Training method of deep convolutional neural network for face recognition

Abstract

The invention discloses a training method of a deep convolutional neural network for face recognition. The method comprises the following steps: 1) preparing a face image data set, dividing the face image data set into a training set and a verification set, and selecting the type, the structure, the hyper-parameter and the magnitude of a deep convolutional neural network model according to the scale and the complexity of the training set and the performance index of face recognition which should be achieved; 2) extracting features of face pictures input by the training set by using the model,and taking the features as input in the step 3); 3) constructing a loss layer, and iteratively calculating a loss value for the training; 4) comparing the loss value calculated in the step 3) with a preset threshold value, judging whether training is stopped or the gradient is calculated, and updating model parameters; and 5) verifying the model performance, and determining whether to stop training. According to the method, the human face features can be constrained by using a multivariate acting force from two aspects of an Euclidean space and an angle space during training, so that the deepconvolutional neural network model can learn the human face features with higher discrimination and robustness.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a training method for a deep convolutional neural network for face recognition. Background technique [0002] Face recognition is a biometric technology for identification based on human facial image information. Compared with identification technologies such as fingerprints and pupils, it has significant advantages such as non-contact, low threshold for collecting information, and high recognition rate. When conducting face verification, since the collection process is non-contact, it can not only reduce the resistance of the person being collected, but also ensure the hygiene and safety of the collection process, especially for epidemic prevention inspections during the epidemic, which can effectively reduce the possibility of virus infection. In addition, face recognition has a wide range of application scenarios, such as building access control systems, monitoring s...

AI Technical Summary

Problems solved by technology

However, the constraints generated by these loss functions have the problem of a single type of action, which cannot effectively and flexibly drive feature points to achieve a better distribution

In addition, there are still some feature points distributed near the spatial origin during training, and these feature points are difficult to gather to their respective class centers, which makes it difficult for the entire training process to converge

Images