing Attribute Value Prediction

Applied Intelligence
Handwritten digit recognition using k nearest-neighbor, radial-basis function, and backpropagation neural networks

Neural Computation
The Image Processing Handbook, Sixth Edition

The Image Processing Handbook, Sixth Edition
Learning with limited numerical precision using the cascade-correlation algorithm

IEEE Transactions on Neural Networks

An SVM-AdaBoost facial expression recognition system

Applied Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a novel process to optical character recognition (OCR) used in real environments, such as gas-meters and electricity-meters, where the quantity of noise is sometimes as large as the quantity of good signal. Our method combines two algorithms an artificial neural network on one hand, and the k-nearest neighbor as the confirmation algorithm. Our approach, unlike other OCR systems, it is based on the angles of the digits rather than on pixels. Some of the advantages of the proposed system are: insensitivity to the possible rotations of the digits, the possibility to work in different light and exposure conditions, the ability to deduct and use heuristics for character recognition. The experimental results point out that our method with moderate level of training epochs can produce a high accuracy of 99.3 % in recognizing the digits, proving that our system is very successful.