工件(错误)
计算机科学
选择(遗传算法)
滤波器(信号处理)
硬化(计算)
计算机视觉
材料科学
人工智能
复合材料
图层(电子)
作者
Chang Liu,Yu Han,Xiaoqi Xi,ZhiCun Zhang,Lei Li,Bin Yan
标识
DOI:10.1109/icmtim62047.2024.10629553
摘要
Cone-beam Computed Tomography (CBCT) has been widely used in industrial object inspection and other fields due to its non-destructive imaging characteristics. However, in real scanning, beam hardening artifacts appear in the reconstructed image due to the absorption of low-energy photons by objects. In order to solve the problem that the filter is mostly selected according to experience, and there is no theoretical guidance to select the optimal material filter when using filters to process low-energy photons, this paper proposes a CBCT beam hardening artifact correction method based on the optimal filter material selection. By constructing two evaluation indicators: the total intensity of high-energy photons and the area ratio of high-energy photons to the total amount of photons. Mutual constraints guide the selection of optimal filtering materials. The experimental results show that the details of CBCT images are better restored, beam hardening artifacts are suppressed, and the values of image Contrast (Contrast) and Root Mean Square Error (RSME) are increased by up to 0.3892 and 11.14, respectively.
科研通智能强力驱动
Strongly Powered by AbleSci AI