基于重叠社区发现的断层扫描图像投影域伪影特征推荐算法研究

Research on Projection Domain Artifact Feature Recommendation Algorithm for Tomography Image Based on Overlapping Community Discovery

针对当前算法图像重建效果差和推荐准确率低等问题,提出基于重叠社区发现的断层扫描图像投影域伪影特征推荐算法,利用复合法将断层扫描图像复合,得到图像经过复合的坐标系。采用加法运算,叠加旋转断层扫描图像投影域伪影,将断层扫描图像的像素值相加,假设复合后图像的像素灰度值将大于255,对像素值取整,利用二值法对图像去噪,完成断层扫描图像重建。在此基础上,利用重叠社区发现算法挖掘,通过挖掘断层扫描图像的重叠社区结构,来实现断层扫描图像投影域伪影的特征推荐。实验结果表明,所提算法不仅具有较好的图像重建效果,还具有较高的重叠社区结构挖掘效率,且特征推荐平均耗时低于传统算法6 s,可以快速、准确的完成断层扫描图像投影域伪影特征推荐。

In order to solve the problems of poor image reconstruction effect and low accuracy of recommendation,an algorithm for recommending artifacts in projection domain of tomography images based on overlapping community discovery is proposed,and the composite method is used to composite the images of CT scans.The image passes through the composite coordinate system.The pixel value of the scanned image is added by adding the artifact in the projection domain.Assuming that the gray value of the pixel of the composite image will be greater than 255,the pixel value is rounded,and the image is de-noised by the two-value method.Complete the reconstruction of tomography images.On this basis,the overlapping community discovery algorithm is used to mine the overlap of tomography images.Community structure to realize the feature recommendation of artifacts in projection domain of tomography images.The experimental results show that the proposed algorithm not only has a good image reconstruction effect,butalso has a higher efficiency of mining overlapping community structures,and the average time consuming of feature recommendation is lower than that of the traditional algorithm 6 s,so it can be fast.Accurately complete the recommendation of the artifacts in the projection domain of the tomography images.