A novel scene based robust video watermarking scheme in DWT domain using extreme learning machine

Charu Agarwal, Anurag Mishra, Arpita Sharma, Girija CHETTY

Research output: A Conference proceeding or a Chapter in BookChapter

6 Citations (Scopus)

Abstract

In this chapter, we present a novel fast and robust watermarking scheme for three different standard video in RGB uncompressed AVI format in DWT domain using a newly developed SLFN commonly known as Extreme Learning Machine (ELM). The embedding is carried out by using scene detection. The LL4 sub-band coefficients of frames constitute the dataset to train the ELM in millisecond time. The output of the ELM is used to embed a binary watermark in the video frames using a pre-specified formula. The resultant video exhibits good visual quality. Five different video processing attacks are executed over signed video. The extracted watermarks from the signed and attacked video yield high normalized correlation (NC) values and low Bit Error Rate (BER) values. This indicates successful watermark recovery and the embedding scheme is found to be robust against these common attacks. It is concluded that the proposed watermarking scheme produces best results due to optimized embedding facilitated by fast training of the ELM. The proposed scheme is found to be suitable for developing real time video watermarking applications due to its low time complexity.
Original languageEnglish
Title of host publicationExtreme Learning Machines 2013: Algorithms and Applications
EditorsFuchen Sun, Kar-Ann Toh, Manuel Grana Romay, Kezhi Mao
Place of PublicationCham, Switzerland
PublisherSpringer
Pages209-225
Number of pages17
Volume16
ISBN (Electronic)9783319047416
ISBN (Print)9783319047409
DOIs
Publication statusPublished - 2014

Publication series

NameAdaptation, Learning, and Optimization
ISSN (Print)1867-4542
ISSN (Electronic)1867-4542

Fingerprint

Watermarking
Learning systems
Bit error rate
Recovery
Processing

Cite this

Agarwal, C., Mishra, A., Sharma, A., & CHETTY, G. (2014). A novel scene based robust video watermarking scheme in DWT domain using extreme learning machine. In F. Sun, K-A. Toh, M. Grana Romay, & K. Mao (Eds.), Extreme Learning Machines 2013: Algorithms and Applications (Vol. 16, pp. 209-225). (Adaptation, Learning, and Optimization). Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-319-04741-6_15
Agarwal, Charu ; Mishra, Anurag ; Sharma, Arpita ; CHETTY, Girija. / A novel scene based robust video watermarking scheme in DWT domain using extreme learning machine. Extreme Learning Machines 2013: Algorithms and Applications. editor / Fuchen Sun ; Kar-Ann Toh ; Manuel Grana Romay ; Kezhi Mao. Vol. 16 Cham, Switzerland : Springer, 2014. pp. 209-225 (Adaptation, Learning, and Optimization).
@inbook{f7f1aedc5ec64376a335d2427885df3e,
title = "A novel scene based robust video watermarking scheme in DWT domain using extreme learning machine",
abstract = "In this chapter, we present a novel fast and robust watermarking scheme for three different standard video in RGB uncompressed AVI format in DWT domain using a newly developed SLFN commonly known as Extreme Learning Machine (ELM). The embedding is carried out by using scene detection. The LL4 sub-band coefficients of frames constitute the dataset to train the ELM in millisecond time. The output of the ELM is used to embed a binary watermark in the video frames using a pre-specified formula. The resultant video exhibits good visual quality. Five different video processing attacks are executed over signed video. The extracted watermarks from the signed and attacked video yield high normalized correlation (NC) values and low Bit Error Rate (BER) values. This indicates successful watermark recovery and the embedding scheme is found to be robust against these common attacks. It is concluded that the proposed watermarking scheme produces best results due to optimized embedding facilitated by fast training of the ELM. The proposed scheme is found to be suitable for developing real time video watermarking applications due to its low time complexity.",
keywords = "Video Watermarking, Video watermarking, Extreme learning machine, Uncompressed RGB AVI format, Scene detection",
author = "Charu Agarwal and Anurag Mishra and Arpita Sharma and Girija CHETTY",
year = "2014",
doi = "10.1007/978-3-319-04741-6_15",
language = "English",
isbn = "9783319047409",
volume = "16",
series = "Adaptation, Learning, and Optimization",
publisher = "Springer",
pages = "209--225",
editor = "Fuchen Sun and Kar-Ann Toh and {Grana Romay}, Manuel and Kezhi Mao",
booktitle = "Extreme Learning Machines 2013: Algorithms and Applications",
address = "Netherlands",

}

Agarwal, C, Mishra, A, Sharma, A & CHETTY, G 2014, A novel scene based robust video watermarking scheme in DWT domain using extreme learning machine. in F Sun, K-A Toh, M Grana Romay & K Mao (eds), Extreme Learning Machines 2013: Algorithms and Applications. vol. 16, Adaptation, Learning, and Optimization, Springer, Cham, Switzerland, pp. 209-225. https://doi.org/10.1007/978-3-319-04741-6_15

A novel scene based robust video watermarking scheme in DWT domain using extreme learning machine. / Agarwal, Charu; Mishra, Anurag; Sharma, Arpita; CHETTY, Girija.

Extreme Learning Machines 2013: Algorithms and Applications. ed. / Fuchen Sun; Kar-Ann Toh; Manuel Grana Romay; Kezhi Mao. Vol. 16 Cham, Switzerland : Springer, 2014. p. 209-225 (Adaptation, Learning, and Optimization).

Research output: A Conference proceeding or a Chapter in BookChapter

TY - CHAP

T1 - A novel scene based robust video watermarking scheme in DWT domain using extreme learning machine

AU - Agarwal, Charu

AU - Mishra, Anurag

AU - Sharma, Arpita

AU - CHETTY, Girija

PY - 2014

Y1 - 2014

N2 - In this chapter, we present a novel fast and robust watermarking scheme for three different standard video in RGB uncompressed AVI format in DWT domain using a newly developed SLFN commonly known as Extreme Learning Machine (ELM). The embedding is carried out by using scene detection. The LL4 sub-band coefficients of frames constitute the dataset to train the ELM in millisecond time. The output of the ELM is used to embed a binary watermark in the video frames using a pre-specified formula. The resultant video exhibits good visual quality. Five different video processing attacks are executed over signed video. The extracted watermarks from the signed and attacked video yield high normalized correlation (NC) values and low Bit Error Rate (BER) values. This indicates successful watermark recovery and the embedding scheme is found to be robust against these common attacks. It is concluded that the proposed watermarking scheme produces best results due to optimized embedding facilitated by fast training of the ELM. The proposed scheme is found to be suitable for developing real time video watermarking applications due to its low time complexity.

AB - In this chapter, we present a novel fast and robust watermarking scheme for three different standard video in RGB uncompressed AVI format in DWT domain using a newly developed SLFN commonly known as Extreme Learning Machine (ELM). The embedding is carried out by using scene detection. The LL4 sub-band coefficients of frames constitute the dataset to train the ELM in millisecond time. The output of the ELM is used to embed a binary watermark in the video frames using a pre-specified formula. The resultant video exhibits good visual quality. Five different video processing attacks are executed over signed video. The extracted watermarks from the signed and attacked video yield high normalized correlation (NC) values and low Bit Error Rate (BER) values. This indicates successful watermark recovery and the embedding scheme is found to be robust against these common attacks. It is concluded that the proposed watermarking scheme produces best results due to optimized embedding facilitated by fast training of the ELM. The proposed scheme is found to be suitable for developing real time video watermarking applications due to its low time complexity.

KW - Video Watermarking

KW - Video watermarking

KW - Extreme learning machine

KW - Uncompressed RGB AVI format

KW - Scene detection

UR - http://www.scopus.com/inward/record.url?scp=84959181768&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/novel-scene-based-robust-video-watermarking-scheme-dwt-domain-using-extreme-learning-machine

U2 - 10.1007/978-3-319-04741-6_15

DO - 10.1007/978-3-319-04741-6_15

M3 - Chapter

SN - 9783319047409

VL - 16

T3 - Adaptation, Learning, and Optimization

SP - 209

EP - 225

BT - Extreme Learning Machines 2013: Algorithms and Applications

A2 - Sun, Fuchen

A2 - Toh, Kar-Ann

A2 - Grana Romay, Manuel

A2 - Mao, Kezhi

PB - Springer

CY - Cham, Switzerland

ER -

Agarwal C, Mishra A, Sharma A, CHETTY G. A novel scene based robust video watermarking scheme in DWT domain using extreme learning machine. In Sun F, Toh K-A, Grana Romay M, Mao K, editors, Extreme Learning Machines 2013: Algorithms and Applications. Vol. 16. Cham, Switzerland: Springer. 2014. p. 209-225. (Adaptation, Learning, and Optimization). https://doi.org/10.1007/978-3-319-04741-6_15