A novel image watermarking scheme using Extreme Learning Machine

Anurag Mishra, Girija Chetty, Lavneet Singh, Amita Goel, Rampal Singh

Research output: A Conference proceeding or a Chapter in BookConference contribution

28 Citations (Scopus)
4 Downloads (Pure)

Abstract

In this paper, a novel digital image watermarking algorithm based on a fast neural network known as Extreme Learning Machine (ELM) for two grayscale images is proposed. The ELM algorithm is very fast and completes its training in milliseconds unlike its other counterparts such as BPN. The proposed watermarking algorithm trains the ELM by using low frequency coefficients of the grayscale host image in transform domain. The trained ELM produces a sequence of 1024 real numbers, normalized as per N(0, 1) as an output. This sequence is used as watermark to be embedded within the host image using Cox's formula to obtain the signed image. The visual quality of the signed images is evaluated by PSNR. High PSNR values indicate that the quality of signed images is quite good. The computed high value of SIM (X, X*) establishes that the extraction process is quite successful and overall the algorithm finds good practical applications, especially in situations that warrant meeting time constraints.
Original languageEnglish
Title of host publicationThe 2012 International Joint Conference on Neural Networks (IJCNN)
EditorsHussein Abbass, Daryl Essam, Ruhul Sarker
Place of PublicationBrisbane
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1-6
Number of pages6
ISBN (Electronic)9781467314909, 9781467314893
ISBN (Print)9781467314886
DOIs
Publication statusPublished - 2012
Event2012 International Joint Conference on Neural Networks (IJCNN) - Brisbane, Brisbane, Australia
Duration: 10 Jul 201215 Jul 2012

Conference

Conference2012 International Joint Conference on Neural Networks (IJCNN)
Abbreviated titleIJCNN 2012
CountryAustralia
CityBrisbane
Period10/07/1215/07/12

Fingerprint

Image watermarking
Learning systems
Watermarking
Neural networks

Cite this

Mishra, A., Chetty, G., Singh, L., Goel, A., & Singh, R. (2012). A novel image watermarking scheme using Extreme Learning Machine. In H. Abbass, D. Essam, & R. Sarker (Eds.), The 2012 International Joint Conference on Neural Networks (IJCNN) (pp. 1-6). Brisbane: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IJCNN.2012.6252363
Mishra, Anurag ; Chetty, Girija ; Singh, Lavneet ; Goel, Amita ; Singh, Rampal. / A novel image watermarking scheme using Extreme Learning Machine. The 2012 International Joint Conference on Neural Networks (IJCNN). editor / Hussein Abbass ; Daryl Essam ; Ruhul Sarker. Brisbane : IEEE, Institute of Electrical and Electronics Engineers, 2012. pp. 1-6
@inproceedings{2ecbd7ef376c400c8786dab56d599f77,
title = "A novel image watermarking scheme using Extreme Learning Machine",
abstract = "In this paper, a novel digital image watermarking algorithm based on a fast neural network known as Extreme Learning Machine (ELM) for two grayscale images is proposed. The ELM algorithm is very fast and completes its training in milliseconds unlike its other counterparts such as BPN. The proposed watermarking algorithm trains the ELM by using low frequency coefficients of the grayscale host image in transform domain. The trained ELM produces a sequence of 1024 real numbers, normalized as per N(0, 1) as an output. This sequence is used as watermark to be embedded within the host image using Cox's formula to obtain the signed image. The visual quality of the signed images is evaluated by PSNR. High PSNR values indicate that the quality of signed images is quite good. The computed high value of SIM (X, X*) establishes that the extraction process is quite successful and overall the algorithm finds good practical applications, especially in situations that warrant meeting time constraints.",
keywords = "Digital Image Watermarking, Extreme Learning Machine (ELM), Real Time applications",
author = "Anurag Mishra and Girija Chetty and Lavneet Singh and Amita Goel and Rampal Singh",
year = "2012",
doi = "10.1109/IJCNN.2012.6252363",
language = "English",
isbn = "9781467314886",
pages = "1--6",
editor = "Hussein Abbass and Daryl Essam and Ruhul Sarker",
booktitle = "The 2012 International Joint Conference on Neural Networks (IJCNN)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Mishra, A, Chetty, G, Singh, L, Goel, A & Singh, R 2012, A novel image watermarking scheme using Extreme Learning Machine. in H Abbass, D Essam & R Sarker (eds), The 2012 International Joint Conference on Neural Networks (IJCNN). IEEE, Institute of Electrical and Electronics Engineers, Brisbane, pp. 1-6, 2012 International Joint Conference on Neural Networks (IJCNN), Brisbane, Australia, 10/07/12. https://doi.org/10.1109/IJCNN.2012.6252363

A novel image watermarking scheme using Extreme Learning Machine. / Mishra, Anurag; Chetty, Girija; Singh, Lavneet; Goel, Amita; Singh, Rampal.

The 2012 International Joint Conference on Neural Networks (IJCNN). ed. / Hussein Abbass; Daryl Essam; Ruhul Sarker. Brisbane : IEEE, Institute of Electrical and Electronics Engineers, 2012. p. 1-6.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - A novel image watermarking scheme using Extreme Learning Machine

AU - Mishra, Anurag

AU - Chetty, Girija

AU - Singh, Lavneet

AU - Goel, Amita

AU - Singh, Rampal

PY - 2012

Y1 - 2012

N2 - In this paper, a novel digital image watermarking algorithm based on a fast neural network known as Extreme Learning Machine (ELM) for two grayscale images is proposed. The ELM algorithm is very fast and completes its training in milliseconds unlike its other counterparts such as BPN. The proposed watermarking algorithm trains the ELM by using low frequency coefficients of the grayscale host image in transform domain. The trained ELM produces a sequence of 1024 real numbers, normalized as per N(0, 1) as an output. This sequence is used as watermark to be embedded within the host image using Cox's formula to obtain the signed image. The visual quality of the signed images is evaluated by PSNR. High PSNR values indicate that the quality of signed images is quite good. The computed high value of SIM (X, X*) establishes that the extraction process is quite successful and overall the algorithm finds good practical applications, especially in situations that warrant meeting time constraints.

AB - In this paper, a novel digital image watermarking algorithm based on a fast neural network known as Extreme Learning Machine (ELM) for two grayscale images is proposed. The ELM algorithm is very fast and completes its training in milliseconds unlike its other counterparts such as BPN. The proposed watermarking algorithm trains the ELM by using low frequency coefficients of the grayscale host image in transform domain. The trained ELM produces a sequence of 1024 real numbers, normalized as per N(0, 1) as an output. This sequence is used as watermark to be embedded within the host image using Cox's formula to obtain the signed image. The visual quality of the signed images is evaluated by PSNR. High PSNR values indicate that the quality of signed images is quite good. The computed high value of SIM (X, X*) establishes that the extraction process is quite successful and overall the algorithm finds good practical applications, especially in situations that warrant meeting time constraints.

KW - Digital Image Watermarking

KW - Extreme Learning Machine (ELM)

KW - Real Time applications

U2 - 10.1109/IJCNN.2012.6252363

DO - 10.1109/IJCNN.2012.6252363

M3 - Conference contribution

SN - 9781467314886

SP - 1

EP - 6

BT - The 2012 International Joint Conference on Neural Networks (IJCNN)

A2 - Abbass, Hussein

A2 - Essam, Daryl

A2 - Sarker, Ruhul

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Brisbane

ER -

Mishra A, Chetty G, Singh L, Goel A, Singh R. A novel image watermarking scheme using Extreme Learning Machine. In Abbass H, Essam D, Sarker R, editors, The 2012 International Joint Conference on Neural Networks (IJCNN). Brisbane: IEEE, Institute of Electrical and Electronics Engineers. 2012. p. 1-6 https://doi.org/10.1109/IJCNN.2012.6252363