Disregarding the big picture: towards local image quality assessment

Oliver Wiedemann, Vlad Hosu, Hanhe Lin, Dietmar Saupe

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

12 Citations (Scopus)

Abstract

Image quality has been studied almost exclusively as a global image property. It is common practice for IQA databases and metrics to quantify this abstract concept with a single number per image. We propose an approach to blind IQA based on a convolutional neural network (patchnet) that was trained on a novel set of 32,000 individually annotated patches of 64×64 pixel. We use this model to generate spatially small local quality maps of images taken from KonIQ-10k, a large and diverse in-the-wild database of authentically distorted images. We show that our local quality indicator correlates well with global MOS, going beyond the predictive ability of quality related attributes such as sharpness. Averaging of patchnet predictions already outperforms classical approaches to global MOS prediction that were trained to include global image features. We additionally experiment with a generic second-stage aggregation CNN to estimate mean opinion scores. Our latter model performs comparable to the state of the art with a PLCC of 0.81 on KonIQ-10k.

Original languageEnglish
Title of host publication2018 10th International Conference on Quality of Multimedia Experience (QoMEX 2018)
PublisherIEEE
Number of pages6
ISBN (Electronic)978-1-5386-2605-4
ISBN (Print)978-1-5386-2606-1
DOIs
Publication statusPublished - 11 Sept 2018
Event10th International Conference on Quality of Multimedia Experience, QoMEX 2018 - Sardinia, Italy
Duration: 29 May 20181 Jun 2018

Publication series

Name2018 10th International Conference on Quality of Multimedia Experience, QoMEX 2018
ISSN (Electronic)2472-7814

Conference

Conference10th International Conference on Quality of Multimedia Experience, QoMEX 2018
Country/TerritoryItaly
CitySardinia
Period29/05/181/06/18

ASJC Scopus subject areas

  • Media Technology
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'Disregarding the big picture: towards local image quality assessment'. Together they form a unique fingerprint.

Cite this