薯类农产品视觉图像的去噪方法

Potato Agricultural Product Visual Image Denoising Method

针对目前图像处理中的阈值去噪方法存在的问题,探讨了小波阈值法中小波分解层数和小波系数处理算法,在视觉图像阈值去噪中采用了小波分解层数的自适应算法,并针对小波系数处理中硬阈值和软阈值函数存在的问题,提出了一种新的阈值函数用于图像去噪。结果显示:去噪后图像的峰值信噪比PSNR、均方差MSE在最优分解层数下相对传统阈值函数能达到全局最优,同时视觉上的清晰度更好。

In view of the current problems in image processing threshold denoising methods,discusses the wavelet decomposition level and wavelet coefficient processing algorithm of the wavelet threshold method,and uses the wavelet decomposition level's adaptive algorithm in visual image threshold denoising,and for the treatment of hard and soft threshold function's problems,puts forward a new threshold function to image denoising,the results show that the denoised image's peak signal to noise ratio and mean square error reach the global optimum on the optimal decomposition level relative to the traditional threshold function,at the same time the visual clarity is better.