An Extensive Analysis on Optimized 3D Watermarking Using Enhanced Clustering Techniques

The rapid advancement of technology and increased internet usage have significantly contributed to the development of multimedia technologies, such as computer games and computer graphics. A key aspect of these advancements is the creation and widespread use of 3D models. However, this rapid develop...

Full description

Saved in:
Bibliographic Details
Main Authors: G. Julie Sharine, L. Jani Anbarasi
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10735202/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199475302170624
author G. Julie Sharine
L. Jani Anbarasi
author_facet G. Julie Sharine
L. Jani Anbarasi
author_sort G. Julie Sharine
collection DOAJ
description The rapid advancement of technology and increased internet usage have significantly contributed to the development of multimedia technologies, such as computer games and computer graphics. A key aspect of these advancements is the creation and widespread use of 3D models. However, this rapid development has also led to issues like illegal usage and theft of 3D models. Ensuring ownership protection is crucial to addressing these challenges. An effective method for copyright protection and preserving the integrity of 3D mesh models is digital watermarking. 3D watermarking is essential for safeguarding the copyright of 3D mesh models. This proposed study introduces an innovative approach that combines three powerful techniques. Fuzzy C-Means (FCM), Gaussian Mixture Model (GMM), and K-Means clustering to cluster similar vertices and embed watermarks. These techniques are chosen due to their simplicity, efficiency and accuracy that are proven in other domains. In the proposed work the cluster size is varied for each algorithm, and the watermark is embedded in the largest cluster, specifically in the ‘Z’ coordinate of the model. To test the robustness of the watermark, common attacks and geometric attacks are applied to the watermarked models. The embedded watermark is extracted with an NCC value close to 1 for all clustering algorithms, indicating high accuracy. The study evaluates the imperceptibility and robustness of the watermarking method, achieving high Peak Signal To Noise Ratio (PSNR) values and low Root Mean Square Error (RMSE), which demonstrate the effectiveness of the novel approach. The results indicate that the method attains excellent Normalized Correlation Coefficient (NCC) values, confirming its reliability and robustness.
format Article
id doaj-art-1f4a81bec0b24bdc914f671fbefab8a3
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-1f4a81bec0b24bdc914f671fbefab8a32025-08-20T02:12:37ZengIEEEIEEE Access2169-35362024-01-011215896615898310.1109/ACCESS.2024.348630810735202An Extensive Analysis on Optimized 3D Watermarking Using Enhanced Clustering TechniquesG. Julie Sharine0https://orcid.org/0009-0002-9161-2952L. Jani Anbarasi1https://orcid.org/0000-0002-8904-2236School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, IndiaSchool of Computer Science and Engineering, Vellore Institute of Technology, Chennai, IndiaThe rapid advancement of technology and increased internet usage have significantly contributed to the development of multimedia technologies, such as computer games and computer graphics. A key aspect of these advancements is the creation and widespread use of 3D models. However, this rapid development has also led to issues like illegal usage and theft of 3D models. Ensuring ownership protection is crucial to addressing these challenges. An effective method for copyright protection and preserving the integrity of 3D mesh models is digital watermarking. 3D watermarking is essential for safeguarding the copyright of 3D mesh models. This proposed study introduces an innovative approach that combines three powerful techniques. Fuzzy C-Means (FCM), Gaussian Mixture Model (GMM), and K-Means clustering to cluster similar vertices and embed watermarks. These techniques are chosen due to their simplicity, efficiency and accuracy that are proven in other domains. In the proposed work the cluster size is varied for each algorithm, and the watermark is embedded in the largest cluster, specifically in the ‘Z’ coordinate of the model. To test the robustness of the watermark, common attacks and geometric attacks are applied to the watermarked models. The embedded watermark is extracted with an NCC value close to 1 for all clustering algorithms, indicating high accuracy. The study evaluates the imperceptibility and robustness of the watermarking method, achieving high Peak Signal To Noise Ratio (PSNR) values and low Root Mean Square Error (RMSE), which demonstrate the effectiveness of the novel approach. The results indicate that the method attains excellent Normalized Correlation Coefficient (NCC) values, confirming its reliability and robustness.https://ieeexplore.ieee.org/document/10735202/3D model watermarkingFCMGMMK-Meansrobustnessimperceptibility
spellingShingle G. Julie Sharine
L. Jani Anbarasi
An Extensive Analysis on Optimized 3D Watermarking Using Enhanced Clustering Techniques
IEEE Access
3D model watermarking
FCM
GMM
K-Means
robustness
imperceptibility
title An Extensive Analysis on Optimized 3D Watermarking Using Enhanced Clustering Techniques
title_full An Extensive Analysis on Optimized 3D Watermarking Using Enhanced Clustering Techniques
title_fullStr An Extensive Analysis on Optimized 3D Watermarking Using Enhanced Clustering Techniques
title_full_unstemmed An Extensive Analysis on Optimized 3D Watermarking Using Enhanced Clustering Techniques
title_short An Extensive Analysis on Optimized 3D Watermarking Using Enhanced Clustering Techniques
title_sort extensive analysis on optimized 3d watermarking using enhanced clustering techniques
topic 3D model watermarking
FCM
GMM
K-Means
robustness
imperceptibility
url https://ieeexplore.ieee.org/document/10735202/
work_keys_str_mv AT gjuliesharine anextensiveanalysisonoptimized3dwatermarkingusingenhancedclusteringtechniques
AT ljanianbarasi anextensiveanalysisonoptimized3dwatermarkingusingenhancedclusteringtechniques
AT gjuliesharine extensiveanalysisonoptimized3dwatermarkingusingenhancedclusteringtechniques
AT ljanianbarasi extensiveanalysisonoptimized3dwatermarkingusingenhancedclusteringtechniques