基于双边伽马校正的保亮度图像增强方法

图像增强的许多实际应用需要保持输入图像的亮度,因此提出基于伽马校正及多尺度图像融合的保亮度图像增强方法。分析伽马校正曲线对图像中过暗和过亮区域的影响,设计能够同时改善过暗和过亮区域对比度的双边伽马校正曲线。对双边伽马校正所生成的两幅校正图像进行多尺度图像融合,其中低频子带图像采用加权平均融合规则以保持亮度,高频子带图像采用平均选取融合规则以突出细节。该方法是一种空频域相结合的保亮度图像增强方法。实验结果表明,该方法在避免过增强、保亮度和突出细节三方面均取得良好效果,且优于一些经典的基于直方图均衡化思想的图像增强方法。

BRIGHTNESS PRESERVING IMAGE ENHANCEMENT METHOD BASED ON BILATERAL GAMMA CORRECTION

Maintaining the brightness of input images are required to many practical applications of image enhancement.Therefore,this paper presented a brightness preserving image enhancement method based on gamma correction and multi-scale image fusion.We designed bi-gamma correction curves to improve the contrast of over-bright and over-dark regions by analyzing the influence of gamma correction curve on both regions.Then,these two revised images,generated by bi-gamma correction,were integrated by multi-scale image fusion.A weighted average fusion rule was adopted for low frequency sub-band images to keep brightness,and an average and selection fusion rule was adopted for high frequency sub-band images to highlight details.This method was performed by a combination of spatial and frequency domain.Experimental results indicate that this method yields good performance in three aspects of avoiding over-enhancement,preserving brightness and enhancing details,and outperforms some image enhancement methods based on the concept of histogram equalization.