基于分层差分表达理论的图像视觉增强  

Image Visual Enhancement Based on Layered Difference Representation

作　　者：耿爱辉[1,2] 万春明[1] 李毅[2] 张云峰[2] 曹立华[2] 冯强[2] 

机构地区：[1]长春理工大学,长春130022 [2]中国科学院长春光学精密机械与物理研究所,长春130033

出　　处：《电子与信息学报》2017年第4期922-929,共8页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(61205143);吉林省科技厅重点项目(20110329)~~

摘　　要：视觉注意机制表明人眼趋向于关注感兴趣区域。为了实现图像视觉增强,该文提出基于2维直方图分层差分表达理论的图像增强方法。该算法首先检测图像的显著性区域,并对该区域进行分割,得到更适合人眼观测的显著图。然后统计原图中显著图对应区域的2维差分直方图,依据分层差分表达理论和考虑各层之间的内在联系,通过解线性优化问题得到显著性区域差分向量。定义原始差分向量代表原图特征,将两个向量加权相加后得到全局变换函数,重建得到视觉增强图像。实验结果表明:该方法有效地增强图像中人眼感兴趣区域对比度,提升细节信息。客观评价指标表明:与其他5种方法比较,该方法处理结果在3组实验中在保持全局亮度、提升峰值信噪比及人眼视觉系统敏感度信噪比指标优势明显。该方法增强后图像显著性区域的EME值适中,有利于视觉观测。客观指标与主观观察结果一致,表明该方法能有效改善图像视觉效果。Human vision pays more attention to the interesting region than other areas. A method based on salient region detection for layered difference representation of 2D histogram is proposed to achieve visual enhancement. The algorithm detects the salient region by salient filtering and cuts salient region with a threshold for visual perception firstly. Then, 2D histogram is calculated for related region in original image of salient region, and statistical information in different layers is converted to layer 2 according to the inner relationship of each layer. Following a difference vector is gained though solving a constrained optimization problem of layered difference representation at a specified layer. To preserve the character of non-salient region, an origin difference vector is defined. Finally, output image is reconstructed by a transformation function, which is the result of two difference vectors for salient region and non-salient region. Experimental results show that the proposed method enhances contrast and details in salient region efficiently while protecting non-salient region in origin image. The objective evaluation parameters in three group experiments illustrate that the proposed algorithm can get better scores in protecting global mean lighting in non-salient region, increasing PSNR and HSNR of the whole image compared to other five algorithms. The EME value of images enhanced by the proposed method is moderate. The objective evaluation parameters are consistent with the subject observation, and it demonstrates the proposed method can achieve visual enhancement effectively.

关 键 词：图像处理 人眼视觉增强 显著性检测 分层差分表达 2维直方图 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]