Home
This Title All WIREs
WIREs RSS Feed
How to cite this WIREs title:
WIREs Data Mining Knowl Discov
Impact Factor: 1.939

Trained convolutional neural network based on selected beta filters for Arabic letter recognition

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

This paper presents a fast deep learning approach to segment and recognize off‐line Arabic printed and handwritten letters from words. We proposed a simple and powerful algorithm for Arabic letter segmentation based on vertical profile and baseline analysis. Then, we proposed a new method for feature extraction using fast wavelet transform. These extracted features are exploited as connection weights to build a convolutional neural network for each letter shape. Finally, all estimated model shapes are boosted to increase the robustness and performance of the proposed system. The proposed approach was tested on APTI and IESK‐arDB databases to evaluate performance for printed letters and handwritten letters, respectively. The obtained results show the robustness of our approach as well as the speed of the proposed recognition algorithm for both databases.

This article is categorized under:

  • Technologies > Machine Learning
  • Technologies > Computational Intelligence
  • Technologies > Classification
The Arabic alphabet and their corresponding shapes
[ Normal View | Magnified View ]
Fonts: (a) Advertising Extra Bold, (b) Diwani, (c) Unicode Sara M, and (d) Times
[ Normal View | Magnified View ]
The different Arabic characters classes
[ Normal View | Magnified View ]
Effect of the abstraction level analysis number on the performance of recognition system
[ Normal View | Magnified View ]
Example of an Arabic letter with different styles
[ Normal View | Magnified View ]
Some examples of Arabic handwritten words
[ Normal View | Magnified View ]
Feature extraction based on convolutional dyadic MRA
[ Normal View | Magnified View ]
Example of Arabic letter segmentation from a semi‐cursive word
[ Normal View | Magnified View ]
Example of Arabic letter segmentation from a cursive word
[ Normal View | Magnified View ]
Overview of the proposed approach
[ Normal View | Magnified View ]

Browse by Topic

Technologies > Classification
Technologies > Computational Intelligence
Technologies > Machine Learning

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts