Registration based retargeted image quality assessment

Bo Zhang, Pedro V. Sander, Amine Bermak

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In recent years, a large number of image retargeting methods have been proposed. Measuring their relative quality is of significant importance, and there is still room for improvement in the effectiveness of objective retargeted image quality assessment (RIQA) metrics. In this paper, we propose a registration based RIQA metric. First, we propose to calculate the flow map using an image registration method which involves SURF point matching and halfway domain optimization. Using the computed flow map and the source image, we propose an LGI metric which contains three factors: 1) local similarity which assesses the local aspect ratio change, edge directional similarity and flow smoothness; 2) global distortion which measures the appearance change of salient objects; 3) salient information loss. Comparing with other six metrics, our LGI metric correlates the best with subjective rankings on the RetargetMe dataset.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1258-1262
Number of pages5
ISBN (Electronic)9781509041176
DOIs
Publication statusPublished - 16 Jun 2017
Event2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States
Duration: 5 Mar 20179 Mar 2017

Other

Other2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
CountryUnited States
CityNew Orleans
Period5/3/179/3/17

Fingerprint

Image quality
Image registration
Aspect ratio

Keywords

  • dense correspondence
  • edge direction similarity
  • retargeted image quality assessment (RIQA)
  • salient object segmentation

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Zhang, B., Sander, P. V., & Bermak, A. (2017). Registration based retargeted image quality assessment. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings (pp. 1258-1262). [7952358] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2017.7952358

Registration based retargeted image quality assessment. / Zhang, Bo; Sander, Pedro V.; Bermak, Amine.

2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1258-1262 7952358.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, B, Sander, PV & Bermak, A 2017, Registration based retargeted image quality assessment. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7952358, Institute of Electrical and Electronics Engineers Inc., pp. 1258-1262, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, United States, 5/3/17. https://doi.org/10.1109/ICASSP.2017.7952358
Zhang B, Sander PV, Bermak A. Registration based retargeted image quality assessment. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1258-1262. 7952358 https://doi.org/10.1109/ICASSP.2017.7952358
Zhang, Bo ; Sander, Pedro V. ; Bermak, Amine. / Registration based retargeted image quality assessment. 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1258-1262
@inproceedings{15023e09f090487ab6f970847e8e582d,
title = "Registration based retargeted image quality assessment",
abstract = "In recent years, a large number of image retargeting methods have been proposed. Measuring their relative quality is of significant importance, and there is still room for improvement in the effectiveness of objective retargeted image quality assessment (RIQA) metrics. In this paper, we propose a registration based RIQA metric. First, we propose to calculate the flow map using an image registration method which involves SURF point matching and halfway domain optimization. Using the computed flow map and the source image, we propose an LGI metric which contains three factors: 1) local similarity which assesses the local aspect ratio change, edge directional similarity and flow smoothness; 2) global distortion which measures the appearance change of salient objects; 3) salient information loss. Comparing with other six metrics, our LGI metric correlates the best with subjective rankings on the RetargetMe dataset.",
keywords = "dense correspondence, edge direction similarity, retargeted image quality assessment (RIQA), salient object segmentation",
author = "Bo Zhang and Sander, {Pedro V.} and Amine Bermak",
year = "2017",
month = "6",
day = "16",
doi = "10.1109/ICASSP.2017.7952358",
language = "English",
pages = "1258--1262",
booktitle = "2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Registration based retargeted image quality assessment

AU - Zhang, Bo

AU - Sander, Pedro V.

AU - Bermak, Amine

PY - 2017/6/16

Y1 - 2017/6/16

N2 - In recent years, a large number of image retargeting methods have been proposed. Measuring their relative quality is of significant importance, and there is still room for improvement in the effectiveness of objective retargeted image quality assessment (RIQA) metrics. In this paper, we propose a registration based RIQA metric. First, we propose to calculate the flow map using an image registration method which involves SURF point matching and halfway domain optimization. Using the computed flow map and the source image, we propose an LGI metric which contains three factors: 1) local similarity which assesses the local aspect ratio change, edge directional similarity and flow smoothness; 2) global distortion which measures the appearance change of salient objects; 3) salient information loss. Comparing with other six metrics, our LGI metric correlates the best with subjective rankings on the RetargetMe dataset.

AB - In recent years, a large number of image retargeting methods have been proposed. Measuring their relative quality is of significant importance, and there is still room for improvement in the effectiveness of objective retargeted image quality assessment (RIQA) metrics. In this paper, we propose a registration based RIQA metric. First, we propose to calculate the flow map using an image registration method which involves SURF point matching and halfway domain optimization. Using the computed flow map and the source image, we propose an LGI metric which contains three factors: 1) local similarity which assesses the local aspect ratio change, edge directional similarity and flow smoothness; 2) global distortion which measures the appearance change of salient objects; 3) salient information loss. Comparing with other six metrics, our LGI metric correlates the best with subjective rankings on the RetargetMe dataset.

KW - dense correspondence

KW - edge direction similarity

KW - retargeted image quality assessment (RIQA)

KW - salient object segmentation

UR - http://www.scopus.com/inward/record.url?scp=85023740437&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023740437&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7952358

DO - 10.1109/ICASSP.2017.7952358

M3 - Conference contribution

SP - 1258

EP - 1262

BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -