New Method Based on Curvelet Transform for Image Denoising

摘要：

A new method to remove noise form image is described in the article. Curvelet transform that combines both WindowShrink and BayesShrink can be used to complete the processing. Though the Wavelet transform can do the job well, it has low Resolving rate in high frequency area and it also lacks of the direction in dealing with images. Cnrvelet transform have an efficient way of representing the line and surface property of image. If the WindowShrink theory and BayesShrink theory are combined, the results are better. Firstly, the image should be done by Curvelet transform, then, the noise should be declined basing on Wavelet theory and the combination of WindowShrink and BayesShrink. The results of the method described in the article are better from both PSNR and the disposed image.

关键词： curvelet transform image denoise hard threshold adaptive coefficient

作者: Donglei Li Zhemin Duan Meng Jia

作者单位: Department of Electronics and Information Northwestern Polytechnical University XiAn, China

会议类型: 国际会议

会议名称: 2010 International Conference on Measuring Technology and Mechatronics Automation(ICMTMA 2010)(2010年检测技术与机电自动化国际会议)

会议地点: 长沙

会议语种:英文

页码: 1885-1888

在线出版日期: 2010-03-13（万方平台首次上网日期，不代表论文的发表时间）