KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment

Vlad Hosu, Hanhe Lin, Tamas Sziranyi, Dietmar Saupe

Research output: Contribution to journalArticlepeer-review

220 Citations (Scopus)


Deep learning methods for image quality assessment (IQA) are limited due to the small size of existing datasets. Extensive datasets require substantial resources both for generating publishable content and annotating it accurately. We present a systematic and scalable approach to creating KonIQ-10k, the largest IQA dataset to date, consisting of 10,073 quality scored images. It is the first in-the-wild database aiming for ecological validity, concerning the authenticity of distortions, the diversity of content, and quality-related indicators. Through the use of crowdsourcing, we obtained 1.2 million reliable quality ratings from 1,459 crowd workers, paving the way for more general IQA models. We propose a novel, deep learning model (KonCept512), to show an excellent generalization beyond the test set (0.921 SROCC), to the current state-of-the-art database LIVE-in-the-Wild (0.825 SROCC). The model derives its core performance from the InceptionResNet architecture, being trained at a higher resolution than previous models ( 512\times 384 ). Correlation analysis shows that KonCept512 performs similar to having 9 subjective scores for each test image.

Original languageEnglish
Article number8968750
Pages (from-to)4041-4056
Number of pages16
JournalIEEE Transactions on Image Processing
Early online date24 Jan 2020
Publication statusPublished - 2020


  • Blind image quality assessment
  • Convolutional neural networks
  • Crowdsourcing
  • Deep learning
  • Diversity sampling
  • Image database
  • Subjective image quality assessment

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment'. Together they form a unique fingerprint.

Cite this