Word recognition system using neural networks

Authors:
H. Y. Y. Sanossian
Affiliations:
Computer Science Department, Mu'tah University, P.O. Box 7, Jordan
Venue:
Highly parallel computaions
Year:
2001

Citing 14
Cited 0

Neural Nets for Adaptive Filtering and Adaptive Pattern Recognition

Computer
On Image Analysis by the Methods of Moments

IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural network positioning and classification of handwritten characters

Neural Networks
On Image Analysis by Moments

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Survey of Methods and Strategies in Character Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Handprinted Character Recognition Based on Spatial Topology Distance Measurement

IEEE Transactions on Pattern Analysis and Machine Intelligence
Orthogonal Moment Features for Use With Parametric and Non-Parametric Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Lexicon Driven Approach to Handwritten Word Recognition for Real-Time Applications

IEEE Transactions on Pattern Analysis and Machine Intelligence
A hierarchical artificial neural network architecture for English character recognition

Neural, Parallel & Scientific Computations
Ligature Modeling for Online Cursive Script Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Character Recognition Without Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning to See Where and What: Training a Net to Make Saccades and Recognize Handwritten Characters

Advances in Neural Information Processing Systems 5, [NIPS Conference]
ID3-derived fuzzy rules and optimized defuzzification for handwritten numeral recognition

IEEE Transactions on Fuzzy Systems
Rotation-invariant neural pattern recognition system estimating a rotation angle

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this chapter we discuss some of the methods used for word recognition. In general, word recognition systems are divided into three stages, segmentation, feature extraction and classification. We also present a technique for Arabic word recognition. Printed and handwritten Arabic words are mainly cursive. A segmentation technique is used taking into consideration the characteristic of the Arabic characters. Once a word is segmented, each subimage is passed through a feature extraction stage where the topological information is extracted and used for classification. The classification stage is performed using a set of neural networks. A feedback from the outcome of the neural networks to the segmentation stage occurs when a character is rejected. The technique is tested on printed Arabic characters.