用径向基函数网络复原超声C扫描图像  

Ultrasonic C-scan Image Restoration Using Radial Basis Function Network

作　　者：朱良峰[1] 曹宗杰[1] 吴勇[1] 薛锦[1] 王裕文[1] 

机构地区：[1]西安交通大学焊接研究所,西安710049

出　　处：《仪器仪表学报》2005年第z1期673-675,共3页Chinese Journal of Scientific Instrument

摘　　要：针对超声C扫描图像中存在噪声干扰和边界模糊而导致图像质量下降的问题,提出了一种基于径向基函数网络复原超声C扫描降质图像的方法。用Φ3mm平底孔的超声C扫描降质图像对网络进行训练,建立了降质图像和复原图像之间的映射关系,并用其它降质图像验证了网络。试验结果表明,该网络能有效地消除图像中的噪声和边界模糊现象,使图像中尺寸更加接近实际尺寸。同时,通过对比三种不同网络的复原效果,得到了一个最佳网络参数。A method for restoration of ultrasonic C-scan images is presented by using a radial basis function net-work. The method attempts to reproduce the mapping between the degraded C-scan image and the high qualityone by training a RBF network. The inputs for training are the sub-images divided from C-scan image of flat-bot-tom hole of size 3mm and the output is the corresponding center in high quality image. After the network wastrained, the other C-scan images were used to verify the network. The results show that the network producesgood restored results, in which the noise is removed and the edges are deblurred. Comparing the restored resultsby the networks trained by the different sub-images, the sub-images with size 7×7, scanning step of 3 are deter-mined as the optimal inputs for training.

关 键 词：超声无损评价 C扫描图像 径向基函数网络 图像复原 

分 类 号：TH7-55[机械工程—仪器科学与技术]