基于信息熵的递变能量X射线图像序列融合

The research of multi- energy X- ray image stack fusion based on the information entropy

常规固定能量的X射线无法对结构不规则、厚度不均匀的工件正常成像,易造成过曝光和欠曝光现象,失去图像信息,因此提出了变电压X射线扫描成像技术.但要得到完整的工件图像,需要对不同电压下得到的图像进行融合.本文首先在灰度直方图的基础上提取发动机缸盖的有效信息区域;然后基于信息熵来研究图像的融合方法.实验结果表明,此方法可以将各个原图像的有效信息结合起来,完整地再现复杂工件的结构信息.

Conventional fixed energy X- ray cannot normally imaging for component of irregular structure,uneven thickness,easy lead overexposed and underexposed,loss of image information,thus variable voltage X- ray scanning imaging is proposed. But to get a complete image artifacts,we need to fuse the image under different voltage. In this paper,first of all,on the basis of gray histogram to extract the effective information area of the engine cylinder head,then to study the image fusion method based on the information entropy. The experimental results show that this method can combine the effective information of original image,fully reproduce the structure information of complex component.