基于BP神经网络的嘴型分类算法

针对传统嘴型分类中医生肉眼观察主观性大且无法量化等问题，文中提出一种嘴型分类算法。该算法在人脸特征点标定ASM的基础上，提取嘴型模板，经过一系列旋转、二值化以及重采样构建特征向量，然后利用BP神经网络进行训练完成嘴型分类。实验结果表明，该算法可以实现较为准确的嘴型分类，对临床医疗整形具有一定的参考价值。

Research on Mouth Type Classification Algorithm Based on BP Neural Network

Aiming at traditional mouth type classification mainly depends the observation of doctor, which is easily influenced by subjective factors and cant be quantified, This paper proposes a kind of mouth type classification algorithm. On the basis of ASM, the algorithm extracts the mouth template, constructs the feature vector with a series of rotation, binarization and heavy sampling, and then using BP neural network training feature vector to complete the mouth type classification. Experimental results show that the proposed algorithm can achieve accurate classification of mouth, which has a certain reference value for clinical medical treatment.