Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/97832
PIRA download icon_1.1View/Download Full Text
Title: Encrypted face recognition method and system based on optical speckles
Other Title: 一种基于光学散斑的加密人脸识别方法和系统
Authors: Lai, P 
Zhao, Q 
Li, H
Yu, Z
Issue Date: 13-Sep-2022
Source: 中国专利 ZL202111273688.7
Abstract: The invention discloses an encrypted face recognition method and system based on optical speckles, and the system comprises a face image encryption module which is used for encrypting an original face image based on the optical speckles to obtain an encrypted face image; the face image decryption module is used for inputting the encrypted face image into a trained ciphertext image decryption neural network to obtain a decrypted face image corresponding to the encrypted face image; and the face recognition module is used for recognizing the decrypted face image to obtain a face recognition result. According to the invention, the face image encryption module encrypts the face image based on optical speckles, the encryption key dimension can be improved, then the encrypted face image is decrypted through a neural network in the face image decryption module, and finally the decrypted image is applied to face recognition through the face recognition module. Therefore, the security of the encrypted face recognition system is improved, and the privacy data of the face photo is protected.
本发明公开了一种基于光学散斑的加密人脸识别方法和系统,所述系统包括:人脸图像加密模块,用于基于光学散斑对原始人脸图像进行加密,得到加密人脸图像;人脸图像解密模块,用于将所述加密人脸图像输入已训练的密文图像解密神经网络,得到与所述加密人脸图像对应的解密人脸图像;人脸识别模块,用于将所述解密人脸图像进行识别,得到人脸识别结果。本发明通过人脸图像加密模块基于光学散斑对人脸图像进行加密,可以提升加密的密钥维度,然后通过人脸图像解密模块中的神经网络对加密人脸图像进行解密,最后通过人脸识别模块将解密图像应用于人脸识别,从而提高加密人脸识别系统的安全性,保护人脸照片隐私数据。
Publisher: 中华人民共和国国家知识产权局
Rights: Assignee: 香港理工大学深圳研究院
Appears in Collections:Patent

Files in This Item:
File Description SizeFormat 
ZL202111273688.7.PDF523.9 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Show full item record

Page views

110
Last Week
4
Last month
Citations as of Nov 30, 2025

Downloads

25
Citations as of Nov 30, 2025

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.