Word-based Handwritten Arabic Scripts Recognition using DCT Features and Neural Network Classifier

Jawad H. AlKhateeb; Jinchang Ren; Jianmin Jiang; Stan S. Ipson; Haikal El Abed; IEEE

Back

Conference proceeding

Word-based Handwritten Arabic Scripts Recognition using DCT Features and Neural Network Classifier

Jawad H. AlKhateeb, Jinchang Ren, Jianmin Jiang, Stan S. Ipson, Haikal El Abed and IEEE

2008 5TH INTERNATIONAL MULTI-CONFERENCE ON SYSTEMS, SIGNALS AND DEVICES, VOLS 1 AND 2, p.486

01/01/2008

Abstract

Engineering

Engineering, Electrical & Electronic

Science & Technology

Technology

Telecommunications

In this paper, a system is proposed for word-based recognition of handwritten Arabic scripts. Techniques are discussed in details in term of three stages in the system, i.e. preprocessing, feature extraction and classification. Firstly, words are segmented from inputted scripts and also normalized in size. Then, DCT features are extracted for each word sample. Finally, these features are then utilized to train a neural network for classification. The proposed system has been successfully tested on database (version v2.0ple) consisting of 32492 Arabic words handwritten by more than 1000 different writers, and the results were promising and very encouraging.

Metrics

1 Record Views

Details

Title: Word-based Handwritten Arabic Scripts Recognition using DCT Features and Neural Network Classifier
Creators - without role: Jawad H. AlKhateeb - University of Bradford
Jinchang Ren - University of Bradford
Jianmin Jiang - University of Bradford
Stan S. Ipson - University of Bradford
Haikal El Abed - Tech Univ Carolo Wilhelmina Braunschweig, Inst Commun Technol, D-38092 Braunschweig, Germany
IEEE
Publication Details: 2008 5TH INTERNATIONAL MULTI-CONFERENCE ON SYSTEMS, SIGNALS AND DEVICES, VOLS 1 AND 2, p.486
Publisher: IEEE
Number of pages: 3
Identifiers: 9930013708331
Academic Unit: Taibah University
Language: English
Resource Type: Conference proceeding