TITLE

Arabic Character Recognition using Artificial Neural Networks and Statistical Analysis

AUTHOR(S)
Sarhan, Ahmad M.; Al Helalat, Omar I.
PUB. DATE
May 2007
SOURCE
Proceedings of World Academy of Science: Engineering & Technolog;2007, Vol. 21, p32
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
In this paper, an Arabic letter recognition system based on Artificial Neural Networks (ANNs) and statistical analysis for feature extraction is presented. The ANN is trained using the Least Mean Squares (LMS) algorithm. In the proposed system, each typed Arabic letter is represented by a matrix of binary numbers that are used as input to a simple feature extraction system whose output, in addition to the input matrix, are fed to an ANN. Simulation results are provided and show that the proposed system always produces a lower Mean Squared Error (MSE) and higher success rates than the current ANN solutions.
ACCESSION #
27981858

Tags: PATTERN recognition systems;  NEURAL networks (Computer science);  STATISTICS;  BACK propagation (Artificial intelligence);  GAUSSIAN processes;  STANDARD deviations

 

Related Articles

  • Application of artificial neural network in estimating monthly time series reference evapotranspiration with minimum and maximum temperatures. Jahanbani, Heerbod; El-Shafie, Ahmed Hussein // Paddy & Water Environment;Jun2011, Vol. 9 Issue 2, p207 

    There are various methods for computing reference evapotranspiration (ET) using meteorological data. However, such models tend to perform well for predicting ET close to the mean, but do not keep accurate performance with extreme observations. It is recognized that the Penman-Monteith (PM) model...

  • A Robust Method for Object Classification Based on Back-Propagation Neural Networks. Vasilescu, Bogdan // Petroleum - Gas University of Ploiesti Bulletin, Technical Serie;2009, Vol. 61 Issue 3, p371 

    This paper will introduce the principles of training multi-layer perceptron neural networks and the application of such a topology to simple-object classification. The neural network is trained with the feed-forward Back-Propagation Network (BPN) algorithm. Finally, the paper presents the...

  • Off-Line Hand Written Character Recognition Using Radial Basis Function. ASHOK, J.; RAJAN, E. G. // International Journal of Advanced Networking & Applications;Jan/Feb2011, Vol. 2 Issue 4, p792 

    Handwriting has continued to persist as a means of communication and recording information in day-to-day life even with the introduction of new technologies. Given its ubiquity in human transactions, machine recognition of handwriting has practical significance, as in reading handwritten notes...

  • The build of a dynamic classifier selection ICBP system and its application to pattern recognition. Qun Dai // Neural Computing & Applications;Feb2010, Vol. 19 Issue 1, p123 

    In neural network ensemble, the diversity of its constitutive component networks is a crucial factor to boost its generalization performance. In terms of how each ensemble system solves the problem, we can roughly categorize the existing ensemble mechanism into two groups: data-driven and...

  • Distortion Analysis Of Tamil Language Characters Recognition. N, Gowri.; Bhaskaran, R. // International Journal of Computer Science Issues (IJCSI);Jan2011, Vol. 8 Issue 1, p390 

    This research work demonstrates how character recognition can be done with a back propagation network and shows how to implement this using the MATLAB Neural Network toolbox. This is a slightly enhanced version of the character recognition application based on the MATLAB Neural Network toolbox....

  • FREEMAN CODE BASED ONLINE HANDWRITTEN CHARACTER RECOGNITION FOR MALAYALAM USING BACKPROPAGATION NEURAL NETWORKS. Sampath, Amritha; C., Tripti; V., Govindaru // Advanced Computing;Jul2012, Vol. 3 Issue 4, p51 

    Handwritten character recognition is conversion of handwritten text to machine readable and editable form. Online character recognition deals with live conversion of characters. Malayalam is a language spoken by millions of people in the state of Kerala and the union territories of Lakshadweep...

  • AN APPROACH FOR IRIS PLANT CLASSIFICATION USING NEURAL NETWORK. Swain, Madhusmita; Dash, Sanjit Kumar; Dash, Sweta; Mohapatra, Ayeskanta // International Journal on Soft Computing;Feb2012, Vol. 3 Issue 1, p79 

    Classification is a machine learning technique used to predict group membership for data instances. To simplify the problem of classification neural networks are being introduced. This paper focuses on IRIS plant classification using Neural Network. The problem concerns the identification of...

  • Exploring Optimal Architecture of Multi-layered Feed- forward (MLFNN) as Bidirectional Associative Memory (BAM) for Function Approximation. Singh, Manisha; Kumar, Somesh // International Journal of Computer Applications;Aug2013, Vol. 76 Issue 1-16, p28 

    Function approximation is an instance of supervised learning which is one of the most studied topics in machine learning, artificial neural networks, pattern recognition, and statistical curve fitting. In principle, any of the methods studied in these fields can be used in reinforcement...

  • Character Recognition Based on BP Artificial Neural Network. Bin xiao; Weilin Peng // International Proceedings of Computer Science & Information Tech;2012, Vol. 52, p373 

    This paper provides a character recognition system based on the Back Propagation artificial neural network that is simplified. Trained with samples of the characters, the characters are recognized, using with VC++. Recognition rate reaches 96%, which meets the design requirement.

Share

Read the Article

Courtesy of VIRGINIA BEACH PUBLIC LIBRARY AND SYSTEM

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics