Lifting Wavelet Transform based Fast Watermarking of Video Summaries using Extreme Learning Machine

Anurag Mishra, Charu Agarwal, Girija CHETTY

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

Abstract

In this paper, we present a robust semi-blind video watermarking scheme in lifting wavelet transform (LWT) domain using Extreme Learning Machine (ELM). In this scheme, first the static video summary is generated using extraction of color features from video frames. Second, the frames comprised of video summary are watermarked in LWT domain. To develop a robust and real time watermarking scheme, a fast Single hidden Layer Feedforward Neural Network (SLFN) known as ELM is used for watermark embedding and extraction. To evaluate the performance of the present scheme, several signal processing attacks are applied to each watermarked frame. Experimental evidence shows that the proposed scheme is robust against selected attacks. Due to fast processing of frames, the proposed scheme is also found to be suitable for real time watermarking of video.
Original languageEnglish
Title of host publicationProceedings 2018 International Joint Conference on Neural Networks (IJCNN)
Place of PublicationRio de Janeiro, Brazil
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1-7
Number of pages7
ISBN (Electronic)9781509060146
ISBN (Print)9781509060153
DOIs
Publication statusPublished - 8 Jul 2018
EventIEEE International Conference on Neural Networks -
Duration: 1 Jan 2011 → …

Conference

ConferenceIEEE International Conference on Neural Networks
Abbreviated titleICNN
Period1/01/11 → …

Fingerprint

Watermarking
Wavelet transforms
Learning systems
Feedforward neural networks
Signal processing
Color
Processing

Cite this

Mishra, A., Agarwal, C., & CHETTY, G. (2018). Lifting Wavelet Transform based Fast Watermarking of Video Summaries using Extreme Learning Machine. In Proceedings 2018 International Joint Conference on Neural Networks (IJCNN) (pp. 1-7). Rio de Janeiro, Brazil: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IJCNN.2018.8489305
Mishra, Anurag ; Agarwal, Charu ; CHETTY, Girija. / Lifting Wavelet Transform based Fast Watermarking of Video Summaries using Extreme Learning Machine. Proceedings 2018 International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro, Brazil : IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 1-7
@inproceedings{687a9c5a97bd444aaab618d26829df8c,
title = "Lifting Wavelet Transform based Fast Watermarking of Video Summaries using Extreme Learning Machine",
abstract = "In this paper, we present a robust semi-blind video watermarking scheme in lifting wavelet transform (LWT) domain using Extreme Learning Machine (ELM). In this scheme, first the static video summary is generated using extraction of color features from video frames. Second, the frames comprised of video summary are watermarked in LWT domain. To develop a robust and real time watermarking scheme, a fast Single hidden Layer Feedforward Neural Network (SLFN) known as ELM is used for watermark embedding and extraction. To evaluate the performance of the present scheme, several signal processing attacks are applied to each watermarked frame. Experimental evidence shows that the proposed scheme is robust against selected attacks. Due to fast processing of frames, the proposed scheme is also found to be suitable for real time watermarking of video.",
keywords = "Watermarking, Wavelet transforms, Extreme Learning Machine (ELM)",
author = "Anurag Mishra and Charu Agarwal and Girija CHETTY",
year = "2018",
month = "7",
day = "8",
doi = "10.1109/IJCNN.2018.8489305",
language = "English",
isbn = "9781509060153",
pages = "1--7",
booktitle = "Proceedings 2018 International Joint Conference on Neural Networks (IJCNN)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Mishra, A, Agarwal, C & CHETTY, G 2018, Lifting Wavelet Transform based Fast Watermarking of Video Summaries using Extreme Learning Machine. in Proceedings 2018 International Joint Conference on Neural Networks (IJCNN). IEEE, Institute of Electrical and Electronics Engineers, Rio de Janeiro, Brazil, pp. 1-7, IEEE International Conference on Neural Networks, 1/01/11. https://doi.org/10.1109/IJCNN.2018.8489305

Lifting Wavelet Transform based Fast Watermarking of Video Summaries using Extreme Learning Machine. / Mishra, Anurag; Agarwal, Charu; CHETTY, Girija.

Proceedings 2018 International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro, Brazil : IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 1-7.

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

TY - GEN

T1 - Lifting Wavelet Transform based Fast Watermarking of Video Summaries using Extreme Learning Machine

AU - Mishra, Anurag

AU - Agarwal, Charu

AU - CHETTY, Girija

PY - 2018/7/8

Y1 - 2018/7/8

N2 - In this paper, we present a robust semi-blind video watermarking scheme in lifting wavelet transform (LWT) domain using Extreme Learning Machine (ELM). In this scheme, first the static video summary is generated using extraction of color features from video frames. Second, the frames comprised of video summary are watermarked in LWT domain. To develop a robust and real time watermarking scheme, a fast Single hidden Layer Feedforward Neural Network (SLFN) known as ELM is used for watermark embedding and extraction. To evaluate the performance of the present scheme, several signal processing attacks are applied to each watermarked frame. Experimental evidence shows that the proposed scheme is robust against selected attacks. Due to fast processing of frames, the proposed scheme is also found to be suitable for real time watermarking of video.

AB - In this paper, we present a robust semi-blind video watermarking scheme in lifting wavelet transform (LWT) domain using Extreme Learning Machine (ELM). In this scheme, first the static video summary is generated using extraction of color features from video frames. Second, the frames comprised of video summary are watermarked in LWT domain. To develop a robust and real time watermarking scheme, a fast Single hidden Layer Feedforward Neural Network (SLFN) known as ELM is used for watermark embedding and extraction. To evaluate the performance of the present scheme, several signal processing attacks are applied to each watermarked frame. Experimental evidence shows that the proposed scheme is robust against selected attacks. Due to fast processing of frames, the proposed scheme is also found to be suitable for real time watermarking of video.

KW - Watermarking

KW - Wavelet transforms

KW - Extreme Learning Machine (ELM)

U2 - 10.1109/IJCNN.2018.8489305

DO - 10.1109/IJCNN.2018.8489305

M3 - Conference contribution

SN - 9781509060153

SP - 1

EP - 7

BT - Proceedings 2018 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Rio de Janeiro, Brazil

ER -

Mishra A, Agarwal C, CHETTY G. Lifting Wavelet Transform based Fast Watermarking of Video Summaries using Extreme Learning Machine. In Proceedings 2018 International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro, Brazil: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 1-7 https://doi.org/10.1109/IJCNN.2018.8489305