基于分段常数直方图模型的亮度保持图像增强  

BRIGHTNESS PRESERVING IMAGE ENHANCEMENT BASED ON PIECEWISE CONSTANT HISTOGRAM MODEL

作　　者：聂超[1] 

机构地区：[1]杭州电子科技大学通信工程学院,浙江杭州310018

出　　处：《南阳理工学院学报》2014年第6期60-64,共5页Journal of Nanyang Institute of Technology

摘　　要：提出了一种新的精确亮度保持对比度增强算法。将目标直方图显式描述为分段常数模型,然后通过亮度保持约束和其他准则确定模型参数,最后应用直方图规定化完成图像增强。实验结果表明,算法在亮度精确保持的同时能够达到较好的图像增强效果。Histogram equalization is a widely-used, simple and effective image contrast enhancement method. However, for some ap- plications such as consumer electronics, it is desired that the enhancement algorithm preserve certain characteristics of input image like mean brightness, which precludes direct use of histogram equalization. In this paper, we propose a new image contrast enhancement al- gorithm, with accurate brightness preservation. Specifically, we explicitly formulate the target histogram as piecewise constant model, then determine the model parameters through brightness preservation constraint and additional criterion, and lastly perform enhancement by histogram specification. Sufficient experiment results show that the proposed method achieves good contrast enhancement while accu- rately preserving mean brightness.

关 键 词：对比度增强 亮度保持 分段常数模型 直方图规定化 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]