基于力场活动轮廓模型的舌图像分割研究

Research on tongue image segmentation based on active contour model of force field

目的:针对现有舌图像分割方法复杂耗时的问题,文章提出一种基于力场活动轮廓模型的舌图像分割方法。方法:基于轮廓点之间的拉力、斥力以及来自边缘点的吸引力,建立力场活动轮廓模型,进行舌图像的分割。结果:提出的舌图像分割方法不仅能够较好地降低图像内噪声点对轮廓变形的影响,而且能够较准确地提取舌体轮廓,取得了较为满意的舌体分割结果。结论:基于力场活动轮廓模型的舌图像分割方法较好地进行舌图像的分割,对舌诊客观化具有一定实用价值和借鉴意义。

Objective: Aiming at the problem that the existing tongue image segmentation method is complicated and time-consuming, this paper proposes a segmentation method of tongue images based active contour model of force field. Methods:Based on the tension and repulsive force between the two contour points, and the attractive force between a contour point and an edge point, the active contour model of force field is established to segment the tongue images. Results: The segmentation method of tongue images proposed in this paper can not only reduce the influence of noise points on the contour deformation, but also obtain satisfactory results of tongue segmentation. Conclusion: The tongue segmentation method can effectively and accurately segment the tongue images, which can provide reference significance for the research of tongue diagnosis objectification.