Face recognition method, device and electronic equipment based on deep learning
A technology of face recognition and deep learning, which is applied in the field of face recognition, can solve the problems of high model speed and other problems, and achieve the effects of reducing model size, improving algorithm performance, and increasing running speed
Active Publication Date: 2020-06-19
智慧眼科技股份有限公司
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The present invention provides a face recognition method, device and electronic equipment based on deep learning, which is suitable for face feature extraction at the front end, so as to solve the technical problem that the existing model is too large and the speed is slow
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0028] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and examples.
[0029] The preferred embodiment of the present invention provides a face recognition method based on deep learning, which can transplant the algorithm to front-ends with limited hardware devices such as mobile phones, embedded devices, etc. under the condition of sacrificing a small recognition rate. refer to figure 1 , the method includes the following steps:
[0030] Step S100, constructing a convolutional neural network model, the convolutional neural network model includes sequentially connected first convolutional units, a first pooling layer, multiple convolutional combinations, a second pooling layer and a fully connected layer, wherein, The first convolutional unit includes a first co...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a face recognition method, device and electronic equipment based on deep learning. The method includes: constructing a convolutional neural network model, the convolutional neural network model includes a sequentially connected first convolutional unit, a first pool layer, a combination of multiple convolutions, a second pooling layer, and a fully connected layer, where the first convolutional unit includes the first convolutional layer, a batch normalization layer, and an activation function layer, and the activation function layer uses the ReLU function at the same time The NReLU function is used as the activation function, and the short-circuit layer of the residual network is used to connect the adjacent convolutional combinations; the convolutional neural network model is trained, the training data is input into the convolutional neural network model, and the stochastic gradient descent method is used for training , the trained convolutional neural network model removes the last fully connected layer and only performs forward propagation, which can be used as the face feature data required for face recognition. The present invention uses ReLU+NReLU as the excitation function, which can reduce the calculation amount, ensure the accuracy, reduce the size of the model and improve the running speed.
Description
technical field [0001] The present invention relates to the field of face recognition, in particular, to a face recognition method, device and electronic equipment based on deep learning. Background technique [0002] Due to the convenience of the face, face recognition technology has become a hot spot in surveillance, security, finance, social security and other fields. With the help of feature learning of deep learning in recent years, face recognition technology has made great progress. Now many factors such as different lighting, posture, and expression are relatively robust. [0003] In recent years, face detection methods are divided into two categories according to whether deep learning methods are used. Algorithms that do not use deep learning methods have better results, such as joint cascade face detection and align (JDA) and Normalized Pixel Difference (NPD). The JDA method combines face detection and face key point detection, and uses a relatively simple pixel ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06V40/16
Inventor 周孺杨东王栋
Owner 智慧眼科技股份有限公司