JISE


  [ 1 ] [ 2 ] [ 3 ] [ 4 ] [ 5 ] [ 6 ] [ 7 ] [ 8 ] [ 9 ] [ 10 ] [ 11 ] [ 12 ] [ 13 ]


Journal of Information Science and Engineering, Vol. 34 No. 3, pp. 701-720


Using a Hybrid of Morphological Operation and Neuro-fuzzy Filter for Transmission Map Refinement and Halation Elimination in Weather Degraded Images


HSUEH-YI LIN1, CHENG-JIAN LIN1,+ AND MEI-LING HUANG2
1Department of Computer Science and Information Engineering
2Department of Industrial Engineering and Management
National Chin-Yi University of Technology
Taichung City, 411 Taiwan


  For photographs taken in outdoor environments, the air medium causes light attenuation, which reduces image quality; this effect is particularly obvious in hazy environments. To eliminate the hazy effect in images and improve the image quality, the present study proposes an efficient hybrid method. The proposed fuzzy estimator was adopted to estimate variations in light attenuation, and morphological erosion and a neuro-fuzzy filter proposed by this study were employed to refine the transmission map and eliminate the halation. Finally, an estimated mean value for atmospheric light was applied to calculate the color vector of atmospheric light to eliminate the color cast. Experimental results indicate that the proposed hybrid method is superior to other dehazing methods.


Keywords: dehazing, fuzzy estimator, neuro-fuzzy filter, learning algorithm, transmission map, halation

  Retrieve PDF document (JISE_201803_08.pdf)