Face recognition method, device, system and equipment based on convolutional neural network

Abstract

The invention discloses a face recognition method, device, system and equipment based on a convolutional neural network. The method includes the following steps: S1: face detection, using a multi-layer CNN feature architecture; S2: key point positioning, using deep learning In the middle, multiple reference frame regression networks are cascaded to obtain the position of key points of the face; S3: preprocessing, to obtain a fixed-size face image; S4: feature extraction, the feature representative vector is obtained through the feature extraction model; S5: feature comparison, Judge the similarity according to the threshold or give the face recognition result according to the distance sorting. The present invention adds a combination of multi-layer CNN features to the traditional CNN single-layer feature architecture to cope with different imaging conditions. Based on the deep convolutional neural network algorithm, a model with strong robustness in the monitoring environment is trained from a massive picture data set. The advanced face detection network reduces the false detection rate and improves the detection response speed.

Description

technical field [0001] The present invention relates to the field of face image recognition, in particular to a face recognition method, device, system and equipment based on a convolutional neural network. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. The technology of collecting images or video streams containing human faces with cameras or cameras, automatically detecting and tracking human faces in the images, and then performing a series of related operations on the detected faces is usually called portrait recognition. [0003] The research on human-based face recognition system began in the 1960s. After the 1980s, it was improved with the development of computer technology and optical imaging technology, and it really entered the primary application stage in the late 1990s; the face recognition system was successful. The key lies in whether it has a cutting-edge core algorithm an...

AI Technical Summary

Problems solved by technology

When the light is too bright or too dark, and the picture is slightly blurred, the traditional method cannot accurately detect the face

[0020] 2) Extremely sensitive to face occlusion

In densely populated areas, face occlusion is unavoidable, and the application of traditional methods in this scenario is very limited

[0021] 3) The calculation time of local features is too long, and real-time processing cannot be performed

[0023] 1) The amount of information of traditional artificial features is insufficient, the generalization is poor, and the main steps in the calculation process are serialized

[0024] 2) Classifiers based on statistical methods have poor generalization performance and are unstable in complex scenes

Images