Research of Tongue Color Recognition Based on BP-ANN with Self-Adaptive Network Structure

Tongue color recognition is one of important research in objective tongue diagnosis. Since the network structure of traditional BP-ANN can greatly affect the recognition rates of tongue color, a kind of improved BP-ANN with self-adaptive network structure is introduced to solve the problem of tongue color recognition. In this method, according to the recognition rates, the node number of the hidden layer is automatically selected, i. e. the network structure is self-adaptive. As the experimental results show, our improved BP-ANN with self-adaptive network structure is more accurate than the traditional one.