Robust deep image clustering using convolutional autoencoder with separable discrete Krawtchouk and Hahn orthogonal moments

By cooperatively learning features and assigning clusters, deep clustering is superior to conventional clustering algorithms. Numerous deep clustering algorithms have been developed for a variety of application levels; however, the majority are still incapable of learning robust noise-resistant late...

Full description

Saved in:
Bibliographic Details
Published in:Intelligent systems with applications Vol. 22; p. 200387
Main Authors: Bouali, Aymane, Ouariachi, Ilham El, Zahi, Azeddine, Zenkouar, Khalid
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.06.2024
Elsevier
Subjects:
Autoencoder
Deep clustering
Discrete separable orthogonal moments
Hahn moments
Image clustering
Krawtchouk moments
Hahn moments
Discrete separable orthogonal moments
Image clustering
Krawtchouk moments
Autoencoder
Deep clustering
ISSN:2667-3053, 2667-3053
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:By cooperatively learning features and assigning clusters, deep clustering is superior to conventional clustering algorithms. Numerous deep clustering algorithms have been developed for a variety of application levels; however, the majority are still incapable of learning robust noise-resistant latent features, which limits the clustering performance. To address this open research challenge, we introduce, for the first time, a new approach called: Robust Deep Embedded Image Clustering algorithm with Separable Krawtchouk and Hahn Moments (RDEICSKHM). Our approach leverages the advantages of Krawtchouk and Hahn moments, such as local feature extraction, discrete orthogonality, and noise tolerance, to obtain a meaningful and robust image representation. Moreover, we employ LayerNormalization to further improve the latent space quality and facilitate the clustering process. We evaluate our approach on four image datasets: MNIST, MNIST-test, USPS, and Fashion-MNIST. We compare our method with several deep clustering methods based on two metrics: clustering accuracy (ACC) and normalized mutual information (NMI). The experimental results show that our method achieves superior or competitive performance on all datasets, demonstrating its effectiveness and robustness for deep image clustering. •Integration of discrete separable moments into autoencoder architectures.•Incorporation of the “LayerNormalization” layer for improvement DEC-based models.•Creating a robust convolutional model “RDEICSKHM” using discrete separable moments.
ISSN:2667-3053
2667-3053
DOI:10.1016/j.iswa.2024.200387