Dynamic Hierarchical Bayesian Network for Arabic Handwritten Word Recognition

TL;DR

This paper introduces a dynamic hierarchical Bayesian network model for recognizing Arabic handwritten words, specifically Tunisian city names, by improving segmentation and feature extraction to enhance recognition accuracy.

Contribution

The work proposes a novel probabilistic graphical model combined with a segmentation method and invariant feature extraction for Arabic handwriting recognition.

Findings

Effective segmentation using vertical histogram smoothing

Invariant feature extraction with Zernike and HU moments

Promising recognition results on IFN / ENIT database

Abstract

This paper presents a new probabilistic graphical model used to model and recognize words representing the names of Tunisian cities. In fact, this work is based on a dynamic hierarchical Bayesian network. The aim is to find the best model of Arabic handwriting to reduce the complexity of the recognition process by permitting the partial recognition. Actually, we propose a segmentation of the word based on smoothing the vertical histogram projection using different width values to reduce the error of segmentation. Then, we extract the characteristics of each cell using the Zernike and HU moments, which are invariant to rotation, translation and scaling. Our approach is tested using the IFN / ENIT database, and the experiment results are very promising.