舌体边缘简易自动识别算法  

The Automatic Recognition Algorithm of Tongue Edge

作　　者：钱耀宇 QIAN Yaoyu(Fujian Xiamen Maternal and Child Care Service Center,Xiamen Fujian 361021)

机构地区：[1]厦门市海沧区妇幼保健院,福建厦门361021

出　　处：《软件》2022年第3期81-83,114,共4页Software

摘　　要：中医舌诊客观化对中医现代化具有重要意义。将舌体从图像中分割出来是自动分析舌象的重要步骤,舌体分割质量会直接影响后续分析算法的准确性。因此,本文提出一种简易舌体边缘自动识别算法。首先,将色彩位图转化为灰度图像,滤波后去除图像中噪点,用全局门限法找出上部边缘。其次,用Sobel算法对图像进行水平和垂直检测,找出左、右和下部边缘。最后,将所有边缘组合起来,并用腐蚀算法对边缘进行优化得出最终的边缘。实验结果表明,该方法能够较好的识别舌体边缘。The objectification of tongue diagnosis in Modernization of Traditional Chinese Medicine(TCM) is of great significance.In order to facilitate the automatic analysis of the tongue image,it’s important to segment the tongue from the whole image,and the segmentation results will directly affect the accuracy of the tongue image feature analysis algorithm.Therefore,this paper proposes a simple automatic tongue edge recognition algorithm.Firstly,it converts the color bitmap into a grayscale image,and removes the noise after filtering the image,and then uses the global threshold method to find the up edge of the tongue.Secondly,the image is detected horizontally and vertically with the Sobel algorithm to find the left, right and low edges.Finally,it combines all the edges and optimizes these edges with a corrosion algorithm to get the final edge of the tongue.The experimental results show that this algorithm can effectively identify the edge of the tongue.

关 键 词：边缘检测 SOBEL算法 阈值算法 腐蚀算法 

分 类 号：R241[医药卫生—中医诊断学] TP391.41[医药卫生—中医临床基础]