基于最小二乘自适应分解插值的图像编码  

Image Coding Based on Least Square Adaptive Splitting and Interpolation

作　　者：刘雪冬[1] 张康[1] 杨杰[1] 

机构地区：[1]武汉理工大学信息工程学院,湖北武汉430070

出　　处：《武汉理工大学学报（信息与管理工程版）》2014年第5期596-599,613,共5页Journal of Wuhan University of Technology：Information & Management Engineering

基　　金：国家自然科学基金资助项目(61001082);中央高校基本科研业务费专项资金资助项目(2013-IV-023);湖北省博士后科技活动择优基金资助项目

摘　　要：为了改善JPEG在低比特率条件下重建图像的质量,以及提高"下采样—JPEG—插值"方案的率失真性能,提出了利用最小二乘法确定双线性插值的最优插值顶点,然后对这些顶点值进行编码,解码的顶点值被用来进行双线性插值以重建原始大小的图像;在预定保真度的情况下,根据局部图像的插值误差是否满足要求来进行插值图像块的自适应分解。实验结果表明,该方法改善了JPEG低比特率条件下的重建质量,率失真性能整体优于"下采样—JPEG—插值"方案。In order to improve the reconstructed image quality at low bit rate and the rate -distortion performance of ＆quot;down-sampling-JPEG-interpolation＆quot;schemes, an image coding algorithm was proposed that determines the optimal interpolating ver -tices of bilinear interpolation using least square method .Then the vertices were coded;the reconstructed image was obtained by bilinear interpolation using the decoded vertices .In addition, the interpolation image block will be split further adaptively accord-ing to whether the interpolation error of the local image meets the predefined fidelity requirement .Experimental results show the algorithm can improve the reconstructed image quality of JPEG at low bit rate;the whole rate-distortion performance outperforms that of the ＆quot;downsampling -JPEG-Interpolation＆quot;schemes.

关 键 词：双线性插值 最小二乘 自适应分解 图像编码 

分 类 号：TN919.81[电子电信—通信与信息系统]