Yanjie Qi, Liming Wang
Department of Electronic Engineering, Taiyuan University of Science and Technology, Taiyuan, China.
Science and Technology on Electronic Test & Measurement Laboratory and Key Laboratory of Instrumentation Science & Dynamic Measurement(Ministry of Education), North University of China, Taiyuan, China.
J Xray Sci Technol. 2016;24(1):67-77. doi: 10.3233/XST-160532.
In order to increase the single digital radiography (DR) image information of the composite component in the industry, the different DR images are captured at different voltages so as to get the structural information at different thickness region firstly. Secondly, the original DR images are decomposed by nonsubsampled contourlet transform (NSCT), and the low-frequency subbands are fused by the role of principle component analysis (PCA), and the modified central energy role is used to carry out the high-frequency directional subbands fusion. The false edges are extracted, and the values of the high-frequency subband coefficients of the false edges are set to be a small value so as to reduce the false edges in the fusion image. Finally, the output image can be obtained by inverse nonsubsampled contourlet transform. The experimental results show that the fused DR image brings more detailed information, and the structure of the component can be seen clearly, so it is useful to the fast and accurate quality judgements of the component.
为了增加工业中复合部件的单幅数字射线照相（DR）图像信息，首先在不同电压下采集不同的DR图像，以便获取不同厚度区域的结构信息。其次，通过非下采样轮廓波变换（NSCT）对原始DR图像进行分解，利用主成分分析（PCA）对低频子带进行融合，并采用改进的中心能量法对高频方向子带进行融合。提取虚假边缘，并将虚假边缘的高频子带系数值设置为较小值，以减少融合图像中的虚假边缘。最后，通过非下采样轮廓波逆变换得到输出图像。实验结果表明，融合后的DR图像带来了更详细的信息，部件结构清晰可见，对部件的快速、准确质量判断具有重要意义。
