针对人脸特征分类问题，提出一种基于主动形状模型(ASM)和 K 近邻算法的人脸脸型分类方法。将 Hausdorff 距离作为 K 近邻算法的距离函数，利用 ASM 算法提取待测图像的特征点，对点集进行归一化后计算人脸轮廓特征点与样本库中所有样本点集的 Hausdorff距离，根据该距离值，通过 K 近邻算法实现待测图像的脸型分类。实验结果证明，该方法分类正确率高、速度快、易于实现。(Aiming at the problem of face feature classification, thi

这是一个图像形状的几何特征提取算法，可以提取圆形、方形、多边形等形状特征。(This is a geometric feature extraction algorithm for image shape, which can extract shape features such as circle, square and polygon.)

In this paper, a multiscale convolutional network (MSCN) and graph-partitioning-based method is proposed for accurate segmentation of cervical cytoplasm and nuclei. Specifically, deep learning via the MSCN is explored to extract scale invariant f