Face detection algorithm based on LVQ neural network model

Yan WANG; Meng QI

doi:10.37188/CJLCD.2020-0295

您当前的位置：

首页 >

文章列表页 >

Face detection algorithm based on LVQ neural network model

Image Processing | 更新时间：2021-07-13

- Face detection algorithm based on LVQ neural network model
- Chinese Journal of Liquid Crystals and Displays Vol. 36, Issue 7, Pages: 1027-1034(2021)
- 作者机构：
  
  成都工业学院电子工程学院, 四川成都 610031
- 作者简介：
- 基金信息：
  
  Supported by National Natural Science Foundation of China(61705022);Sichuan Province Science and Technology Planning Project(2019YJ0377)
- DOI：10.37188/CJLCD.2020-0295
  CLC： TP394.1
- Received：03 November 2020，
  
  Revised：24 November 2020，
  
  Published：2021-07
- 稿件说明：
移动端阅览
Yan WANG, Meng QI. Face detection algorithm based on LVQ neural network model[J]. Chinese journal of liquid crystals and displays, 2021, 36(7): 1027-1034.
DOI：

Yan WANG, Meng QI. Face detection algorithm based on LVQ neural network model[J]. Chinese journal of liquid crystals and displays, 2021, 36(7): 1027-1034. DOI： 10.37188/CJLCD.2020-0295.

摘要

人脸检测是人脸识别的首要环节。为快速准确地从复杂背景中定位出人脸区域，本文提出一种基于LVQ神经网络的人脸检测算法。通过分析肤色特征，将图像分别转换到YCbCr空间和HSI空间，提取

、

颜色分量用来描述人脸图像特征。构建结构为4-20-2的LVQ神经网络模型，选取100幅图像作为LVQ神经网络的训练样本，20幅图像作为测试样本，迭代次数为150次，误差为0.001。经过训练，得到了有效的权值。利用训练后的神经网络，分别在LFW、AFW和Faces数据集上进行了性能测试，在3个数据集的正检率分别为76.82%，84.42%，100%，误检率分别为17.34%，12.34%，0，漏检率分别为21.55%，15.63%，0。实验结果表明，相对于传统的基于肤色特征的人脸检测方法，本方法在正检率、误检率及漏检率方面均表现出良好的优越性。

Abstract

Face detection is the first step of face recognition. In order to fix the face region from the complex background rapidly

a method based on LVQ is studied in this paper. By analyzing the color features of skin

images are converted into YCbCr space and HSI space firstly

and then

color components are extracted to describe the facial image features. An LVQ neural network with a structure of 4-20-2 is constructed

100 images as training samples and 20 images as test samples are selected for this neural network. The number of iterations is 150 and the error is 0.001. After training

the effective weight are obtained. Using the trained neural network

the performance tests are performed on the LFW

Faces

and AFW datasets. The positive detection rates in the three data sets are 76.82%

84.42%

100%

the false detection rates are 17.34%

12.34%

and 0

and the missed detection rates are 21.55%

15.63%

and 0

respectively. The experimental results show that the method in our paper shows good superiority in terms of positive detection rate

false detection rate and missed detection rate compared with the traditional face detection method based on skin color features.

关键词

Keywords

references

张新景 , 兰育飞 , 史颖刚 . 基于肤色特征的人脸检测 . 信息技术与信息化 , 2019 . ( 4 ): 37 - 39 . DOI: 10.3969/j.issn.1672-9528.2019.04.009 http://doi.org/10.3969/j.issn.1672-9528.2019.04.009 .

X J ZHANG , Y F LAN , Y G SHI . Face detection based on skin color features . Information Technology and Informatization , 2019 . ( 4 ): 37 - 39 . DOI: 10.3969/j.issn.1672-9528.2019.04.009 http://doi.org/10.3969/j.issn.1672-9528.2019.04.009 .

H J LI , C Y SUEN . Robust face recognition based on dynamic rank representation . Pattern Recognition , 2016 . 60 13 - 24 . DOI: 10.1016/j.patcog.2016.05.014 http://doi.org/10.1016/j.patcog.2016.05.014 .

FEI Z, QIANG Q. Face detection based on rectangular knowledge rule and face structure[C]// Proceedings of the 2009 1 st IEEE International Conference on Information Science and Engineering . Nanjing, China: IEEE, 2009: 56-64.

Z Y SHI , M J LIN , Z B GAO , 等 . Face recognition based on improved LBP algorithm . Journal of Computers , 2019 . 30 ( 4 ): 122 - 129 .

ARAKI Y, SHIMADA N, SHIRAI Y. Face detection and face direction estimation using color and shape features[M]//ARAI E, ARAI T, TAKANO M. Human Friendly Mechatronics , Amsterdam: Elsevier, 2001: 229-234.

F A PUJOL , M PUJOL , A JIMENO-MORENILLA , 等 . Face detection based on skin color segmentation using fuzzy entropy . Entropy , 2017 . 19 ( 1 ): 26 DOI: 10.3390/e19010026 http://doi.org/10.3390/e19010026 .

林国军 , 杨明中 , 陈明举 , 等 . 一种肤色定位的人脸检测算法 . 液晶与显示 , 2019 . 34 ( 1 ): 70 - 73 . http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193401.0070&graphicAbstract=0 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193401.0070&graphicAbstract=0 .

G J LIN , M Z YANG , M J CHEN , 等 . Face detection algorithm based on skin color location . Chinese Journal of Liquid Crystals and Displays , 2019 . 34 ( 1 ): 70 - 73 . http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193401.0070&graphicAbstract=0 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193401.0070&graphicAbstract=0 .

李明 , 平凯 , 年福忠 . 基于彩色人脸模板的人脸检测算法 . 计算机工程与应用 , 2014 . 50 ( 15 ): 153 - 156 . DOI: 10.3778/j.issn.1002-8331.1208-0455 http://doi.org/10.3778/j.issn.1002-8331.1208-0455 .

M LI , K PING , F Z NIAN . Algorithm of human-face detection based on color face template . Computer Engineering and Applications , 2014 . 50 ( 15 ): 153 - 156 . DOI: 10.3778/j.issn.1002-8331.1208-0455 http://doi.org/10.3778/j.issn.1002-8331.1208-0455 .

邵平 , 杨路明 , 黄海滨 . 适于人脸检测的模板匹配快速算法 . 计算机应用 , 2006 . 26 ( 7 ): 1607 - 1610 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY200607036.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY200607036.htm .

P SHAO , L M YANG , H B HUANG . Rapid algorithm of template matching for face detection . Computer Applications , 2006 . 26 ( 7 ): 1607 - 1610 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY200607036.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY200607036.htm .

H Z AI , L H LIANG , G Y XU . Face detection based on template matching and support vector machines . Chinese Journal of Computers , 2002 . 1 ( 1 ): 1006 - 1009 . http://ieeexplore.ieee.org/document/959218 http://ieeexplore.ieee.org/document/959218 .

A SOULA , K TBARKI , R KSANTINI , 等 . A novel incremental kernel nonparametric SVM model (iKN-SVM) for data classification: an application to face detection . Engineering Applications of Artificial Intelligence , 2020 . 89 103468 DOI: 10.1016/j.engappai.2019.103468 http://doi.org/10.1016/j.engappai.2019.103468 .

刘燕 , 贺松 , 成雨风 . 一种改进型Adaboost算法的人脸检测 . 智能计算机与应用 , 2019 . 9 ( 5 ): 98 - 101, 110 . https://www.cnki.com.cn/Article/CJFDTOTAL-DLXZ201905023.htm https://www.cnki.com.cn/Article/CJFDTOTAL-DLXZ201905023.htm .

Y LIU , S HE , Y F CHENG . An improved Adaboost algorithm for face detection . Intelligent Computer and Applications , 2019 . 9 ( 5 ): 98 - 101, 110 . https://www.cnki.com.cn/Article/CJFDTOTAL-DLXZ201905023.htm https://www.cnki.com.cn/Article/CJFDTOTAL-DLXZ201905023.htm .

LI H X, LIN Z, SHEN X H, et al . A convolutional neural network cascade for face detection[C]// Proceedings of 2015 Computer Vision and Pattern Recognition . Boston, USA: IEEE, 2015: 1123-1127.

C M BISHOP . Pattern recognition and machine learning . Information Science and Statistics , 2006 . 56 ( 23 ): 198 - 201 . http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1057854 http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1057854 .

Y B YING , J P WANG , H Y JIANG . Inspecting diameter and defect area of fruit with machine vision . Transactions of the CSAE , 2002 . 18 ( 5 ): 216 - 220 . http://en.cnki.com.cn/Article_en/CJFDTOTAL-NYGU200205041.htm http://en.cnki.com.cn/Article_en/CJFDTOTAL-NYGU200205041.htm .

范丽丽 , 赵宏伟 , 赵浩宇 , 等 . 基于深度卷积神经网络的目标检测研究综述 . 光学精密工程 , 2020 . 28 ( 5 ): 1152 - 1164 . https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM202005019.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM202005019.htm .

L L FAN , H W ZHAO , H Y ZHAO , 等 . Survey of target detection based on deep convolutional neural networks . Optics and Precision Engineering , 2020 . 28 ( 5 ): 1152 - 1164 . https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM202005019.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM202005019.htm .

王春哲 , 安军社 , 姜秀杰 , 等 . 基于卷积神经网络的候选区域优化算法 . 中国光学 , 2019 . 12 ( 6 ): 1348 - 1361 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA201906018.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA201906018.htm .

C Z WANG , J S AN , X J JIANG , 等 . Region proposal optimization algorithm based on convolutional neural networks . Chinese Optics , 2019 . 12 ( 6 ): 1348 - 1361 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA201906018.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA201906018.htm .

黄乐弘 , 曹立华 , 李宁 , 等 . 深度学习的空间红外弱小目标状态感知方法 . 中国光学 , 2020 . 13 ( 3 ): 527 - 536 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA202003014.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA202003014.htm .

L H HUANG , L H CAO , N LI , 等 . A state perception method for infrared dim and small targets with deep learning . Chinese Optics , 2020 . 13 ( 3 ): 527 - 536 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA202003014.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA202003014.htm .

L H HUANG , L H CAO , N LI , 等 . A state perception method for infrared dim and small targets with deep learning . Chinese Optics , 2019 . 12 ( 6 ): 1348 - 1361 . DOI: 10.3788/co.20191206.1348 http://doi.org/10.3788/co.20191206.1348 .

张敏灵 , 陈兆乾 , 周志华 . SOM算法、LVQ算法及其变体综述 . 计算机科学 , 2002 . 29 ( 7 ): 97 - 100 . DOI: 10.3969/j.issn.1002-137X.2002.07.030 http://doi.org/10.3969/j.issn.1002-137X.2002.07.030 .

M L ZHANG , Z Q CHEN , Z H ZHOU . Survey on SOM algorithm, LVQ algorithm and their variants . Computer Science , 2002 . 29 ( 7 ): 97 - 100 . DOI: 10.3969/j.issn.1002-137X.2002.07.030 http://doi.org/10.3969/j.issn.1002-137X.2002.07.030 .

L Y DENG . Genetic algorithm LVQ neural network application in remote sensing image classification . Modern Electronic Technology , 2020 . ( 1 ): 40 - 43 .

Q ZHANG , X ZHANG , Y TIAN , 等 . Study on recognition of wear degree of pick based on LVQ neural network . Journal of Sensing Technology , 2018 . 31 ( 11 ): 105 - 110 . http://www.researchgate.net/publication/330885012_Research_on_Recognition_of_Pick_Cutting_Wear_Degree_Based_on_LVQ_Neural_Network http://www.researchgate.net/publication/330885012_Research_on_Recognition_of_Pick_Cutting_Wear_Degree_Based_on_LVQ_Neural_Network .

刘文轩 , 严凤 , 田霖 , 等 . 基于LVQ神经网络的配电网故障定位方法 . 电力系统保护与控制 , 2012 . 40 ( 5 ): 90 - 95 . DOI: 10.3969/j.issn.1674-3415.2012.05.017 http://doi.org/10.3969/j.issn.1674-3415.2012.05.017 .

W X LIU , F YAN , L TIAN , 等 . LVQ neural network approach for fault location of distribution network . Power System Protection and Control , 2012 . 40 ( 5 ): 90 - 95 . DOI: 10.3969/j.issn.1674-3415.2012.05.017 http://doi.org/10.3969/j.issn.1674-3415.2012.05.017 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Face detection algorithm based on skin color location

3 D human-machine interaction based on human eye detection

Human eye locating and tracking using space-time context and random forest

Related Author

Meng QI

Yan WANG

Guo-jun LIN

Ming-zhong YANG

Ming-ju CHEN

Mei XIE

Jia-hui HUANG

Zhi-gang CAI

Related Institution

Chengdu Technological University

School of Automation & Information Engineering, Sichuan University of Science & Engineering

School of Electronic Engineering, University of Electronic Science and Technology of China

School of Electronics and Information Technology, SunYat-sen University

Physics Experiment Teaching Center, School of Physics,Sun Yat-sen University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰