基于小波包变换与自适应阈值的SMT焊点图像去噪

SMT soldering image denoising based on wavelet packet transform and adaptive threshold

为提高表面组装技术焊点图像去噪效果,提出一种基于小波包变换和自适应阈值的焊点图像噪声去除新方法.利用小波包变换对图像进行多层分解,通过对图像小波包树系数的分析,对小波包树系数高频部分和低频部分进行Wiener滤波;为提高去噪性能,通过计算小波包系数对应的中值绝对方差估计,提出一种改进的自适应小波包阀值算法,并对图像进行第二次去噪;最后采用中值滤波对图像进行平滑处理,得到最终的去噪图像.结果表明,与传统方法相比,所提出的算法不仅能提高去噪性能和去噪效果,而且能很好的保留表面组装技术焊点图像边缘信息.

A novel image processing approach is proposed to reduce the mixed noise in surface mount technology soldering image based on wavelet packet transformed adaptive threshold.At first,by using wavelet packet transform,the approach not only decomposes the image into the low frequency part but also into the high frequency part of image in several scales.After analyzing the wavelet packet tree coefficients,they were processed with the Wiener filter,and kept the wavelet packet tree low frequency coefficients without change.Secondly,an improved wavelet adaptive threshold algorithm is proposed to denoise the mixed noise again.At last,the inverse wavelet packet transform is applied to reconstruct the image and median filter is used to smooth the image.The experimental results have illustrated that the approach can obtain a better result in soldering image denoising compared with the conventional methods and can retain the image edges very well.