Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Combining slanted-frame classifiers for improved HMM-based Arabic handwriting recognition.

Ramy Al-Hajj Mohamad¹, Laurence Likforman-Sulem, Chafic Mokbel

¹Lebanese International University, Mazraa/Salim-Slam, Beirut, Lebanon. al-hajj@enst.fr

IEEE Transactions on Pattern Analysis and Machine Intelligence

|May 16, 2009

Summary

This summary is machine-generated.

Related Concept Videos

Aggregates Classification

Aggregates Classification

Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Dynamic and Contextual Information in HMM Modeling for Handwritten Word Recognition.

IEEE transactions on pattern analysis and machine intelligence·2011

Same author

Classification of contrast ultrasound images using autoregressive model coupled to Gaussian mixture model.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2007

See all related articles

This study improves handwritten Arabic city name recognition by combining Hidden Markov Model (HMM) classifiers. The novel approach achieves over 90% accuracy, outperforming single classifiers and handling variations in diacritical marks.

Area of Science:

Computer Science
Artificial Intelligence
Pattern Recognition

Background:

Offline recognition of handwritten Arabic city names presents challenges due to variations in script and diacritical marks.
Existing systems often struggle with issues like inclination, overlap, and shifted diacritics, leading to errors.

Purpose of the Study:

To develop an improved system for offline recognition of handwritten Arabic city names.
To address common error sources in Hidden Markov Model (HMM)-based recognition systems.
To evaluate the effectiveness of combining multiple HMM classifiers for enhanced accuracy.

Main Methods:

Developed a baseline Hidden Markov Model (HMM) recognizer using a sliding window approach with both baseline-dependent and independent features.
Proposed a novel approach combining three homogeneous HMM-based classifiers with differing sliding window orientations.

Related Experiment Videos

Compared three decision-level combination schemes, including a neural network-based method.

Main Results:

The combined HMM classifier system achieved over 90% accuracy on the IFN/ENIT Arabic Tunisian city names database.
The neural network-based combination scheme demonstrated superior performance compared to other combination methods.
The proposed approach outperformed a single classifier even when dealing with slant-corrected images and showed robustness across various orientation angles.

Conclusions:

Combining multiple HMM classifiers effectively enhances the accuracy of handwritten Arabic city name recognition.
The neural network-based combination strategy is particularly effective for this task.
The developed method offers a robust solution for recognizing handwritten Arabic city names, addressing key error sources.