Face identification method based on variable-speed learning deep auto-encoder network

Abstract

The invention provides a face identification method based on a variable-speed learning deep auto-encoder network, and belongs to the mode identification field of the deep neural network. The method comprises the following contents: images comprise a training image and a to-be-identified image; the steps are as follows: firstly preprocessing the training image to obtain normalized data; secondly inputting the preprocessed training data into the deep auto-encoder network, guiding the layer-by-layer pre-training of the deep auto-encoder network through a variable-speed learning policy, and addinga classifier on the top layer of the network, further optimizing the network through fine adjustment to acquire an identification model; identifying the preprocessed to-be-identified face image, outputting an identification result, and counting an identification rate. The capacity of discovering the data substantive characteristics of the deep auto-encoder network is sufficiently utilized by themodel, and the characteristics learning speed and the network convergence speed are accelerated at the same time, thereby obtaining more optimal identification performance.

Description

technical field [0001] The invention belongs to the field of pattern recognition of a deep neural network, and in particular relates to a face image recognition model of a variable-speed learning deep self-encoding network. This model makes full use of the ability of the deep self-encoding network to discover the essential characteristics of the data, and at the same time speeds up the feature learning speed and the convergence speed of the network, and improves the performance of face recognition. Background technique [0002] Face recognition is a popular research direction in the field of computer vision, and it is also the main content involved in the application of pattern recognition. The deep self-encoding network can simulate the principle of human neuron activity, and learn the internal features of different levels of face images independently, so that face recognition can get rid of the complex and inefficient use of traditional manual feature extraction. In the r...

AI Technical Summary

Problems solved by technology

Usually, the learning rate is obtained based on experience after a large number of trial and error experiments. This method is time-consuming and laborious, and the learning rate obtained is for the entire network rather than individual features, so the efficiency is not high.

Images