CT图像边缘退化模型的建立及其在图像尺寸测量中的应用  

Computed tomography image edge degradation model and its application to image size measurement

作　　者：陈平[1] 潘晋孝[1] 刘宾[1] 

机构地区：[1]中北大学电子测试技术国家重点实验室,山西太原030051

出　　处：《光学精密工程》2009年第9期2269-2275,共7页Optics and Precision Engineering

基　　金：国家自然科学基金资助项目(No.60532080;No.60602041);山西省自然科学基金资助项目(No.20051042)

摘　　要：考虑工业CT产品质量检测和逆向设计的需求,特别针对有规则边缘的CT图像,建立了CT图像边缘退化模型,并将该模型应用于CT图像尺寸测量技术以提高测量精度。首先根据CT图像边缘退化的数学描述,构建了图像边缘退化模型;然后通过原CT图像的灰度信息以及灰度曲线的拐点信息确定退化模型中的相关参数;最后,利用这个退化模型对原CT图像的边缘进行恢复,准确提取CT图像的边缘信息,从而完成CT图像的尺寸测量。实验结果显示,该方法对边缘阶跃性较差的CT图像进行尺寸测量得到的相对误差为2%,比常用的图像尺寸测量方法减小了1.5%。结果表明,该方法能够有效地提取CT图像边缘信息,且尺寸测量精度较高。In consideration of the requirements of quality inspection and reverse design for Computed Tomography （CT） products, a CT image edge degradation model was established and used in the image size measurement to improve the measurement accuracy. At first, the model was established based on mathematical description of CT image edge degradation. Then, the parameters of degradation model were confirmed according to the image intensity and inflexions of CT image gray curves. Finally, this constructed degradation model was used to restore the primary CT image edge and accurately extract the information of image edge. Hence, the measurement of CT image is accomplished. Experimental results indicate that the relative error is 2% for the CT image with a poor step edge, which has decreased by 1.5 % as compared with those of traditional image measurement methods. These results show that this new model can effectively extract the information of CT image edge, and can get an accurate measurement result.

关 键 词：工业CT 尺寸测量 边缘恢复 退化模型 拐点 

分 类 号：TP391.76[自动化与计算机技术—计算机应用技术] TG115.22[自动化与计算机技术—计算机科学与技术]