Face recognition living body detection method based on pre-training picture residual error

The invention discloses a face recognition living body detection method based on a pre-training picture residual error. The method specifically comprises the following steps: carrying out average face processing on a data set; performing residual error on the input judged picture and the average face to obtain a residual error image; and inputting the processed image into a neural network to obtain a judgment result. According to the method, the image residual error of the average face model is compared, the result is obtained through judgment according to the neural network model, and based on the common neural network model ShuffleNet, the time consumption is low, the speed is high, and the accuracy of using a single lens is equivalent to the recognition rate of a multimode lens. The generalization of the model can be obviously enhanced by using the mode of comparing the picture residual error of the average face model, and the single-lens scheme is used, so that the application range is wide, the cost is l