Enhanced just noticeable difference (JND) estimation with image decomposition for separating edge and textured regions

Anmin Liu; Weisi Lin; Fan Zhang; Manoranjan Paul

doi:10.1109/ICIP.2010.5653355

Enhanced just noticeable difference (JND) estimation with image decomposition for separating edge and textured regions

Anmin Liu, Weisi Lin, Fan Zhang, Manoranjan Paul

Research output: Book chapter/Published conference paper › Conference paper › peer-review

6 Citations (Scopus)

49 Downloads (Pure)

Abstract

Contrast masking (CM) on edge and textured regions have to be distinguished since distortions on edge regions are easier to be noticed than that on textured regions. Therefore, how to efficiently estimate the CM on edge and textured regions of an image is a key issue for accurate JND (Just Noticeable Difference) estimation. An enhanced image domain JND estimator is devised in this paper with new model for CM. We use the total variation method to obtain a structural image (which contains edge information) and a textural image (which contains texture information) from the input image, and then evaluate the CM for the two images separately rather than the whole image, and hence edge and texture are better distinguished and the under-estimation of JND on textured regions can be effectively avoided. Experimental results of subjective viewing confirm that the proposed model is capable of determining more accurate visibility thresholds.

Original language	English
Title of host publication	IEEE International Conference on Image Processing
Place of Publication	USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	317-320
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2010.5653355
Publication status	Published - 2010
Event	ICIP 17th International Conference - Hong Kong, Hong Kong Duration: 26 Sept 2010 → 29 Sept 2010

Conference

Conference	ICIP 17th International Conference
Country/Territory	Hong Kong
Period	26/09/10 → 29/09/10

Access to Document

10.1109/ICIP.2010.5653355

23104 ManusciptAccepted author manuscript, 1.99 MB

Cite this

@inproceedings{b5107221bf9140cbaaa38bc33bff3b14,

title = "Enhanced just noticeable difference (JND) estimation with image decomposition for separating edge and textured regions",

abstract = "Contrast masking (CM) on edge and textured regions have to be distinguished since distortions on edge regions are easier to be noticed than that on textured regions. Therefore, how to efficiently estimate the CM on edge and textured regions of an image is a key issue for accurate JND (Just Noticeable Difference) estimation. An enhanced image domain JND estimator is devised in this paper with new model for CM. We use the total variation method to obtain a structural image (which contains edge information) and a textural image (which contains texture information) from the input image, and then evaluate the CM for the two images separately rather than the whole image, and hence edge and texture are better distinguished and the under-estimation of JND on textured regions can be effectively avoided. Experimental results of subjective viewing confirm that the proposed model is capable of determining more accurate visibility thresholds.",

keywords = "Open access version available, Contrast masking, Image decomposition, JND, Visibility threshold",

author = "Anmin Liu and Weisi Lin and Fan Zhang and Manoranjan Paul",

note = "Imported on 03 May 2017 - DigiTool details were: publisher = USA: Institute of Electrical and Electronics Engineers (IEEE) Press, 2010. editor/s (773b) = Professor Wan-Chi Siu; Event dates (773o) = 26-29 September 2010; Parent title (773t) = IEEE International Conference on Image Processing. ISSNs: 1522-4880; ; ICIP 17th International Conference ; Conference date: 26-09-2010 Through 29-09-2010",

year = "2010",

doi = "10.1109/ICIP.2010.5653355",

language = "English",

pages = "317--320",

booktitle = "IEEE International Conference on Image Processing",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

}

Liu, A, Lin, W, Zhang, F & Paul, M 2010, Enhanced just noticeable difference (JND) estimation with image decomposition for separating edge and textured regions. in IEEE International Conference on Image Processing. IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 317-320, ICIP 17th International Conference, Hong Kong, 26/09/10. https://doi.org/10.1109/ICIP.2010.5653355

Enhanced just noticeable difference (JND) estimation with image decomposition for separating edge and textured regions. / Liu, Anmin; Lin, Weisi; Zhang, Fan et al.
IEEE International Conference on Image Processing. USA: IEEE, Institute of Electrical and Electronics Engineers, 2010. p. 317-320.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Enhanced just noticeable difference (JND) estimation with image decomposition for separating edge and textured regions

AU - Liu, Anmin

AU - Lin, Weisi

AU - Zhang, Fan

AU - Paul, Manoranjan

N1 - Imported on 03 May 2017 - DigiTool details were: publisher = USA: Institute of Electrical and Electronics Engineers (IEEE) Press, 2010. editor/s (773b) = Professor Wan-Chi Siu; Event dates (773o) = 26-29 September 2010; Parent title (773t) = IEEE International Conference on Image Processing. ISSNs: 1522-4880;

PY - 2010

Y1 - 2010

N2 - Contrast masking (CM) on edge and textured regions have to be distinguished since distortions on edge regions are easier to be noticed than that on textured regions. Therefore, how to efficiently estimate the CM on edge and textured regions of an image is a key issue for accurate JND (Just Noticeable Difference) estimation. An enhanced image domain JND estimator is devised in this paper with new model for CM. We use the total variation method to obtain a structural image (which contains edge information) and a textural image (which contains texture information) from the input image, and then evaluate the CM for the two images separately rather than the whole image, and hence edge and texture are better distinguished and the under-estimation of JND on textured regions can be effectively avoided. Experimental results of subjective viewing confirm that the proposed model is capable of determining more accurate visibility thresholds.

AB - Contrast masking (CM) on edge and textured regions have to be distinguished since distortions on edge regions are easier to be noticed than that on textured regions. Therefore, how to efficiently estimate the CM on edge and textured regions of an image is a key issue for accurate JND (Just Noticeable Difference) estimation. An enhanced image domain JND estimator is devised in this paper with new model for CM. We use the total variation method to obtain a structural image (which contains edge information) and a textural image (which contains texture information) from the input image, and then evaluate the CM for the two images separately rather than the whole image, and hence edge and texture are better distinguished and the under-estimation of JND on textured regions can be effectively avoided. Experimental results of subjective viewing confirm that the proposed model is capable of determining more accurate visibility thresholds.

KW - Open access version available

KW - Contrast masking

KW - Image decomposition

KW - JND

KW - Visibility threshold

U2 - 10.1109/ICIP.2010.5653355

DO - 10.1109/ICIP.2010.5653355

M3 - Conference paper

SP - 317

EP - 320

BT - IEEE International Conference on Image Processing

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

T2 - ICIP 17th International Conference

Y2 - 26 September 2010 through 29 September 2010

ER -

Enhanced just noticeable difference (JND) estimation with image decomposition for separating edge and textured regions

Abstract

Conference

Access to Document

Fingerprint

Cite this