SIFT based view invariant watermarking for DIBR 3D image

Shuvendu Rana; Vishavdeep Mattu; Arijit Sur

doi:10.1109/NCVPRIPG.2015.7490030

SIFT based view invariant watermarking for DIBR 3D image

Shuvendu Rana, Vishavdeep Mattu, Arijit Sur

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

2 Citations (Scopus)

Abstract

In this paper, a view invariant watermarking scheme is proposed for depth image based rendering (DIBR) 3D image representation. To make the scheme invariant against view synthesis process, the watermark is inserted in the image locations selected by the SIFT (Scale-invariant feature transform) feature points. A novel SIFT feature based coefficient selection scheme has been implemented for watermark embedding by exploiting the shift invariance and directional property of the DIBR based view synthesis process. A coefficient partitioning based blind watermarking method has been included to make the scheme more efficient. A comprehensive set of experiments have been carried out to justify the robustness of the proposed scheme against the view synthesis attack.

Original language	English
Title of host publication	2015 5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2015
Place of Publication	Piscataway, NJ
Publisher	IEEE
Number of pages	4
ISBN (Electronic)	9781467385640
DOIs	https://doi.org/10.1109/NCVPRIPG.2015.7490030
Publication status	Published - 13 Jun 2016
Event	5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2015 - Patna, Bihar, India Duration: 16 Dec 2015 → 19 Dec 2015

Conference

Conference	5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2015
Country/Territory	India
City	Patna, Bihar
Period	16/12/15 → 19/12/15

Keywords

watermarking
feature extraction
three-dimensional displays
discrete cosine transforms
image representation
robustness
visualisation

Access to Document

10.1109/NCVPRIPG.2015.7490030

Cite this

@inproceedings{4a84f6f6611f45d893143cd7611bb0dd,

title = "SIFT based view invariant watermarking for DIBR 3D image",

abstract = "In this paper, a view invariant watermarking scheme is proposed for depth image based rendering (DIBR) 3D image representation. To make the scheme invariant against view synthesis process, the watermark is inserted in the image locations selected by the SIFT (Scale-invariant feature transform) feature points. A novel SIFT feature based coefficient selection scheme has been implemented for watermark embedding by exploiting the shift invariance and directional property of the DIBR based view synthesis process. A coefficient partitioning based blind watermarking method has been included to make the scheme more efficient. A comprehensive set of experiments have been carried out to justify the robustness of the proposed scheme against the view synthesis attack.",

keywords = "watermarking, feature extraction, three-dimensional displays, discrete cosine transforms, image representation, robustness, visualisation",

author = "Shuvendu Rana and Vishavdeep Mattu and Arijit Sur",

year = "2016",

month = jun,

day = "13",

doi = "10.1109/NCVPRIPG.2015.7490030",

language = "English",

booktitle = "2015 5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2015",

publisher = "IEEE",

note = "5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2015 ; Conference date: 16-12-2015 Through 19-12-2015",

}

Rana, S, Mattu, V & Sur, A 2016, SIFT based view invariant watermarking for DIBR 3D image. in 2015 5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2015., 7490030, IEEE, Piscataway, NJ, 5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2015, Patna, Bihar, India, 16/12/15. https://doi.org/10.1109/NCVPRIPG.2015.7490030

TY - GEN

T1 - SIFT based view invariant watermarking for DIBR 3D image

AU - Rana, Shuvendu

AU - Mattu, Vishavdeep

AU - Sur, Arijit

PY - 2016/6/13

Y1 - 2016/6/13

N2 - In this paper, a view invariant watermarking scheme is proposed for depth image based rendering (DIBR) 3D image representation. To make the scheme invariant against view synthesis process, the watermark is inserted in the image locations selected by the SIFT (Scale-invariant feature transform) feature points. A novel SIFT feature based coefficient selection scheme has been implemented for watermark embedding by exploiting the shift invariance and directional property of the DIBR based view synthesis process. A coefficient partitioning based blind watermarking method has been included to make the scheme more efficient. A comprehensive set of experiments have been carried out to justify the robustness of the proposed scheme against the view synthesis attack.

AB - In this paper, a view invariant watermarking scheme is proposed for depth image based rendering (DIBR) 3D image representation. To make the scheme invariant against view synthesis process, the watermark is inserted in the image locations selected by the SIFT (Scale-invariant feature transform) feature points. A novel SIFT feature based coefficient selection scheme has been implemented for watermark embedding by exploiting the shift invariance and directional property of the DIBR based view synthesis process. A coefficient partitioning based blind watermarking method has been included to make the scheme more efficient. A comprehensive set of experiments have been carried out to justify the robustness of the proposed scheme against the view synthesis attack.

KW - watermarking

KW - feature extraction

KW - three-dimensional displays

KW - discrete cosine transforms

KW - image representation

KW - robustness

KW - visualisation

UR - http://www.scopus.com/inward/record.url?scp=84979574371&partnerID=8YFLogxK

UR - http://www.iitp.ac.in/ncvpripg/index.html

U2 - 10.1109/NCVPRIPG.2015.7490030

DO - 10.1109/NCVPRIPG.2015.7490030

M3 - Conference contribution book

AN - SCOPUS:84979574371

BT - 2015 5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2015

PB - IEEE

CY - Piscataway, NJ

T2 - 5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2015

Y2 - 16 December 2015 through 19 December 2015

ER -

SIFT based view invariant watermarking for DIBR 3D image

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this