Low-resolution face recognition method and system, device and storage medium
A low-resolution, face recognition technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of low-resolution face recognition methods, low work efficiency, high labor costs, etc., to improve recognition accuracy Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0037] In order to illustrate the low-resolution face recognition method provided by the present invention, figure 1 It shows the flow of the low-resolution face recognition method provided by the present invention.
[0038] Such as figure 1 As shown, the low-resolution face recognition method provided by the present invention includes:
[0039] S110: Perform resolution reduction processing on existing pre-collected high-resolution data samples to obtain corresponding low-resolution data samples.
[0040] It should be noted that due to the fact that there are different resolutions in the face capture under the surveillance video, after statistics on the actual surveillance face resolution, there are many low-resolution faces around 30*30, so in the training data set ( Under the collection of high-resolution data samples), the purpose of simulating the real scene is achieved by downsampling the face data in different sizes.
[0041]Specifically, the process of reducing the r...
Embodiment 2
[0079] Corresponding to the above method, the present application also provides a low-resolution face recognition system, which includes:
[0080] A resolution reduction processing unit, configured to perform resolution reduction processing on high resolution data samples to obtain low resolution data samples;
[0081] A network training unit, configured to use the high-resolution data samples and the low-resolution data samples to train a preset dual-channel network, wherein the dual-channel network includes a guide network, a target network, and a discriminator network, so The guide network is used to receive the high-resolution data samples, and the target network is used to receive the low-resolution data samples; the discriminator network is used to discriminate the output data of the guide network and the target network , to achieve confrontation training between the discriminator network and the target network;
[0082] The test unit is used to test the dual-channel ne...
Embodiment 3
[0085] The present invention also provides an electronic device 70 . refer to image 3 As shown, this figure is a schematic structural diagram of a preferred embodiment of the electronic device 70 provided by the present invention.
[0086] In this embodiment, the electronic device 70 may be a server, a smart phone, a tablet computer, a portable computer, a desktop computer, and other terminal devices with computing functions.
[0087] The electronic device 70 includes: a processor 71 and a memory 72 .
[0088] Memory 72 includes at least one type of readable storage media. The at least one type of readable storage medium may be a non-volatile storage medium such as a flash memory, a hard disk, a multimedia card, a memory card, or the like. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 70 , such as a hard disk of the electronic device 70 . In other embodiments, the readable storage medium can also be an external m...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More