Detection of images degraded by rain using image quality assessment

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F22%3A50019131" target="_blank" >RIV/62690094:18450/22:50019131 - isvavai.cz</a>

Result on the web

<a href="https://link.springer.com/article/10.1007/s11042-022-13041-5" target="_blank" >https://link.springer.com/article/10.1007/s11042-022-13041-5</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s11042-022-13041-5" target="_blank" >10.1007/s11042-022-13041-5</a>

Result language

angličtina

Original language name

Detection of images degraded by rain using image quality assessment

Original language description

Various weather conditions degrade images, and hence the quality of the images is compromised to a large extent. Atmospheric conditions like Rain, Fog, Haze, Mist, etc., degrade scenes, and the scene&apos;s acquisition results in noisy images. The noisy images have less visibility than regular images. Therefore, the images degraded by the weather conditions need some special attention before processing them. Otherwise, the processing of noisy images using the same process applied for noise-free images cannot find the desired results. Hence, the identification of images degraded by weather conditions is essential before further processing. Rain is one of the most complex atmospheric conditions that degraded images. In the case of rain, water droplets present in the air are visible, wherein,in other atmospheric conditions, water droplets cannot be seen. In rainy images, the large size of water droplets in the air causes more complex degradation. This research paper has proposed a technique for detecting images degraded by rain using an image quality assessment approach. We have used no-reference image quality assessment techniques for this work. We have proposed an image quality metric specially designed for the images degraded by rain. We have used the proposed metric along with other state-of-the-art metrics for identifying rainy images. Our proposed technique has been evaluated using a public dataset containing about 1500 images. We found promising results by applying our technique to that dataset to detect images degraded by rain. This technique can help security and surveillance applications, where the automatic selection of degraded frames is crucial.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2022

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Multimedia Tools and Applications

ISSN

1380-7501

e-ISSN

1573-7721

Volume of the periodical

81

Issue of the periodical within the volume

24

Country of publishing house

NL - THE KINGDOM OF THE NETHERLANDS

Number of pages

17

Pages from-to

35445-35461

UT code for WoS article

000784679300018

EID of the result in the Scopus database

2-s2.0-85128549009