基于K-means和GVF Snake模型的纤维图像分割

Fiber Image Segmentation Based on K-means and GVF Snake Model

在纤维图像自动识别系统中,分割出完整连续的纤维是纤维特征分析的必要前提.针对纤维图像的背景和前景灰度区别不大、光照不均对图像的影响等特征,提出融合K-means和GVF(Gradient Vector Flow)Snake模型的纤维图像分割算法.该算法以提取完整连续的纤维轮廓为标准,利用K-means聚类分割结果为GVF Snake模型的初始轮廓线,并对得到的存在毛刺的轮廓结果采用轮廓跟踪去除毛刺,从而得到完整连续的单根纤维图像.该算法不仅能有效解决传统图像分割方法对纤维图像分割的不连续问题,而且能有效抑制纤维图像中噪声的影响.

In the automatic fiber classification system based on image processing technology,to segment a complete and continuous fiber is the critical task.According to the impact of little gray-scale differences between image background and foreground and uneven illumination,a new fiber image segmentation algorithm based on K-means and GVF（Gradient Vector Flow）Snake model is proposed.The K-means clustering segmentation is used to obtain the initial coarse contour of fiber firstly,then the GVF Snake algorithm is applied to calculate the accurate fiber contour.Due to the noise of fiber micrographic image,some fiber contours have burrs,which can be removed by contour tracing method.The experimental result shows that this algorithm is effectively and accurately,which can not only extract the complete and continuous fiber contour,but also depress the noise of fiber image.