CAJ | 학술논문

为了进一步提高针对印章图像的去噪性能，提出了一种基于阈值函数和 TV 模型的印章图像去噪方法。首先对含噪印章图像进行 Contourlet 分解；然后低频部分利用自适应 TV 模型进行扩散，高频部分通过阈值函数进行筛选；最后经 Contourlet 逆变换重构印章图像。实验结果表明，与小波阈值法、小波扩散法及 Contourlet 阈值法相比，该方法能有效地去除高斯白噪声和椒盐噪声的混合噪声，提高峰值信噪比，并较好地保留图像的细节和纹理，具有更好的视觉效果。
위료진일보제고침대인장도상적거조성능，제출료일충기우역치함수화 TV 모형적인장도상거조방법。수선대함조인장도상진행 Contourlet 분해；연후저빈부분이용자괄응 TV 모형진행확산，고빈부분통과역치함수진행사선；최후경 Contourlet 역변환중구인장도상。실험결과표명，여소파역치법、소파확산법급 Contourlet 역치법상비，해방법능유효지거제고사백조성화초염조성적혼합조성，제고봉치신조비，병교호지보류도상적세절화문리，구유경호적시각효과。
In order to further improve the denoising performance of seal image , a method of the seal image denoising based on threshold function and total variation model is proposed . Firstly , the seal image with noise is decomposed through contourlet trans-form . Then adaptive total variation model is used as diffusion of low-frequency component , contourlet threshold function is acted on high-frequency component . Finally , the seal image is reconstructed by inverse contourlet transform . Experimental results show that the proposed method can effectively remove the mixed noise of Gaussian white noise and salt and pepper noise , increase the peak signal to noise ratio , remain the details and textures of images better compared with wavelet threshold method , wavelet diffusion method and contourlet threshold method .