Study on image quality assessment under foggy condition

Xiangfeng Xue; Hui Yang; Song Xue; Zhibin Hou; Lan Hu

doi:10.1117/12.2284312

24 October 2017 Study on image quality assessment under foggy condition

Xiangfeng Xue, Hui Yang, Song Xue, Zhibin Hou, Lan Hu

Proceedings Volume 10462, AOPC 2017: Optical Sensing and Imaging Technology and Applications; 1046220 (2017) https://doi.org/10.1117/12.2284312
Event: Applied Optics and Photonics China (AOPC2017), 2017, Beijing, China

Abstract

Image quality assessment can provide important prior knowledge for subsequent picture processing, but it may be challenged by foggy distortion under a foggy weather condition, and there is no effective solution for the distorted images. In this paper, an effective image quality assessment method under foggy condition was proposed, with the purpose of giving image quality scores and their changes under different foggy density. Based on 29 reference images in LIVE image database, different image samples in a foggy day were generated. On the basis of analyzing foggy influences on image quality, this paper extracted features representing image scene characteristics in foggy day, used a method based on codebook to encode features, and trained features after using pooling strategy to encode, and, finally acquired image quality scores through the regression mode. Experimental results showed that, the higher accuracy, subjective and objective consistency, and higher identification on image quality under different foggy density can be obtained by the codebook-based method rather than other normal algorithms. The algorithm in this paper can solve the problem of image quality assessment under foggy condition.

Citation Download Citation

Xiangfeng Xue, Hui Yang, Song Xue, Zhibin Hou, and Lan Hu "Study on image quality assessment under foggy condition", Proc. SPIE 10462, AOPC 2017: Optical Sensing and Imaging Technology and Applications, 1046220 (24 October 2017); https://doi.org/10.1117/12.2284312

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available