(3) Determine the network structure of BP neural network: Thisparticular BP neural network is a three-layer network: the input layer, the hidden layer and the output layer. Both theinput layer and output layer consist of 3 neurons. The input isthe captured R1, G1and B1sample values of the color checkerwhile the output is the standard target color L1*, a1* and b1*.It has been proved that if a BP network with one hidden layerhas enough number of neurons, it can realize any nonlin-ear mapping. In consideration of the premises, to fulfill therequirements on accuracy and training time-saving, the num-ber of hidden layers is decided to be 1. The structure of a BPneural network is shown in Fig. 3. Each node in the networkis a neuron whose function is to calculate the inner productof the input vector and weight vector by a nonlinear transferfunction to get a scalar result. As we know, the number of thesingle hidden layer node can be calculated by the followingequation: