An Efficient Arabic HMM System Based on Convolutional Features Learning

Published works recently indicate that the generic features extracted from the convolutional neural networks are very powerful. This paper shows that CNN feature can be used with a HMM system [1] for Arabic handwritten word recognition, to yield classification results that outperform the handcrafted...

Full description

Saved in:
Bibliographic Details
Published in2019 International Conference of Computer Science and Renewable Energies (ICCSRE) pp. 1 - 5
Main Authors AMROUCH, Mustapha, RABI, Mouhcine, MEZOUARY, Ali EL
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2019
Subjects
CNN
Convolution
Extraction features
Feature extraction
Handwriting recognition
Hidden Markov models
HMM
Task analysis
Training
Online AccessGet full text

Cover

More Information
Summary:Published works recently indicate that the generic features extracted from the convolutional neural networks are very powerful. This paper shows that CNN feature can be used with a HMM system [1] for Arabic handwritten word recognition, to yield classification results that outperform the handcrafted features. These features are usually based on heuristic approaches that describe either basic geometric properties or statistical distributions of raw pixel values. The CNN features based HMM is shown satisfactory recognition accuracy on the well-known IFN/ENIT database and outperformed some other prominent existing methods.
DOI:10.1109/ICCSRE.2019.8807548