Lightweight face recognition method and system
A face recognition, lightweight technology, applied in the field of face recognition, can solve the problems of slow recognition speed, large amount of calculation, and large amount of parameters of embedded devices, achieve low calculation amount, strong representation ability, and ease the amount of calculation increased effect
Inactive Publication Date: 2022-05-27
中科南京智能技术研究院
View PDF2 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Aiming at the problems that the existing lightweight face recognition method has too many calculations, too many parameters, and the deployment of
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
[0042] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0043] The purpose of the present invention is to provide a lightweight face recognition method and system, which can improve the recognition speed and reduce the calculation cost on the basis of ensuring the recognition accuracy.
[0044] In order to make the above objects, features and advantages of the present invention more clearly understood, the present invention will be described in further detail below with reference to the ac...
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 relates to a lightweight face recognition method and system. The method comprises the following steps: determining a recognition result by adopting a trained lightweight face recognition model according to a face image; the trained lightweight face recognition model comprises a weight sharing convolution module, a dynamic feature extraction module, a bottleneck layer and a dynamic bottleneck layer; a weight sharing convolution module optimizes all convolution layers and deep convolution layers in the face recognition model; the dynamic feature extraction module comprises an attention module and a parallel aggregation convolution module; the dynamic feature extraction module is alternately used in the trained lightweight face recognition model; the convolution layers in the bottleneck layer are all optimized by using the weight sharing convolution module; and a convolution layer in the dynamic bottleneck layer is subjected to joint nested optimization by using a weight sharing convolution module and a dynamic feature extraction module. On the basis of ensuring the recognition precision, the recognition speed is improved, and the calculation cost is reduced.
Description
technical field [0001] The invention relates to the field of face recognition, in particular to a lightweight face recognition method and system. Background technique [0002] In recent years, with the rapid development of artificial intelligence (Artificial Intelligence, AI) technology, the research pattern of face recognition (Face Recognition, FR) has been reshaped. Since DeepFace and DeepID were proposed in 2014, deep learning-based face recognition Recognition technology is constantly innovating and striving to achieve better performance. DeepFace is the first to use a nine-layer Convolutional Neural Networks (CNN) with several locally connected layers, which utilizes a 3D alignment method for face processing, in the face dataset (Labled Faces in the Wild, The accuracy on LFW) reached 97.35%; in 2015, FaceNet used a large private dataset to train GoogleNet, and finally achieved an accuracy of 99.63%; in the same year, VGGface collected a large amount of face data on th...
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 IPC IPC(8): G06V40/16G06V10/44G06V10/74G06V10/77G06V10/82G06N3/04G06K9/62
CPCG06N3/047G06N3/048G06N3/045G06F18/213G06F18/22
Inventor 李原超李威君王路远游恒尚德龙周玉梅
Owner 中科南京智能技术研究院