基于梯度域融合的图像视觉效果改善  

Image visualization improvement based on gradient fusion

作　　者：许欣[1] 陈强[1] 孙怀江[1] 夏德深[1] 

机构地区：[1]南京理工大学计算机科学与技术学院,南京210094

出　　处：《中国图象图形学报》2011年第2期278-286,共9页Journal of Image and Graphics

基　　金：国家自然科学基金项目(60805003;60773172);江苏省博士后基金项目(AD41158)

摘　　要：针对同一场景不同图像之间可存在互补优缺点的特点,提出了采用梯度域融合的方法改善图像视觉效果的增强方法。首先将待融合各图像的结构张量按一定比例进行融合,在权重的设计中考虑了各通道图像的局部对比度。之后求出目标梯度场,其结构张量在Frobenius范数意义下逼近前述融合后得到的结构张量。最后采用最小二乘拟合从目标梯度场重建出增强后的图像。方法可应用于同一图像不同增强方法结果之间、相同场景采用不同对焦距离或不同曝光时间所拍摄照片之间等的融合。实验结果表明,融合后的图像能保持各输入通道图像中显著的有意义细节和结构信息,有效改善增强图像的视觉效果。There exists complementarity between different images of one scene. A better image can be obtained by fusing these images in gradient domain, The structure tensors of the images are fused and the local contrasts are incorporated in the design of fusion weights. The target gradient field whose structure tensor approximates the aforementioned tensor in the Frobenius norm sense is then obtained. An enhanced image is finally reconstructed from the target gradient field by least square fitting. Applications can include fusion of results by different enhancement methods, photos of the same scene with different focus or different exposures, etc. Experimental results demonstrate that the fused image can preserve significant details and structural information of each input image channel and the visual effect is improved.

关 键 词：图像增强 梯度域 图像融合 结构张量 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]