水平集在盐水白带细胞显微图像分割中的应用

Application of Level Set Method to Segmentation of Brine Leucorrhea Cell Images

盐水白带细胞种类繁多成分复杂,细胞存在弱边缘、相互交织和面积小不易区分等特点,加之受杂质的影响,都给细胞分割带来困难.为此本文采用一种新的水平集方法,解决了传统水平集方法的演化曲线难以探测到细胞弱边缘的问题,而且这种水平集方法避免了重新初始化符号距离函数减少了计算量.实验结果表明,这种方法的演化曲线可以探测到细胞弱边缘,能够对盐水白带细胞显微图像进行分割.

The variety of brine leucorrhea cells and its ingredient already makes the image segmentation diffi-cult. And the weak contour, overlapping, tininess, impurity can further increase the difficulty. A new level set method proposed by Li is applied to detecting the cell＇ s weak contour, where the traditional level set method fails to work. This method saves much computation by eliminating re-initiation of the signed distance function. The tests show that Li＇s method works pretty well in detecting cell＇s contour and segmenting brine leucorrhea cell image.