Journal of IKEEE (전기전자학회논문지)

Institute of Korean Electrical and Electronics Engineers (한국전기전자학회)
권호 표지
DOI QR코드

DOI QR Code

Improving Performance of Machine Learning-based Haze Removal Algorithms with Enhanced Training Database

  • Ngo, Dat (Dept. of Electronics Engineering, Dong-A University) ;
  • Kang, Bongsoon (Dept. of Electronics Engineering, Dong-A University)
  • Received : 2018.11.23
  • Accepted : 2018.12.21
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Haze removal is an object of scientific desire due to its various practical applications. Existing algorithms are founded upon histogram equalization, contrast maximization, or the growing trend of applying machine learning in image processing. Since machine learning-based algorithms solve problems based on the data, they usually perform better than those based on traditional image processing/computer vision techniques. However, to achieve such a high performance, one of the requisites is a large and reliable training database, which seems to be unattainable owing to the complexity of real hazy and haze-free images acquisition. As a result, researchers are currently using the synthetic database, obtained by introducing the synthetic haze drawn from the standard uniform distribution into the clear images. In this paper, we propose the enhanced equidistribution, improving upon our previous study on equidistribution, and use it to make a new database for training machine learning-based haze removal algorithms. A large number of experiments verify the effectiveness of our proposed methodology.

Keywords

JGGJB@_2018_v22n4_948_f0001.png 이미지

Fig. 1. Training procedure proposed by Zhu et al. consists of training data preparation (upper part) and supervised learning process (lower part)

JGGJB@_2018_v22n4_948_f0002.png 이미지

Fig. 2. Histogram of 1,000 random numbers drawn from SUD on the open interval (0, 1)

JGGJB@_2018_v22n4_948_f0003.png 이미지

Fig. 3. An example of applying the enhanced equidistribution to a small random sequence

Table 1. Average e, r values on IVC

JGGJB@_2018_v22n4_948_t0001.png 이미지

Table 2. Average TMQI, MSE values on FRIDA2

JGGJB@_2018_v22n4_948_t0002.png 이미지

References

  1. Z. Xu, X. Liu, and N. Ji, "Fog Removal from Color Images using Contrast Limited Adaptive Histogram Equalization," 2009 2nd International Congress on Image and Signal Processing, pp. 1-5, 2009. DOI:10.1109/CISP.2009.5301485
  2. R. Tan, "Visibility in bad weather from a single image," 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2008. DOI:10.1109/CVPR.2008.4587643
  3. Q. Zhu, J. Mai, and L. Shao, "A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior," IEEE Transactions on Image Processing, vol.24, no.11, pp.3522-3533, 2015. DOI:10.1109/TIP.2015.2446191
  4. D. Ngo and B. Kang, "A New Data Preparation Methodology in Machine Learning-based Haze Removal Algorithms," submitted to International Conference on Electronics, Information, and Communication (ICEIC) 2019. DOI:10.1109/ICIP.2015.7351475
  5. K. Ma, W. Liu, and Z. Wang, "Perceptual evaluation of single image dehazing algorithm," 2015 IEEE International Conference on Image Processing (ICIP), pp.3600-3604, 2015. DOI:10.1109/ICIP.2015.7351475
  6. J. P. Tarel, N. Hautiere, L. Caraffa, A. Cord, H. Halmaoui, and D. Gruyer, "Vision Enhancement in Homogeneous and Heterogeneous Fog," IEEE Intelligent Transportation Systems Magazine, vol.4, no.2, pp.6-20, 2012. DOI:10.1109/MITS.2012.2189969
  7. N. Hautiere, J. P. Tarel, D. Aubert, and E. Dumont, "BLIND CONTRAST ENHANCEMENT ASSESSMENT BY GRADIENT RATIOING AT VISIBLE EDGES," Image Analysis & Stereology, vol.27, no.2, pp.87-95, 2011. DOI:10.5566/ias.v27.p87-95
  8. H. Yeganeh and Z. Wang, "Objective Quality Assessment of Tone-Mapped Images," IEEE Transactions on Image Processing, vol.22, no.2, pp.657-667, 2013. DOI:10.1109/TIP.2012.2221725