원문정보
초록
영어
In order to solve such problems as excessive enhancement and chessboard effect, difficult image brightness keeping and distortion in the image enhancement algorithm based on histogram equalization, an anti-distortion image contrast enhancement algorithm based on fuzzy statistics and sub-histogram equalization is proposed in this article. Specifically, the fuzzy set theory is introduced therein to convert the image into fuzzy matrix; then, by virtue of the membership function and the probability of the image gradation, the weighting function is embedded to construct the weighted fuzzy histogram calculation model; then, the mid-value of the initial image is adopted to divide the fuzzy histogram into two sub-histograms, and the corresponding cumulative density functions are defined, and the transformation models thereof are also constructed; then, the inverse transformation function is established to realize defuzzification and output the enhanced image. The experimental data show: compared with the present image enhancement algorithm based on histogram equalization, this algorithm can significantly eliminate excessive enhancement and noise amplification, thus to not only have better visual enhancement quality and anti-distortion performance, but also have maximum AIC (Average Information Contents) value and minimum NIQE (Natural Image Quality Evaluator) value.
목차
1. Introduction
2. Improved Histogram Equalization
3. Algorithm Design
3.1. Generation of Fuzzy Matrix
3.2. Calculation of Fuzzy Histogram
3.3. Histogram Division and Equalization
3.4. Image Defuzzification
4. Simulation Result and Analysis
4.1. Image Enhancement Effect Comparison
4.2. Objective Evaluation for Enhancement Quality
5. Conclusion
References