ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2018, Vol. 55 ›› Issue (3): 629-642.doi: 10.7544/issn1000-1239.2018.20160942

• 图形图像 • 上一篇    下一篇

基于NSCT的区域自适应图像插值算法

范清兰1,2,3,张云峰1,2,3,包芳勋4,沈晓红1,2,3,姚勋祥1,2,3,   

  1. 1(山东财经大学计算机科学与技术学院 济南 250014); 2(山东省数字媒体技术重点实验室 济南 250014); 3(山东省高校经济运行动态仿真重点实验室 济南 250014); 4(山东大学数学学院 济南 250100) (fan_qinglan@163.com)
  • 出版日期: 2018-03-01
  • 基金资助: 
    国家自然科学基金项目(61373080,61672018,61402261,U1609218);山东省重点研发计划项目(2016GSF120013);山东省高等学校优势学科人才团队培育计划

An Region Adaptive Image Interpolation Algorithm Based on the NSCT

Fan Qinglan1,2,3, Zhang Yunfeng1,2,3, Bao Fangxun4, Shen Xiaohong1,2,3, Yao Xunxiang1,2,3   

  1. 1(School of Computer Science & Technology, Shandong University of Finance and Economics, Jinan 250014); 2(Shandong Provincial Key Laboratory of Digital Media Technology, Jinan 250014); 3(Economic Operation and Dynamic Simulation Key Laboratory of Shandong Colleges and Universities, Jinan 250014); 4(School of Mathematics, Shandong University, Jinan 250100)
  • Online: 2018-03-01

摘要: 提出一种基于非下采样轮廓波变换(nonsubsampled contourlet transform, NSCT)的分区域自适应插值算法,将图像划分为不同区域,相应地采用不同的方法实现图像插值.首先,构造了一类有理函数插值模型,分析了其C\+2连续性条件,给出了误差估计.其次,通过NSCT捕获到图像的边缘轮廓信息,利用其高频信息的统计特性设定阈值,根据阈值将图像自适应地划分为边缘区域和非边缘区域.最后,边缘区域采用新的基于边缘指导的插值(new edge-directed interpolation, NEDI)模型,非边缘区域采用C\+2连续有理函数模型插值,进而得到目标图像.实验结果证明:提出的基于NSCT的区域自适应插值算法与当前经典插值算法相比,在处理图像纹理细节和边缘方面具有明显优势,同时获得了较好的客观评价数据,且时间复杂度较低.

关键词: 图像插值, 非下采样轮廓波变换, 自适应, 有理函数插值, 边缘指导插值

Abstract: Image interpolation plays a vital role in digital image processing. In order to preserve image texture detail and edge sharpness, a new method of region adaptive image interpolation based on NSCT (nonsubsampled contourlet transform) is proposed. Image is divided into different regions and interpolated by different methods respectively. Firstly, a new type of C\+2 continuous rational function interpolation model is constructed, and the error estimates are given. Secondly, image edge contour information is captured by the NSCT, and the image is divided into edge region and non-edge region adaptively according to a preset threshold. Finally, as for edge region, edge-directed interpolation technique is used to get high resolution image. Similarly, rational function interpolation algorithm is used in non-edge region. The objective image with higher resolution ratio than the input image is obtained by adaptive interpolation. Compared with the classical image interpolation algorithm, the proposed method is highly competitive not only in PSNR (peak signal to noise ratio) and SSIM (structural similarity index) but also in visual effect. Experimental results show that the proposed algorithm not only has lower time complexity, but also can preserve image details, eliminate phenomenon of edge aliasing, and have a high quality of interpolation image.

Key words: image interpolation, nonsubsampled contourlet transform (NSCT), adaptive, rational function interpolation, edge-directed interpolation (EDI)

中图分类号: