A Neuro-Fuzzy Approach for Compensating Color Backlight Images

Authors:
Mu-Chun Su;Yuan-Shao Yang;Jonathan Lee;Gwo-Dong Chen
Affiliations:
Department of Computer Science & Information Engineering, National Central University, Taiwan, R.O.C;Department of Computer Science & Information Engineering, National Central University, Taiwan, R.O.C;Department of Computer Science & Information Engineering, National Central University, Taiwan, R.O.C;Department of Computer Science & Information Engineering, National Central University, Taiwan, R.O.C
Venue:
Neural Processing Letters
Year:
2006

Citing 10
Cited 1

Adaptive histogram equalization and its variations

Computer Vision, Graphics, and Image Processing
Digital Image Processing

Digital Image Processing
Shape preserving local contrast enhancement

ICIP '97 Proceedings of the 1997 International Conference on Image Processing (ICIP '97) 3-Volume Set-Volume 1 - Volume 1
A multiscale contrast enhancement method

ICIP '97 Proceedings of the 1997 International Conference on Image Processing (ICIP '97) 3-Volume Set-Volume 1 - Volume 1
Fuzzy basis functions: comparisons with other basis functions

IEEE Transactions on Fuzzy Systems
Contrast enhancement using brightness preserving bi-histogram equalization

IEEE Transactions on Consumer Electronics
Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering

IEEE Transactions on Consumer Electronics
Adaptive gamma processing of the video cameras for the expansion of the dynamic range

IEEE Transactions on Consumer Electronics
Adaptive image contrast enhancement using generalizations of histogram equalization

IEEE Transactions on Image Processing
An advanced contrast enhancement using partially overlapped sub-block histogram equalization

IEEE Transactions on Circuits and Systems for Video Technology

Application areas of AIS: The past, the present and the future

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a neuro-fuzzy approach for compensating exposure in the case of backlighting, regardless of the position of objects. To achieve the compensation effect, the fuzzy C-means algorithm is first used to extract features from a backlight image. Then these extracted features are presented to a trained artificial immune system based neuro-fuzzy system (AISNFS) to estimate the amount of compensation. Finally, the estimated amount of compensation incorporated with a compensation equation is used to enhance the intensity component of the backlight image to produce a compensated image. Several backlight images were used to test the performance of the algorithm.