Haze Image Database and Preliminary Assessments

Ying Chu, Zhiyuan Chen, Yu Fu, Hengyong Yu


Published in:Fully3D 2017 Proceedings


haze image, subjective evaluation, mean opinion score, image database, image quality assessment
A database named HID2016 is built to provide a public benchmark to blindly evaluate image quality of haze images. The image set comes from a photographic exhibition held in China in 2014, and the single-stimulus method is adopted to develop the subjective evaluation experiments on those images. The contribution of this database not only lies in the fact that HID2016 is the first image database aiming at evaluating quality of haze images, but also lies in that the environmental indexes of each haze picture are provided, including air quality index (AQI), fine particulate matter (PM2.5) index and inhalable particles (PM10) index, which can help to explore the relationship between image quality and air quality. A three-order polynomial fitting function is adopted to simulate the experimental data, aiming at revealing the relationship between subjective score and environmental index. The experimental results show that the subjective scores in the HID2016 database keep a good accordance with the visual quality of haze images, and they roughly negative correlate with the air quality.
Ying Chu
Shenzhen University, China
Zhiyuan Chen
Shenzhen University, China
Yu Fu
Shenzhen University, China
Hengyong Yu
University of Massachusetts Lowell, USA
  1. M. Ding, and R. Tong, "Efficient dark channel based image dehazing using quadtrees," Science China Information Sciences, vol. 56, pp. 1-9, 2012.
  2. Q. Liu, M. Chen, and D. Zhou, "Single image haze removal via depth-based contrast stretching transform," Science China Information Sciences, vol. 58, pp. 1-17, 2014.
  3. Y. H. Shiau, P. Y. Chen, H. Y. Yang, C. H. Chen, and S. S. Wang, "Weighted haze removal method with halo prevention," Journal of Visual Communication and Image Representation, vol. 25, pp. 445-453, 2014.
  4. Z. Wang, and Y. Feng, "Fast single haze image enhancement," Computers & Electrical Engineering, vol. 40, pp. 785-795, 2014.
  5. J.-B. Wang, N. He, L.-L. Zhang, and K. Lu, "Single image dehazing with a physical model and dark channel prior," Neurocomputing, vol. 149, Part B, pp. 718-728, 2015.
  6. D. Wu, Q. Zhu, J. Wang, Y. Xie, and L. Wang, "Image Haze Removal Status, Challenges and Prospects," Proc. of 2014 4th IEEE International Conference on Information Science and Technology, pp. 492-497, 2014.
  7. S. Fang, J. Yang, J. Zhan, H. Yuan, and R. Rao, "Image Quality Assessment on Image Haze Removal," Proc. of Chinese Control and Decision Conference, pp. 610-614, 2011.
  8. J. Li, H. Zhang, D. Yuan, and M. Sun, "Single image dehazing using the change of detail prior," Neurocomputing, vol. 156, pp. 1-11, 2015.
  9. F. Guo, J. Tang, and Z.-X. Cai, "Image dehazing based on haziness analysis," International Journal of Automation and Computing, vol. 11, pp. 78-86, 2014.
  10. N. Hautiere, J.-P. Tarel, D. Aubert, and E. Dumont, "Blind contrast enhancement assessment by gradient ratioing at visible edges," Image Analysis and Stereology, vol. 27, pp. 87-95, 2008.