Full reference objective quality assessment for reconstructed background images

Aditee Shrotre, Lina Karam

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

With an increased interest in applications that require a clean background image, such as video surveillance, object tracking, street view imaging and location-based services on web-based maps, multiple algorithms have been developed to reconstruct a background image from cluttered scenes. Traditionally, statistical measures and existing image quality techniques have been applied for evaluating the quality of the reconstructed background images. Though these quality assessment methods have been widely used in the past, their performance in evaluating the perceived quality of the reconstructed background image has not been verified. In this work, we discuss the shortcomings in existing metrics and propose a full reference Reconstructed Background image Quality Index (RBQI) that combines color and structural information at multiple scales using a probability summation model to predict the perceived quality in the reconstructed background image given a reference image. To compare the performance of the proposed quality index with existing image quality assessment measures, we construct two different datasets consisting of reconstructed background images and corresponding subjective scores. The quality assessment measures are evaluated by correlating their objective scores with human subjective ratings. The correlation results show that the proposed RBQI outperforms all the existing approaches. Additionally, the constructed datasets and the corresponding subjective scores provide a benchmark to evaluate the performance of future metrics that are developed to evaluate the perceived quality of reconstructed background images.

Original languageEnglish (US)
Article number82
JournalJournal of Imaging
Volume4
Issue number6
DOIs
StatePublished - Jan 1 2018

Fingerprint

Image quality
Benchmarking
Color
Location based services
Imaging techniques
Datasets

Keywords

  • Background reconstruction
  • Image dataset
  • Image quality assessment
  • Objective quality metric
  • Perceptual quality
  • Subjective evaluation

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Full reference objective quality assessment for reconstructed background images. / Shrotre, Aditee; Karam, Lina.

In: Journal of Imaging, Vol. 4, No. 6, 82, 01.01.2018.

Research output: Contribution to journalArticle

@article{ea9d7664bd3b43969e09399e24e142e3,
title = "Full reference objective quality assessment for reconstructed background images",
abstract = "With an increased interest in applications that require a clean background image, such as video surveillance, object tracking, street view imaging and location-based services on web-based maps, multiple algorithms have been developed to reconstruct a background image from cluttered scenes. Traditionally, statistical measures and existing image quality techniques have been applied for evaluating the quality of the reconstructed background images. Though these quality assessment methods have been widely used in the past, their performance in evaluating the perceived quality of the reconstructed background image has not been verified. In this work, we discuss the shortcomings in existing metrics and propose a full reference Reconstructed Background image Quality Index (RBQI) that combines color and structural information at multiple scales using a probability summation model to predict the perceived quality in the reconstructed background image given a reference image. To compare the performance of the proposed quality index with existing image quality assessment measures, we construct two different datasets consisting of reconstructed background images and corresponding subjective scores. The quality assessment measures are evaluated by correlating their objective scores with human subjective ratings. The correlation results show that the proposed RBQI outperforms all the existing approaches. Additionally, the constructed datasets and the corresponding subjective scores provide a benchmark to evaluate the performance of future metrics that are developed to evaluate the perceived quality of reconstructed background images.",
keywords = "Background reconstruction, Image dataset, Image quality assessment, Objective quality metric, Perceptual quality, Subjective evaluation",
author = "Aditee Shrotre and Lina Karam",
year = "2018",
month = "1",
day = "1",
doi = "10.3390/jimaging4060082",
language = "English (US)",
volume = "4",
journal = "Journal of Imaging",
issn = "2313-433X",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "6",

}

TY - JOUR

T1 - Full reference objective quality assessment for reconstructed background images

AU - Shrotre, Aditee

AU - Karam, Lina

PY - 2018/1/1

Y1 - 2018/1/1

N2 - With an increased interest in applications that require a clean background image, such as video surveillance, object tracking, street view imaging and location-based services on web-based maps, multiple algorithms have been developed to reconstruct a background image from cluttered scenes. Traditionally, statistical measures and existing image quality techniques have been applied for evaluating the quality of the reconstructed background images. Though these quality assessment methods have been widely used in the past, their performance in evaluating the perceived quality of the reconstructed background image has not been verified. In this work, we discuss the shortcomings in existing metrics and propose a full reference Reconstructed Background image Quality Index (RBQI) that combines color and structural information at multiple scales using a probability summation model to predict the perceived quality in the reconstructed background image given a reference image. To compare the performance of the proposed quality index with existing image quality assessment measures, we construct two different datasets consisting of reconstructed background images and corresponding subjective scores. The quality assessment measures are evaluated by correlating their objective scores with human subjective ratings. The correlation results show that the proposed RBQI outperforms all the existing approaches. Additionally, the constructed datasets and the corresponding subjective scores provide a benchmark to evaluate the performance of future metrics that are developed to evaluate the perceived quality of reconstructed background images.

AB - With an increased interest in applications that require a clean background image, such as video surveillance, object tracking, street view imaging and location-based services on web-based maps, multiple algorithms have been developed to reconstruct a background image from cluttered scenes. Traditionally, statistical measures and existing image quality techniques have been applied for evaluating the quality of the reconstructed background images. Though these quality assessment methods have been widely used in the past, their performance in evaluating the perceived quality of the reconstructed background image has not been verified. In this work, we discuss the shortcomings in existing metrics and propose a full reference Reconstructed Background image Quality Index (RBQI) that combines color and structural information at multiple scales using a probability summation model to predict the perceived quality in the reconstructed background image given a reference image. To compare the performance of the proposed quality index with existing image quality assessment measures, we construct two different datasets consisting of reconstructed background images and corresponding subjective scores. The quality assessment measures are evaluated by correlating their objective scores with human subjective ratings. The correlation results show that the proposed RBQI outperforms all the existing approaches. Additionally, the constructed datasets and the corresponding subjective scores provide a benchmark to evaluate the performance of future metrics that are developed to evaluate the perceived quality of reconstructed background images.

KW - Background reconstruction

KW - Image dataset

KW - Image quality assessment

KW - Objective quality metric

KW - Perceptual quality

KW - Subjective evaluation

UR - http://www.scopus.com/inward/record.url?scp=85063140944&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063140944&partnerID=8YFLogxK

U2 - 10.3390/jimaging4060082

DO - 10.3390/jimaging4060082

M3 - Article

VL - 4

JO - Journal of Imaging

JF - Journal of Imaging

SN - 2313-433X

IS - 6

M1 - 82

ER -