作 者: ;
机构地区: 嘉应学院电子信息工程学院
出 处: 《嘉应学院学报》 2008年第3期93-97,共5页
摘 要: 提出了一种基于数据融合的多小波基联合图像去噪新方法.该方法首先用多个小波基分别对含噪图像进行分解、阈值处理和恢复,得到多幅恢复图像,然后根据像素点邻域的方差对这些图像进行加权融合获得最终去噪图像。该方法充分体现小波基的多样性和图像的局部特性。实验结果表明,该方法去噪效果比单一小波基方法和已有的多小波基联合方法都有明显的改善。 A new joint image denoising method via multiple wavelet bases is proposed based on data fusion. Firstly, every wavelet base is employed to decompose , threshold , and recover the image , and then a set of the denoised images are obtained. Next , these denoised images are fused by using weighted fusion method to obtain a clean image, the weights on individual wavelet bases are chosen by processing pixel neighboring region variance. The differences among the bases are used properly and the local image characteristic is revealed in this method. The experimental results indicate that the denoising effect of this method is remarkably improved than the method of single wavelet base and existing joint multiple wavelet bases.