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

Abstract

The invention discloses a face recognition method, device, system and apparatus based on a convolutional neural network (CNN). The method comprises the following steps: S1, face detection: using a multilayer CNN feature architecture; S2, key point positioning: obtaining the key point positions of the face by using connecting reference frame regression networks in a cascaded way in deep learning; S3, preprocessing: obtaining a face image with a fixed size; S4, feature extraction: obtaining a feature representative vector by means of a feature extraction model; and S5: feature comparison: determining the similarity according to a threshold or giving a face recognition result according to distance sorting. The method adds a multilayer CNN feature combination to a traditional CNN single-layer feature architecture to treat different imaging conditions, trains a face detection network with good robustness in the monitoring environment from massive image data sets based on a deep convolution neural network algorithm, reduces a false detection rate, and improves 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