Adaptive Convolutional Neural Network and Its Application in Face Recognition

被引:75
作者
Zhang, Yuanyuan [1 ]
Zhao, Dong [2 ]
Sun, Jiande [2 ,3 ]
Zou, Guofeng [4 ]
Li, Wentao [2 ]
机构
[1] Shandong Acad Sci, Informat Res Inst, Jinan 250014, Peoples R China
[2] Shandong Univ, Sch Informat Sci & Engn, Jinan 250100, Peoples R China
[3] Hisense State Key Lab Digital Media Technol, Qingdao 266061, Peoples R China
[4] Shandong Univ Technol, Coll Elect & Elect Engn, Zibo 255049, Peoples R China
关键词
Convolutional neural network; Network construction; Adaptive convolutional neural network; Global expansion; Local expansion; Incremental learning;
D O I
10.1007/s11063-015-9420-y
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Convolutional neural network (CNN) has more and more applications in image recognition. However, the structure of CNN is often determined after a performance comparison among the CNNs with different structures, which impedes the further development of CNN. In this paper, an adaptive convolutional neural network (ACNN) is proposed, which can determine the structure of CNN without performance comparison. The final structure of ACNN is determined by automatic expansion according to performance requirement. First, the network is initialized by a one-branch structure. The system average error and recognition rate of the training samples are set to control the expansion of the structure of CNN. That is to say, the network is extended by global expansion until the system average error meets the requirement and when the system average error is satisfied, the local network is expanded until the recognition rate meets the requirement. Finally, the structure of CNN is determined automatically. Besides, the incremental learning for new samples can be achieved by adding new branches while keeping the original network unchanged. The experiment results of face recognition on ORL face database show that there is a better tradeoff between the consumption of training time and the recognition rate in ACNN.
引用
收藏
页码:389 / 399
页数:11
相关论文
共 50 条
[41]   Anti-occlusion face recognition algorithm based on a deep convolutional neural network [J].
Wang, Xi ;
Zhang, Wei .
COMPUTERS & ELECTRICAL ENGINEERING, 2021, 96
[42]   Sensitive deep convolutional neural network for face recognition at large standoffs with small dataset [J].
Jalali, Amin ;
Mallipeddi, Rammohan ;
Lee, Minho .
EXPERT SYSTEMS WITH APPLICATIONS, 2017, 87 :304-315
[43]   Genetic algorithm-optimised structure of convolutional neural network for face recognition applications [J].
Rikhtegar, Arash ;
Pooyan, Mohammad ;
Manzuri-Shalmani, Mohammad Taghi .
IET COMPUTER VISION, 2016, 10 (06) :559-566
[44]   A Face Recognition Algorithm Based on Angular Distance Loss Function and Convolutional Neural Network [J].
Xin, Long ;
Su Hansong ;
Liu Gaohua ;
Chen Zhenyu .
LASER & OPTOELECTRONICS PROGRESS, 2018, 55 (12)
[45]   A Face Emotion Recognition Method Using Convolutional Neural Network and Image Edge Computing [J].
Zhang, Hongli ;
Jolfaei, Alireza ;
Alazab, Mamoun .
IEEE ACCESS, 2019, 7 :159081-159089
[46]   Face Recognition Based on Full Convolutional Neural Network Based on Transfer Learning Model [J].
Fan, Zhongkui ;
Guan, Ye-peng .
COMPUTER SCIENCE AND INFORMATION SYSTEMS, 2021, 18 (04) :1395-1409
[47]   Nodules Detection by Deep Convolutional Neural Network and Its Application [J].
Fang, Ruoxi ;
Tang, Haotian ;
Xu, Qiannuo ;
You, Jinxiong .
SECOND IYSF ACADEMIC SYMPOSIUM ON ARTIFICIAL INTELLIGENCE AND COMPUTER ENGINEERING, 2021, 12079
[48]   A Convolutional Neural Network Approach for Face Verification [J].
Khalil-Hani, Mohamed ;
Sung, Liew Shan .
2014 INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING & SIMULATION (HPCS), 2014, :707-714
[49]   Face and Face Mask Detection Using Convolutional Neural Network [J].
Zainal, Muhammad Mustaqim ;
Ambar, Radzi ;
Abd Wahab, Mohd Helmy ;
Poad, Hazwaj Mhd ;
Abd Jamil, Muhammad Mahadi ;
Choon, Chew Chang .
INTELLIGENT HUMAN COMPUTER INTERACTION, IHCI 2021, 2022, 13184 :597-609
[50]   OPFaceNet: OPtimized Face Recognition Network for noise and occlusion affected face images using Hyperparameters tuned Convolutional Neural Network [J].
Lokku, Gurukumar ;
Reddy, G. Harinatha ;
Prasad, M. N. Giri .
APPLIED SOFT COMPUTING, 2022, 117