基于2-D Gabor滤波器的光学定穴体表特征提取方法

Feature extraction of anatomical landmark using 2-D Gabor filters for localizing acupoints

取穴准确性是决定针灸效果的最基本要求,这就需要对取穴体表特征进行精确地定位。文中提出一种新的人体体表特征定位的光学方法,在光学检测平台上通过相机采集不同方向的图像,选取合适的Gabor滤波器参数,得到图像的强度响应并提取局部极大值,从而获得定穴体表轮廓特征。为验证该方法的有效性和精度,采用Sobel算子、Canny算子、LoG算子以及Gabor滤波器分别对灰度图像和二值图像进行特征提取。通过对比和分析,发现经过Gabor函数滤波后得到的图像轮廓是连续且最清晰的;Gabor函数对二值图像的滤波效果优于对灰度图像。实验结果表明,所提出的方法能精确快速地定位体表轮廓特征,为进一步利用轮廓特征提取定穴体表特征点以及研究穴位光学定位方法奠定基础。

Localization of body surface features is needed for the correctness of localizing acupuncture points that determines the acupuncture effect. In this paper, a novel optical method was presented for locating surface features. Firstly, the images around the human model were collected using a camera on a designed optical platform; Then, the images were processed using Gabor filter into magnitude response, and the local maximum were obtained; Finally, the contour features localizing anatomical landmarks were extracted. To test the feasibility and accuracy of the proposed method, the features in gray and binary images were respectively extracted using the edge detection operators （Sobel, Canny, LoG and Gabor operator）. It is found that, the contour features by Gabor filter are continuous and clearest; and the filtering effects of the binary images are better than that of the gray. The results show that the proposed method is valid for locating accurately and quickly the surface contour features, and it lays a foundation for further extracting anatomical landmark based on contour features and studying the optical method localizing the acupoints.