采用分数阶微分边缘检测的图像插值  

Image Interpolation Algorithm Based on Edge Detection of Fractional Differential

作　　者：汪成亮[1] 兰利彬[1] 

机构地区：[1]重庆大学计算机科学与工程学院,重庆400044

出　　处：《北京理工大学学报》2011年第9期1085-1089,共5页Transactions of Beijing Institute of Technology

基　　金：国家自然科学基金资助项目(61004112);博士后科学基金资助项目(20080430750)

摘　　要：针对目前的边缘插值算法不能有效改善插值图像的中低频纹理细节的问题,研究并提出了一种基于分数阶微分边缘检测的图像插值算法.依据分数阶微分理论,设计并实现了可以有效提取中低频纹理信息的算子掩模.按照检测到的边缘纹理信息,分别对沿边缘方向、垂直于边缘方向和平滑区域的待插值像素点进行线性插值、二次插值和双线性插值.采用了峰值信噪比(PSNR)和信息熵(IE)等图像质量评价标准做定量分析和实验验证.结果表明,该方法可以得到丰富的图像纹理信息,提高了峰值信噪比,其结果符合人们的视觉感受.Previous edge-based image interpolation algorithm could not improve the medium and low-frequency texture details of interpolated image effectively. To preserve the texture-rich information, an image interpolation approach based on edge detection of fractional differential was studied and proposed. The fractional differential operator mask, which can extract medium and low-frequency texture detail effectively, was designed and realized on the basis of fractional differential theory. Then the measures of linear interpolation, quadratic interpolation and bilinear interpolation were used for those pixel points to be interpolated along edge directions, perpendicular to edge directions and in smooth areas, respectively. To evaluate the interpolated image quality, the indexes of peak signal to noise ratio （PSNR） and information entropy were used. The quantitative analysis and experimental verification of the proposed approach were implemented. The results show that this method could obtain texture-rich image information, increase the peak signal to noise ratio and satisfy the human visual sense.

关 键 词：分数阶微分 边缘检测 纹理抽取 图像插值 

分 类 号：TN911.73[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]