Wavelet-based illumination normalization algorithm for face recognition

doi:10.3778/j.issn.1002-8331.2010.06.051

Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (6): 174-177.DOI: 10.3778/j.issn.1002-8331.2010.06.051

• 图形、图像、模式识别 • Previous Articles Next Articles

Wavelet-based illumination normalization algorithm for face recognition

FAN Chun-nian^1，2，WANG Shui-ping¹，ZHANG Fu-yan²

1.Computer and Software Institute，Nanjing University of Information Science & Technology，Nanjing 210044，China
2.Department of Computer Science and Technology，Nanjing University，Nanjing 210093，China

Received:2008-08-27 Revised:2008-11-12 Online:2010-02-21 Published:2010-02-21
Contact: FAN Chun-nian

一种基于小波的人脸图像光照归一化算法

范春年^1，2，王水平¹，张福炎²

1.南京信息工程大学计算机与软件学院，南京 210044
2.南京大学计算机科学与技术系，南京 210093

通讯作者: 范春年

Abstract

Abstract: The appearance of a face image is severely affected by illumination conditions that hinder the automatic face recognition process.To recognize faces under varying illuminations，a wavelet-based normalization method is proposed so as to normalize illuminations.An image is decomposed into its low frequency and high frequency components.Then different band coefficients are manipulated separately.Histogram equalization is applied to the approximation（low frequency） coefficients and at the same time accentuate the detail（high frequency） coefficients by multiplying by a scalar so as to enhance edges.A normalized image is obtained from the modified coefficients by inverse wavelet transform.Finally，PCA method is used to recognize normalized image with only one training sample.The experimental results obtained by testing on the AR face database and FERRET face database demonstrate the effectiveness of this method with significant improvement in the face recognition system.

Key words: face recognition, wavelet analysis, illumination normalization

摘要： 光照变化严重影响了人脸图像的外貌，这阻碍了人脸识别的过程。为了识别可变光照下的人脸图像，提出了一种基于小波的光照归一化算法，将一幅图像分解为低频成分和高频成分，对不同的频带成分进行不同的操作——对低频成分进行直方图均衡化，同时着重强调细节（高频成分），将它乘以一个标量从而增强图像边缘；对修改后的系数进行逆小波变换就得到归一化后的图像。最后，直接使用PCA方法对单训练样本条件下的人脸进行识别，在AR和FERRET人脸库上的实验结果表明，提出的方法可以显著提高人脸识别系统的识别率。

关键词: 人脸识别, 小波分析, 光照归一化

CLC Number:

TP391

FAN Chun-nian^1，2，WANG Shui-ping¹，ZHANG Fu-yan². Wavelet-based illumination normalization algorithm for face recognition[J]. Computer Engineering and Applications, 2010, 46(6): 174-177.

范春年^1，2，王水平¹，张福炎². 一种基于小波的人脸图像光照归一化算法[J]. 计算机工程与应用, 2010, 46(6): 174-177.

[1]	QIAO Hui, ZHOU Shuisheng. Nolinear Angle 2DPCA and Its Application on Face Recognition [J]. Computer Engineering and Applications, 2021, 57(8): 112-118.
[2]	HU Wentao, CHEN Xiuhong. Low-Rank Projection Learning Based on Neighbor Graph [J]. Computer Engineering and Applications, 2021, 57(7): 209-214.
[3]	WANG Peng, YE Xueyi, WANG Tao, QIAN Dingwei. Face Recognition Based on Double Variation and Double Space Local Directional Pattern [J]. Computer Engineering and Applications, 2021, 57(4): 91-99.
[4]	SHI Zhengyu, CHEN Renwen, HUANG Bin. Low-Resolution Face Recognition Based on Self-Normalizing Neural Network [J]. Computer Engineering and Applications, 2021, 57(3): 137-143.
[5]	LI Junyao, LI Zhihui, XIE Lanchi, HOU Xinyu, YE Dong. Advances of Age Progression Based Cross-Age Face Recognition [J]. Computer Engineering and Applications, 2021, 57(24): 27-38.
[6]	LIU Jinjin, LI Qingbao, LI Xiaonan. Neural Network Compression Algorithm Based on Adversarial Learning and Knowledge Distillation [J]. Computer Engineering and Applications, 2021, 57(21): 180-187.
[7]	XU Xialing, LIU Tao, TIAN Guohui, YU Wenjuan, XIAO Dajun, LIANG Shanpeng. Review of Occlusion Face Recognition Methods [J]. Computer Engineering and Applications, 2021, 57(17): 46-60.
[8]	XU Ranran, WU Xiaojun, YIN Hefeng. Face Recognition via Discriminative Non-negative Representation Based Classification [J]. Computer Engineering and Applications, 2021, 57(13): 147-153.
[9]	WANG Yu, LIU Fan, WANG Fei. Autoencoder Based Sparse Representation for Single Sample Face Recognition [J]. Computer Engineering and Applications, 2021, 57(1): 168-172.
[10]	DONG Yanhua, ZHANG Shumei, ZHAO Junli. Review of Occlusion Face Recognition Method [J]. Computer Engineering and Applications, 2020, 56(9): 1-12.
[11]	LIN Kezheng, ZHANG Yuanming, LI Haotian. Research on HOG Feature Extraction Algorithm Weighted by Information Entropy [J]. Computer Engineering and Applications, 2020, 56(6): 147-152.
[12]	YUAN Xiaoping, CUI Qiwen, CHENG Gan, ZHANG Xia, ZHANG Yi, WANG Suyuan. Improved Gabor Self Quotient Image Algorithm and Its Application to Face Recognition [J]. Computer Engineering and Applications, 2020, 56(5): 206-213.
[13]	ZHANG Feixiang, YU Xueru, HE Weifeng, LI Chen. Face Recognition with Improved Loss Function and Multiple-Norm [J]. Computer Engineering and Applications, 2020, 56(24): 144-150.
[14]	CHEN Zhe, WU Xiaojun. Robust Face Recognition Algorithm Based on Structured Low-Rank Recovery [J]. Computer Engineering and Applications, 2019, 55(6): 126-132.
[15]	BAI Chuang, CHEN Xiang. Research on New LeNet-FC Convolutional Neural Network Model Algorithm [J]. Computer Engineering and Applications, 2019, 55(5): 105-111.

Wavelet-based illumination normalization algorithm for face recognition

一种基于小波的人脸图像光照归一化算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics