No-reference perceptual blur model based on inherent sharpness

Seungchul Ryu, Kwanghoon Sohn

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

3 Citations (Scopus)

Abstract

An objective blurriness model is useful in various image processing applications. Especially, a no-reference model is expected as a highly desirable approach due to its applicability to wide range of applications. Blurriness of an image is known as to be commonly induced by the attenuation of spatial high-frequency and thus most conventional researches focused on a model estimating the amount of spatial high-frequency. However, the human-perceived blurriness might be varied across image contents. Very few researches have been investigated the human visual system model for the blurriness perception. To address the lack of an efficient model, this paper presents the blurriness perception model designed as a spatially varying function based on the inherent sharpness. Pixel-wise perceptual blurriness is computed employing the blurriness perception model and then integrated into an overall blurriness index using saliency information. The experimental comparisons with state-of-the-arts blurriness models for extensive public databases show that the proposed model is well-correlated with the subjective scores across different content of images, and outperforms the compared models.

Original languageEnglish
Title of host publication2014 IEEE International Conference on Image Processing, ICIP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages580-584
Number of pages5
ISBN (Electronic)9781479957514
DOIs
Publication statusPublished - 2014 Jan 28

Publication series

Name2014 IEEE International Conference on Image Processing, ICIP 2014

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'No-reference perceptual blur model based on inherent sharpness'. Together they form a unique fingerprint.

Cite this