CAJ | 학술논문

利用非下采样Contourlet变换（NSCT）平移不变性、多分辨率、多方向的优点，提出了一种基于非下采样Contourlet变换的子带自适应Bayes阈值图像去噪算法。该算法将源图像分解至NSCT变换域．能根据不同尺度、不同方向的子带能量，自适应调整去噪阈值。实验表明，与Contourlet多尺度阈值去噪、Contourlet自适应阈值去噪相比，该算法在图像去噪上能获得更好的视觉效果和更高的峰值信噪比。
이용비하채양Contourlet변환（NSCT）평이불변성、다분변솔、다방향적우점，제출료일충기우비하채양Contourlet변환적자대자괄응Bayes역치도상거조산법。해산법장원도상분해지NSCT변환역．능근거불동척도、불동방향적자대능량，자괄응조정거조역치。실험표명，여Contourlet다척도역치거조、Contourlet자괄응역치거조상비，해산법재도상거조상능획득경호적시각효과화경고적봉치신조비。
Utilizing the nonsubsampled contourlet transform＇s （NSCT） advantages of translation invariance,multi-resolution, multidirection, a image de-noising algorithm using adaptive bayes threshold by subband based on nonsubsampled contourlet transform is presented. Source images are decomposed to the domain of the NSCT, and can adjust denosing threshold adaptively according to different scales and directions of sub-band energy. Comparing with the multi-scale threshold using contourlet transform and using adaptive threshold based on contourlet transform, the simulation results show that the performance of this method is superior in Visual effects and PSNR.