计算机科学 ›› 2018, Vol. 45 ›› Issue (8): 268-271.doi: 10.11896/j.issn.1002-137X.2018.08.048

所属专题: 人脸识别

• 图形图像与模式识别 • 上一篇    下一篇

基于卷积神经网络的人脸信息增强识别研究

王燕, 王双印   

  1. 兰州理工大学计算机与通信学院 兰州730050
  • 收稿日期:2017-07-21 出版日期:2018-08-29 发布日期:2018-08-29
  • 作者简介:王 燕(1971-),女,教授,硕士生导师,主要研究方向为模式识别、数据挖掘,E-mail:wangyan@lut.cn(通信作者); 王双印(1988-),男,硕士生,主要研究方向为模式识别。
  • 基金资助:
    本文受国家自然科学基金:多民族欠发达地区传染病传播动力学特征分析与建模(61263019)资助。

Research on Face Information Enhancement and Recognition Based on Convolutional Neural Network

WANG Yan, WANG Shuang-yin   

  1. School of Computer and Communication,Lanzhou University of Technology,Lanzhou 730050,China
  • Received:2017-07-21 Online:2018-08-29 Published:2018-08-29

摘要: 在采集人脸图像时,图像存在模糊性较大或者姿态变化幅度较大等问题,人脸准确识别的精度不高,为了提高人脸识别的准确率,提出一种基于卷积神经网络的信息增强的人脸识别算法。对采集的模糊人脸图像进行小波降噪处理,对降噪输出的图像进行自适应模板匹配,结合图像分割方法对人脸图像进行分块,利用Radon尺度变换的几何特征不变性对人脸的关键特征点进行信息增强,采用卷积神经网络分类器对增强的人脸特征点进行分类,实现特征点优化提取和人脸准确辨识。仿真结果表明,采用该方法进行人脸识别的准确性较好,且能满足大批量样本人脸快速识别的应用需求。

关键词: Radon尺度变换, 分块, 降噪, 卷积神经网络, 人脸识别, 图像

Abstract: There exist large fuzziness of human face and large change of people’s gesture and other issues when images are collected,and the accuracy of face recognition is not high.In order to improve the accuracy of human face recognition,this paper proposed a new face recognition algorithm based on information enhancement of convolutional neural network.Wavelet denoising is applied to the collected fuzzy face images.Theadaptive template matching is given for output image affter noise reduction,and the face image is segmented by the image segmentation method.The geometric feature invariance of the Radon scale transform is used to implement information enhancement for the key feature points of the face.The convolutional neural network classifier is used to classify the enhanced facial feature points to realize feature point optimization and accurate face recognition.The experiments show that the accuracy of proposed method is better,and the proposed method can fulfill the application requirements of rapid recognition for large-scale sample faces.

Key words: Block, Convolutional neural networks, Face recognition, Image, Noise reduction, Radon scale transform

中图分类号: 

  • TP391.9
[1]TUIA D,PASOLLI E,EMERY W J.Using active learning toadapt remote sensing image classifiers[J].Remote Sensing of Environment,2011,115(9):2232-2242.
[2]JIANG Z,CHENG C L.Improved HOG Face Feature Extrac-tion Algorithm Based on Haar Characteristics[J].Computer Scie-nce,2017,44(1):303-307.(in Chinese)蒋政,程春玲.基于Haar特性的改进HOG的人脸特征提取算法[J].计算机科学,2017,44(1):303-307.
[3]QIU Y,ZHAO J Y,WANG Y F.Facial Expression Recognition Using Temporal Relations Among Facial Movements[J].Acta Electronica Sinica,2016,44(6):1307-1313.(in Chinese)邱玉,赵杰煜,汪燕芳.结合运动时序性的人脸表情识别方法[J].电子学报,2016,44(6):1307-1313.
[4]LI X X,GONG X.3D face modeling and validation in cross-pose face matching[J].Journal of Computer Applications,2017,37(1):262-267.(in Chinese)李昕昕,龚勋.三维人脸建模及在跨姿态人脸匹配中的有效性验证[J].计算机应用,2017,37(1):262-267.
[5]HUANG M,WANG L T,ZHANG H C.Face RecognitionBased on Gabor Wavelet Transform and K-L Gaussian Riemannian Manifold Discriminant[J].Computer Engineering,2016,42(9):208-213.(in Chinese)黄淼,王刘涛,张海朝.基于Gabor小波变换与K-L高斯黎曼流形判别的人脸识别[J].计算机工程,2016,42(9):208-213.
[6]YANG L P,LI W.Low-Rank Relative Gradient Histogram Features for Illumination-Robust Face Recognition[J].Acta Electronica Sinica,2016,44(8):1940-1946.(in Chinese)杨利平,李武.光照健壮人脸识别的低秩相对梯度直方图特征[J].电子学报,2016,44(8):1940-1946.
[7]WANG X Y,ZHANG Y Z,CHEN D Y.Face detection based on MB-LBP and eye tracking[J].Chinese Journal of Scientific Instrument,2014,35(12):2739-2745.(in Chinese)王小玉,张亚洲,陈德运.基于多块局部二值模式特征和人眼定位的人脸检测[J].仪器仪表学报,2014,35(12):2739-2745.
[8]MOHAMMADZADE H,HATZINAKOS D.Iterative closestnormal point for 3D face recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(2):381-397.
[9]ZHANG J.Sparse Orthogonal Procrustes Problem Based Re-gression for Face Recognition with Pose Variations[J].Compu-ter Science,2017,44(2):302-305.(in Chinese)张娟.稀疏正交普鲁克回归处理跨姿态人脸识别问题[J].计算机科学,2017,44(2):302-305.
[10]El-MEZOUAR M C,KPALMA K,TALEB N,et al.A Pan-sharpening Based on the Non-subsampled Contourlet Transform:Application to Worldview-2 Imagery[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(5):1806-1815.
[11]MORENO-SALINAS D,PASCOAL A M,ARANDA J.Optimal sensor placement for multiple target positioning with range-only measurements in two-dimensional scenarios[J].Sensors,2013,13(8):10674-10710.
[12]BHADOURIA V S,GHOSHAL D,SIDDIQI A H.A new approach for high density saturated impulse noise removal using decision-based coupled window median filter[J].Signal,Image and Video Processing,2014,8(1):71-84.
[13]HUANG L W,YANG H H,WANG B.Research and Improvement of Multi-Methods Combining Face Image Illumination Compensation Algorithm.Journal of Chongqing University of Technology(Natural Science),2017,31(11):179-184.(in Chinese)黄丽雯,杨欢欢,王勃.多方法结合人脸图像光照补偿算法研究及改进.重庆理工大学学报(自然科学),2017,31(11):178-184.
[1] 周乐员, 张剑华, 袁甜甜, 陈胜勇.
多层注意力机制融合的序列到序列中国连续手语识别和翻译
Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion
计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[2] 李宗民, 张玉鹏, 刘玉杰, 李华.
基于可变形图卷积的点云表征学习
Deformable Graph Convolutional Networks Based Point Cloud Representation Learning
计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[3] 周连兵, 周湘贞, 崔学荣.
基于双重二维混沌映射的压缩图像加密方案
Compressed Image Encryption Scheme Based on Dual Two Dimensional Chaotic Map
计算机科学, 2022, 49(8): 344-349. https://doi.org/10.11896/jsjkx.210700235
[4] 陈泳全, 姜瑛.
基于卷积神经网络的APP用户行为分析方法
Analysis Method of APP User Behavior Based on Convolutional Neural Network
计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121
[5] 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥.
基于注意力机制的医学影像深度哈希检索算法
Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism
计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[6] 魏恺轩, 付莹.
基于重参数化多尺度融合网络的高效极暗光原始图像降噪
Re-parameterized Multi-scale Fusion Network for Efficient Extreme Low-light Raw Denoising
计算机科学, 2022, 49(8): 120-126. https://doi.org/10.11896/jsjkx.220200179
[7] 王坤姝, 张泽辉, 高铁杠.
基于Hachimoji DNA和QR分解的遥感图像可逆隐藏算法
Reversible Hidden Algorithm for Remote Sensing Images Based on Hachimoji DNA and QR Decomposition
计算机科学, 2022, 49(8): 127-135. https://doi.org/10.11896/jsjkx.210700216
[8] 郭拯危, 付泽文, 李宁, 白澜.
高分辨率斜视聚束SAR回波仿真加速算法研究
Study on Acceleration Algorithm for Raw Data Simulation of High Resolution Squint Spotlight SAR
计算机科学, 2022, 49(8): 178-183. https://doi.org/10.11896/jsjkx.210600066
[9] 檀莹莹, 王俊丽, 张超波.
基于图卷积神经网络的文本分类方法研究综述
Review of Text Classification Methods Based on Graph Convolutional Network
计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064
[10] 武红鑫, 韩萌, 陈志强, 张喜龙, 李慕航.
监督和半监督学习下的多标签分类综述
Survey of Multi-label Classification Based on Supervised and Semi-supervised Learning
计算机科学, 2022, 49(8): 12-25. https://doi.org/10.11896/jsjkx.210700111
[11] 金方焱, 王秀利.
融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取
Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM
计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190
[12] 张颖涛, 张杰, 张睿, 张文强.
全局信息引导的真实图像风格迁移
Photorealistic Style Transfer Guided by Global Information
计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036
[13] 戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮.
基于DNGAN的磁共振图像超分辨率重建算法
Super-resolution Reconstruction of MRI Based on DNGAN
计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105
[14] 刘月红, 牛少华, 神显豪.
基于卷积神经网络的虚拟现实视频帧内预测编码
Virtual Reality Video Intraframe Prediction Coding Based on Convolutional Neural Network
计算机科学, 2022, 49(7): 127-131. https://doi.org/10.11896/jsjkx.211100179
[15] 徐鸣珂, 张帆.
Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法
Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition
计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!