作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (22): 226-228. doi: 10.3969/j.issn.1000-3428.2007.22.078

• 人工智能及识别技术 • 上一篇    下一篇

基于阈值控制的边缘自适应快速图像插值算法

吴锡生1,党向盈1,2,赵 勇2   

  1. (1. 江南大学信息工程学院,无锡 214122;2. 徐州工程学院,徐州 221008)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-11-20 发布日期:2007-11-20

Fast Self-adaptive Edge-oriented Interpolation Based on Threshold Method

WU Xi-sheng1, DANG Xiang-ying1,2, ZHAO Yong2   

  1. (1. School of Information Engineering, Southern Yangtze University, Wuxi 214122; 2. Xuzhou Institute of Technology, Xuzhou 221008)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-11-20 Published:2007-11-20

摘要: 在处理视频、网络信号时,要求较低的算法复杂度和运算量。该文通过阈值控制方式分类像素点区域,采用双通道达到快速插值的目的。利用与边缘像素点相邻的6个降采样像素局部结构多方向信息特征,估计高分辨率像素值。实验结果证明,该算法有效地保持了边缘特征,减少了CPU处理插值的时间,获得了较高的分辨率图像,并满足快速处理信号的要求。

关键词: 图像插值, 放大, 阈值, 边缘保持

Abstract: Lower computational complexity of the algorithm and better subjective quality are important in video and network signal processing. The interpolation of pixel is accomplished by double-channel method. To estimate relative information at high resolution, the algorithm analyzes the multiple directions relativity of local neighbors and makes full use of six down-sampled neighbors involved in the low resolution image. Experimental results demonstrate that algorithm not only decreases the computational complexity but also substantially improves the visual quality of the interpolated images.

Key words: image interpolation, enlargement, threshold, edge-preserving

中图分类号: