PMID- 38521848
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240326
IS  - 2045-2322 (Electronic)
IS  - 2045-2322 (Linking)
VI  - 14
IP  - 1
DP  - 2024 Mar 23
TI  - Levenberg-Marquardt deep neural watermarking for 3D mesh using nearest centroid 
      salient point learning.
PG  - 6942
LID - 10.1038/s41598-024-57360-z [doi]
LID - 6942
AB  - Watermarking is one of the crucial techniques in the domain of information 
      security, preventing the exploitation of 3D Mesh models in the era of Internet. 
      In 3D Mesh watermark embedding, moderately perturbing the vertices is commonly 
      required to retain them in certain pre-arranged relationship with their 
      neighboring vertices. This paper proposes a novel watermarking authentication 
      method, called Nearest Centroid Discrete Gaussian and Levenberg-Marquardt 
      (NCDG-LV), for distortion detection and recovery using salient point detection. 
      In this method, the salient points are selected using the Nearest Centroid and 
      Discrete Gaussian Geometric (NC-DGG) salient point detection model. Map 
      segmentation is applied to the 3D Mesh model to segment into distinct sub regions 
      according to the selected salient points. Finally, the watermark is embedded by 
      employing the Multi-function Barycenter into each spatially selected and 
      segmented region. In the extraction process, the embedded 3D Mesh image is 
      extracted from each re-segmented region by means of Levenberg-Marquardt Deep 
      Neural Network Watermark Extraction. In the authentication stage, watermark bits 
      are extracted by analyzing the geometry via Levenberg-Marquardt back-propagation. 
      Based on a performance evaluation, the proposed method exhibits high 
      imperceptibility and tolerance against attacks, such as smoothing, cropping, 
      translation, and rotation. The experimental results further demonstrate that the 
      proposed method is superior in terms of salient point detection time, distortion 
      rate, true positive rate, peak signal to noise ratio, bit error rate, and root 
      mean square error compared to the state-of-the-art methods.
CI  - (c) 2024. The Author(s).
FAU - Narendra, Modigari
AU  - Narendra M
AD  - School of Computer Science and Engineering, Vellore Institute of Technology, 
      Chennai, India.
FAU - Valarmathi, M L
AU  - Valarmathi ML
AD  - Department of Computer Science and Engineering, Dr. Mahalingam College of 
      Engineering and Technology, Pollachi, India.
FAU - Anbarasi, L Jani
AU  - Anbarasi LJ
AD  - School of Computer Science and Engineering, Vellore Institute of Technology, 
      Chennai, India.
FAU - Gandomi, Amir H
AU  - Gandomi AH
AD  - Faculty of Engineering and IT, University of Technology Sydney, Sydney, NSW, 
      2007, Australia. gandomi@uts.edu.au.
AD  - University Research and Innovation Center (EKIK), Obuda University, Budapest, 
      1034, Hungary. gandomi@uts.edu.au.
LA  - eng
PT  - Journal Article
DEP - 20240323
PL  - England
TA  - Sci Rep
JT  - Scientific reports
JID - 101563288
SB  - IM
PMC - PMC10960838
OTO - NOTNLM
OT  - Deep neural network
OT  - Discrete Gaussian geometric
OT  - Levenberg-Marquardt
OT  - Multi-function barycenter
OT  - Salient point detection
COIS- The authors declare no competing interests.
EDAT- 2024/03/24 06:42
MHDA- 2024/03/24 06:43
PMCR- 2024/03/23
CRDT- 2024/03/24 00:22
PHST- 2023/05/20 00:00 [received]
PHST- 2024/03/18 00:00 [accepted]
PHST- 2024/03/24 06:43 [medline]
PHST- 2024/03/24 06:42 [pubmed]
PHST- 2024/03/24 00:22 [entrez]
PHST- 2024/03/23 00:00 [pmc-release]
AID - 10.1038/s41598-024-57360-z [pii]
AID - 57360 [pii]
AID - 10.1038/s41598-024-57360-z [doi]
PST - epublish
SO  - Sci Rep. 2024 Mar 23;14(1):6942. doi: 10.1038/s41598-024-57360-z.