On the use of the convolutional autoencoder for Arabic writer identification using handwritten text fragments
No Thumbnail Available
Date
2022-01-24
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
University of Eloued جامعة الوادي
Abstract
Convolutional autoencoders (CAE) are designed to reconstruct the input
image to the output in a near-perfect way via a compact data namely encoded
data containing relevant features. The encoded data can be used in various applications
as for compressing or classifying the image. The present paper tries to
investigate the use of the CAE for writer identification using handwritten text
fragments. Hence, the CAE is used for generating features, which is fed to the
distance-based classifier. Experimental evaluation is performed on the wellknown
IFN/ENIT dataset containing 411 writers. During training, a subset is selected
from the 411 writers containing only 11 writers allowing to produce a lite
CAE. Experimental results show an identification rate of 92.70% using the whole
dataset when the feature vector is appropriately normalized.
Description
Forum Intervention of Artificial Intelligence and Its Applications. Faculty of Exat science. University of Eloued
Keywords
Writer identification, Handwritten, Text fragment, Convolutional autoencoders.
Citation
Briber, Amina. Chibani,Youcef. On the use of the convolutional autoencoder for Arabic writer identification using handwritten text fragments. Forum of Artificial Intelligence and Its Applications. 24-26 Jan 2022. Faculty of Exat science. University of Eloued. [visited in ../../….]. available from [copy the link here]