Cover Image

Image entropy equalization: a novel preprocessing technique for image recognition tasks.

Image entropy is the metric used to represent a complexity of an image. This study considers the hypothesis that image entropy differences affect machine learning algorithms' performance. This paper proposes a novel preprocessing technique, image entropy equalization, to delete the image entrop...

Full description

Saved in:
Bibliographic Details
Main Authors: Hayashi, Toshitaka, Cimr, Dalibor, Fujita, Hamido, Cimler, Richard
Format: Article
Published: Elsevier Inc. 2023
Subjects:
T Technology (General)
Online Access:http://eprints.utm.my/105064/
http://dx.doi.org/10.1016/j.ins.2023.119539
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.105064
record_format eprints
spelling my.utm.1050642024-04-02T06:46:25Z http://eprints.utm.my/105064/ Image entropy equalization: a novel preprocessing technique for image recognition tasks. Hayashi, Toshitaka Cimr, Dalibor Fujita, Hamido Cimler, Richard T Technology (General) Image entropy is the metric used to represent a complexity of an image. This study considers the hypothesis that image entropy differences affect machine learning algorithms' performance. This paper proposes a novel preprocessing technique, image entropy equalization, to delete the image entropy differences. The goal is to transform all images into the same entropy. Such a process is implemented by editing all images into the same histogram. Image entropy equalization is evaluated by comparing the original and equalized images in various machine learning tasks. The main advantage of image entropy equalization is to improve the AUC score for one-class autoencoder (OCAE). This result gives a new hypothesis that using image entropy equalization could improve various studies using autoencoder (AE). In addition, the proposed method shows fair results for classification and regression tasks. On the other hand, the main challenges are that the equalization process depends on a reference histogram and is affected by diverse backgrounds. Elsevier Inc. 2023-11 Article PeerReviewed Hayashi, Toshitaka and Cimr, Dalibor and Fujita, Hamido and Cimler, Richard (2023) Image entropy equalization: a novel preprocessing technique for image recognition tasks. Information Sciences, 647 (119539). NA-NA. ISSN 0020-0255 http://dx.doi.org/10.1016/j.ins.2023.119539 DOI: 10.1016/j.ins.2023.119539
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic T Technology (General)
spellingShingle T Technology (General)
Hayashi, Toshitaka
Cimr, Dalibor
Fujita, Hamido
Cimler, Richard
Image entropy equalization: a novel preprocessing technique for image recognition tasks.
description Image entropy is the metric used to represent a complexity of an image. This study considers the hypothesis that image entropy differences affect machine learning algorithms' performance. This paper proposes a novel preprocessing technique, image entropy equalization, to delete the image entropy differences. The goal is to transform all images into the same entropy. Such a process is implemented by editing all images into the same histogram. Image entropy equalization is evaluated by comparing the original and equalized images in various machine learning tasks. The main advantage of image entropy equalization is to improve the AUC score for one-class autoencoder (OCAE). This result gives a new hypothesis that using image entropy equalization could improve various studies using autoencoder (AE). In addition, the proposed method shows fair results for classification and regression tasks. On the other hand, the main challenges are that the equalization process depends on a reference histogram and is affected by diverse backgrounds.
format Article
author Hayashi, Toshitaka
Cimr, Dalibor
Fujita, Hamido
Cimler, Richard
author_facet Hayashi, Toshitaka
Cimr, Dalibor
Fujita, Hamido
Cimler, Richard
author_sort Hayashi, Toshitaka
title Image entropy equalization: a novel preprocessing technique for image recognition tasks.
title_short Image entropy equalization: a novel preprocessing technique for image recognition tasks.
title_full Image entropy equalization: a novel preprocessing technique for image recognition tasks.
title_fullStr Image entropy equalization: a novel preprocessing technique for image recognition tasks.
title_full_unstemmed Image entropy equalization: a novel preprocessing technique for image recognition tasks.
title_sort image entropy equalization: a novel preprocessing technique for image recognition tasks.
publisher Elsevier Inc.
publishDate 2023
url http://eprints.utm.my/105064/
http://dx.doi.org/10.1016/j.ins.2023.119539
_version_ 1797905934232584192
score 13.244367

Similar Items