基于区域Hough变换的眼睑退缩诊断  

Diagnosis of eyelid retraction based on improved Hough transform

作　　者：胡敏[1] 梁挺 张光华 黄宏程[1] HU Min;LIANG Ting;ZHANG Guang-hua;HUANG Hong-cheng(School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;Department of Computer Science and Engineering,Taiyuan University,Taiyuan 030000,China)

机构地区：[1]重庆邮电大学通信与信息工程学院,重庆400065 [2]太原学院计算机科学与工程系,山西太原030000

出　　处：《计算机工程与设计》2022年第11期3217-3224,共8页Computer Engineering and Design

基　　金：山西省回国留学人员科研基金项目(2020-149);山西省卫健委基金项目(2018090)。

摘　　要：为克服传统的人工眼睑退缩检查诊断准确率低和耗时的缺点,采用一种Hough转换算法。对脸部的轮廓和上下眼睑的特征点进行提取;采用Bezier曲线和3次B样条曲线拟合面部和眼皮;采用最优Canny算子对图像进行边缘提取;采用改进的霍夫变形法进行虹膜外圆定位;根据眼睑退缩的诊断标准,确定有无眼睑退缩。用该算法解决实际眼睑退缩诊断问题,将仿真结果与其它算法进行比较,验证了该算法的准确率与速度均优于其它算法。To overcome the accuracy and time-cost shortcomings of the traditional artificial eyelid retraction examination diagnosis,a Hough transform algorithm was adopted.The contour of the face and the feature points of the upper and lower eyelids were extracted.The Bezier curve and the cubic B-spline curve were extracted to fit the face and eyelids.The optimal Canny ope-rator was extracted to extract the edge of the image.The improved Hough deformation method was used to locate the outer iris.According to the diagnostic criteria of eyelid retraction,the presence or absence of eyelid retraction was determined.The algorithm was used to solve the actual eyelid retraction diagnosis problem,and the simulation results were compared with other algorithms,which verified that the accuracy and speed of the algorithm are better than that of the other algorithms.

关 键 词：HOUGH变换 虹膜定位 图像处理 眼睑退缩 甲状腺相关性眼病 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]