检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]南京医科大学口腔医学院正畸科,南京210029 [2]东南大学影像科学与技术实验室,南京210096
出 处:《口腔医学》2006年第5期351-353,共3页Stomatology
基 金:江苏省科委自然科学基金资助项目(BS99063)
摘 要:目的初步探讨计算机头影测量自动定点技术。方法随机选择20张头颅侧位片作为待测图像,另选1张高质量的X线片为标准图像。使用仿射变换结合模板匹配的方法来识别标志点。首先在标准图像上手工确定各标志点的位置并建立标志点的标准模板;然后用仿射变换的方法把标志点从标准图像变换到待测图像上,获得标志点的初始位置;最后经模板匹配确定标志点的准确位置。结果共识别出11个硬组织点和10个软组织点。硬组织点平均误差2.28 mm,软组织点平均误差0.77 mm。有4个硬组织标志点的定点误差<2 mm。结论初步建立了头影测量标志点自动识别系统,但整体上标志点识别的准确性尚不能满足临床应用要求。Objective To study automatic identification of cephalometric landmarks. Methods A high quality lateral skull image was chosen as standard image. Landmarks were labeled manually on standard image, and then the template of each landmark was established. Resuits Totally, 11 hard tissue landmarks and 10 soft tissue landmarks were identified automatically by means of template matching combined with affined transformation in 20 test images. The mean error of hard tissue landmarks identification was 2.28 mm and the mean error of soft tissue landmarks was 0.77 mm. Conclusion An automatic cephalometric landmarks identification system was built in this study. The result of the landmarking was not good enough for clinic use. Further efforts should be made to improve the accuracy of automatic identification of cephalometric landmarks.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.198