欢迎访问《兵工学报》官方网站,今天是

兵工学报 ›› 2011, Vol. 32 ›› Issue (7): 896-900.

• 研究简报 • 上一篇    下一篇

自适应小波阈值去噪算法及在图像处理中的应用

林杰, 付梦印, 李道平   

  1. (北京理工大学 自动化学院, 北京 100081)
  • 收稿日期:2009-09-11 修回日期:2009-09-11 上线日期:2014-05-04
  • 通讯作者: 林杰 E-mail:linjason@bit.edu.cn
  • 作者简介:林杰(1977—),男,助理研究员,博士研究生

Self-adaptive Wavelet Threshold De-noising Method and Its Application in Image Processing

LIN Jie, FU Meng-yin, LI Dao-ping   

  1. (School of Automation, Beijing Institute of Technology, Beijing 100081,China)
  • Received:2009-09-11 Revised:2009-09-11 Online:2014-05-04
  • Contact: LIN Jie E-mail:linjason@bit.edu.cn

摘要: 针对图像去噪的问题,提出一种基于自适应小波阈值去噪的算法。该方法根据噪声在小波变换下的特性自适应确定小波分解的阈值,并将去噪图像的峰值信噪比作为性能指标,采用中点法进行寻优,得到最优的阈值参数。该方法具有自适应性强、算法简单、去噪效果好等特点。通过实例表明,该方法比原有的阈值去噪算法去噪效果更佳,使图像达到更良好的视觉效果。

关键词: 信息处理技术, 自适应, 小波变换, 图像去噪, 中点法

Abstract: For the problem image de-noising, a new method based on self-adaptive wavelet threshold algorithm was proposed. It can decide the threshold of wavelet analysis automatically according to the noise characteristics in wavelet transform, then takes PSNR as a function of filter parameter and acquires the optimal threshold parameter by using midpoint method. It has the strong self-adaptation, simple calculation,good de-noising result and so on. Experiment results show that this new method is much better than original threshold de-noising algorithms and achieves better visual effect.

Key words: information processing, self-adaptive, wavelet transform, image de-noising, midpoint method

中图分类号: