基于噪声调节主成分分析法的彩色图象融合滤波

彩色图象滤波是图象处理领域中的经典命题之一.由于滤波算子选择的不同,滤波后影像的质量也不尽相同.为此在分析经典滤波算子的滤波器特性的基础上,将含噪彩色图象的亮度分量分别经过中值滤波与小波软门限滤波,形成亮度滤波结果图象,而后利用基于噪声调节的主成分分析法对彩色图象与亮度滤波结果影像进行融合处理,得到融和滤波图象.同矢量中值滤波器和α-TMF滤波结果影像相比,融合滤波后影像与原始影像具有更好的峰值归一化均方误差,能够更加真实地反映原始景物的色彩信息.实验证明,该融合滤波方法能有效地滤除高斯噪声、脉冲噪声及其混合噪声.

De-noising in Color Image Based on The Noise-Adjusted Principal Components Analysis and Image Fusion

De-noising in color image using different filter will get the different image quality. In this paper, we analysis the filter feature of the classic filter,get the filtered illumination image with the median filter and the wavelet filter,and then merge the filtered illumination image with the color image after vector median filter to get the result image. Experiment result shows that the fused filter can suppress the pulse noise,Gussian noise and the mixed noise. Compared with images by vector filter and-TMF, the fused filtered image has the least normalized peak-value mean square error. It approximately reflect the real colors of nature object like the origin non-noise image.