基于CycleGAN的非配对人脸图片光照归一化方法

曾碧; 任万灵; 陈云华

doi:10.12052/gdutxb.180031

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于CycleGAN的非配对人脸图片光照归一化方法

综合研究 | 更新时间：2026-05-27

- 基于CycleGAN的非配对人脸图片光照归一化方法
- An Unpaired Face Illumination Normalization Method Based on CycleGAN
- 广东工业大学学报 2018年35卷第5期页码：11-19
- 作者机构：
  
  广东工业大学　计算机学院,广东,广州,510006
- 作者简介：
  
  曾碧(1963–)，女，教授，博士，主要研究方向为智能机器人、机器学习
- 基金信息：
  
  国家自然科学基金资助项目(61703115);广东省自然科学基金资助项目(2016A030313713);广东省重大科技专项项目(2016B010108004);广东省产学研合作专项项目(2014B090904080)
- DOI：10.12052/gdutxb.180031
  中图分类号： TP391
- 网络首发：2018-07-10，
  
  纸质出版：2018
- 稿件说明：
移动端阅览
曾碧, 任万灵, 陈云华. 基于CycleGAN的非配对人脸图片光照归一化方法[J]. 广东工业大学学报, 2018, 35(5): 11-19.

Zeng Bi, Ren Wan-ling, Chen Yun-hua. An Unpaired Face Illumination Normalization Method Based on CycleGAN[J]. 2018, 35(5): 11-19.
曾碧, 任万灵, 陈云华. 基于CycleGAN的非配对人脸图片光照归一化方法[J]. 广东工业大学学报, 2018, 35(5): 11-19. DOI： 10.12052/gdutxb.180031.

Zeng Bi, Ren Wan-ling, Chen Yun-hua. An Unpaired Face Illumination Normalization Method Based on CycleGAN[J]. 2018, 35(5): 11-19. DOI： 10.12052/gdutxb.180031.

摘要

针对人脸识别过程中光照对识别结果的影响问题

提出了一种基于CycleGAN的光照归一化方法. 使用了生成对抗式的网络结构

利用图像翻译的原理

将较亮图片的光照风格迁移至较暗图片

同时保持原人脸表面平滑且结构基本不变. 使用非配对的数据集

无需人工标注标签

简化了数据准备阶段的工作

达到了利用无监督的深度学习方法去除图片光照影响的目的. 最后用训练好的模型处理CroppedYale测试集

比较处理前后的人脸识别准确率. 实验证明

本文方法具有较强的降低人脸光照对识别率影响的能力且基本不改变人脸结构

有利于提高人脸识别的准确率.

Abstract

Aiming at the influence of illumination in face recognition process

a method of illumination normalization based on CycleGAN is presented. By using the Generative Adversarial Nets and the principle of image translation

the illumination style of the darker image was shifted to the brighter image

while the surface and the structure of the face kept smooth at the same time. Unpaired data sets without labels are used

in order to achieve unsupervised removal of illumination

and greatly simplify the work of data preprocessing. Finally

the CroppedYale data set is used to train a deep learning face recognition model

using this CycleGAN model to process the test set

and comparing the accuracy before and after processing. Experiments show that this method has a strong ability to reduce the influence of human face illumination on recognition rate while basically not changing the face structure

and therefore is helpful to improve the accuracy of face recognition.

关键词

Keywords

references

CHEN X, ZHANG J, CHEN W W, et al . Convolutional neural network algorithm and case [J ] . Journal of Guangdong University of Technology, 2017, 34(6): 20-26.

LEE P H, WU S W, HUNG Y P. Illumination compensation using oriented local histogram equalization and its application to face recognition [J]. IEEE Transactions on Image processing, 2012, 21(9): 4280-4289.

CHEN W, ER M J, WU S. Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2006, 36(2): 458-466.

白小叶. 光照变化下的人脸识别算法研究[D]. 南京: 南京邮电大学通信与信息工程学院, 2016.

NIE X F, YANG Z J, HE X. Face illumination processing using discrete cosine transform and gradient faces [J]. Microcomputer it’s applications, 2017, 36(11): 50-53.

GOODFELLOW I J, POUGET-ABADIE J, Mirza M, et al. Generative adversarial nets[C]// International Conference on Neural Information Processing Systems. Massachusetts: MIT Press, 2014: 2672-2680.

RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. arXiv preprint arXiv: 1511.06434, 2015.

MIRZA M, OSINDERO S. Conditional generative adversarial nets[J]. arXiv preprint arXiv: 1411.1784, 2014.

ZHU J Y, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[J]. arXiv preprint arXiv: 1703.10593, 2017.

ISOLA P, ZHU J Y, ZHOU T H, et al. Image-to-image translation with conditional adversarial networks[J]. arXiv preprint arXiv: 1611.07004, 2016.

ULYANOV D, VEDALDI A, LEMPITSKY V. Instance normalization: The missing ingredient for fast stylization[J]. arXiv preprint arXiv: 1607.08022, 2016.

CLEVERT D A, UNTERTHINER T, HOCHREITER S. Fast and accurate deep network learning by exponential linear units (elus)[J]. arXiv preprint arXiv: 1511.07289, 2015.

GAO W, CAO B, SHAN S G, et al . The CAS-PEAL large-scale Chinese face database and baseline evaluations [J ] . IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 2007, 38(1): 149-161.

GEORGHIADES A S, BELHUMEUR P N, KRIEGMAN D J. From few to many: illumination cone models for face recognition under variable lighting and pose [J]. IEEE Transactions on Pattern Analysis Machine Intelligence, 2001, 23(6): 643-660.

LEE K C, HO J, KRIEGMAN D J. Acquiring linear subspaces for face recognition under variable lighting [J]. IEEE Transactions on Pattern Analysis Machine Intelligence, 2005, 27(5): 684-98.

WU X, HE R, SUN Z N, et al. A light CNN for deep face representation with noisy labels[J]. arXiv preprint arXiv: 1511.02683, 2015.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向电力场景图像的动态自适应增量目标检测DA-IOD算法

基于域不变判别特征学习的深子域自适应方法

基于主动学习和视觉状态空间模型的热点检测器

基于数字混频的脉冲式激光测距方法的研究与实现

具守恒量波动方程的循环双子网物理信息神经网络