Fly facial recognition based on deep convolutional neural network

Yan-tong CHEN; Wei-nan CHEN; Xian-zhong ZHANG; Yu-yang LI; Jun-sheng WANG

doi:10.37188/OPE.20202807.1558

您当前的位置：

首页 >

文章列表页 >

Fly facial recognition based on deep convolutional neural network

Information Sciences | 更新时间：2020-08-13

- Fly facial recognition based on deep convolutional neural network
- Optics and Precision Engineering Vol. 28, Issue 7, Pages: 1558-1567(2020)
- 作者机构：
  
  大连海事大学信息科学技术学院, 辽宁大连 116026
- 作者简介：
- 基金信息：
- DOI：10.37188/OPE.20202807.1558
  CLC： TP306
- Received：10 January 2020，
  
  Revised：08 March 2020，
  
  Accepted：08 March 2020，
  
  Published：15 July 2020
- 稿件说明：
移动端阅览
Yan-tong CHEN, Wei-nan CHEN, Xian-zhong ZHANG, et al. Fly facial recognition based on deep convolutional neural network[J]. Optics and precision engineering, 2020, 28(7): 1558-1567.
DOI：

Yan-tong CHEN, Wei-nan CHEN, Xian-zhong ZHANG, et al. Fly facial recognition based on deep convolutional neural network[J]. Optics and precision engineering, 2020, 28(7): 1558-1567. DOI： 10.37188/OPE.20202807.1558.

摘要

针对蝇类昆虫物种繁多、特征复杂等因素，导致蝇类识别准确率低、耗时较长等问题。本文借鉴深度学习方法中的人脸识别算法，提出一种基于深度卷积神经网络的蝇类面部识别方法。首先，在图像对齐过程中，使用多任务卷积神经网络并进行优化即应用深度可分离卷积减少计算参数，缩短图像预处理时间。其次，应用轮廓特征粗提取和具体部位特征细提取相结合的方式提取更加丰富的特征信息：即使用卷积池化粗提取出图像的轮廓特征值；同时，使用Inception-ResNet网络、Reduction网络细提取出具体部位特征值。最终在网络训练时，结合上述方法使得提取到的特征信息更加精确全面。实验表明，所提方法的准确率达到94.03%，相较于其他网络训练方法，该方法在保证较高准确率的情况下提升计算效率。

Abstract

Given the large number of species of flies and their individual complex characteristics

recognizing a particular type of fly has proved to be time consuming and

for the most part

inaccurate. In this paper

a method for the facial recognition of a fly using deep learning technologies was proposed

specifically a Convolutional Neural Network (CNN)

and its related face recognition algorithms. Initially

a multi-task convolutional neural network was utilized and optimized for the image alignment process. Thus

depth-wise separable convolutions were applied to reduce the number of calculation parameters as well as the image preprocessing time. Next

we combined the rough extraction of contour features and fine extraction of specific parts to derive more abundant feature information. The convolution and pooling layers were harnessed to elicit contour eigenvalues of the image

while Inception-ResNet and Reduction networks were administered simultaneously to obtain eigenvalues of specific parts. Finally

the above methods were coalesced to enhance the accuracy and comprehensibility of the resultant feature information for network training. Experimental results show that the mean average precision of the proposed method is 94.03%. When compared with other network training methods

this method not only improves the computational efficiency but also ensures high accuracy.

关键词

Keywords

references

刘颖 , 张倩楠 , 王富平 , 等 . 基于颜色通道融合特征的现勘图像分类算法 . 现代电子技术 , 2020 . 43 ( 4 ): 67 - 72 . http://d.old.wanfangdata.com.cn/Periodical/xddzjs202004017 http://d.old.wanfangdata.com.cn/Periodical/xddzjs202004017 .

Y LIU , Q N ZHANG , F P WANG , 等 . Classification algorithm of prospecting image based on color channel fusion feature . Modern Electronics Technique , 2020 . 43 ( 4 ): 67 - 72 . http://d.old.wanfangdata.com.cn/Periodical/xddzjs202004017 http://d.old.wanfangdata.com.cn/Periodical/xddzjs202004017 .

黄鸿 , 李政英 , 石光耀 , 等 . 面向高光谱影像分类的多特征流形鉴别嵌入 . 光学精密工程 , 2019 . 27 ( 3 ): 726 - 738 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201903024 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201903024 .

H HUANG , ZH Y LI , G Y SHI , 等 . Multi-feature manifold discriminant embedding for hyperspectral image classification . Opt. Precision Eng. , 2019 . 27 ( 3 ): 726 - 738 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201903024 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201903024 .

吴潇颖 , 李锐 , 吴胜昔 . 基于CNN与双向LSTM的行为识别算法 . 计算机工程与设计 , 2020 . 41 ( 2 ): 361 - 366 . http://d.old.wanfangdata.com.cn/Periodical/jsjgcysj202002010 http://d.old.wanfangdata.com.cn/Periodical/jsjgcysj202002010 .

X Y WU , R LI , SH X WU . Behavior recognition algorithm based on CNN and bi-directional LSTM . Computer Engineering & Design , 2020 . 41 ( 2 ): 361 - 366 . http://d.old.wanfangdata.com.cn/Periodical/jsjgcysj202002010 http://d.old.wanfangdata.com.cn/Periodical/jsjgcysj202002010 .

HUANG , LAN , YANG , 等 . Deep learning versus Object-based Image Analysis (OBIA) in weed mapping of UAV imagery . International Journal of Remote Sensing , 2020 . 41 ( 9 ): 221 - 227 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=10.1080/01431161.2019.1706112 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=10.1080/01431161.2019.1706112 .

KANG B N, KIM Y, KIM D. Deep convolutional neural network using triplets of faces, deep ensemble, and score-level fusion for face recognition[C] 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE , 2017: 76-84.

HE K, ZHANG X, REN S, et al.. Deep residual learning for image recognition[C] 2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE , 2016: 770-778.

W W SHI , Y H GONG , X Y TAO , 等 . Fine-grained image classification using modified DCNNs Trained by cascaded softmax and generalized large-margin losses . IEEE transactions on neural networks and learning systems , 2019 . 30 ( 3 ): 683 - 694 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=9abe58bbdc0660a43c3ca996c3a383ca http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=9abe58bbdc0660a43c3ca996c3a383ca .

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 . http://d.old.wanfangdata.com.cn/Periodical/zggxyyygxwz201906016 http://d.old.wanfangdata.com.cn/Periodical/zggxyyygxwz201906016 .

CH ZH WANG , J SH AN , X J JIANG , 等 . Candidate region optimization algorithm based on convolutional neural network . Chinese Optics , 2019 . 12 ( 6 ): 1348 - 1361 . http://d.old.wanfangdata.com.cn/Periodical/zggxyyygxwz201906016 http://d.old.wanfangdata.com.cn/Periodical/zggxyyygxwz201906016 .

K ZHANG , Z ZHANG , Z LI , 等 . Joint face detection and alignment using multitask cascaded convolutional networks . IEEE Signal Processing Letters , 2016 . 23 ( 10 ): 1499 - 1503 .

陈希彤 , 卢涛 . 基于全局深度分离卷积残差网络的高效人脸识别算法 . 武汉工程大学学报 , 2019 . 41 ( 3 ): 276 - 282 . http://d.old.wanfangdata.com.cn/Periodical/whhgxyxb201903014 http://d.old.wanfangdata.com.cn/Periodical/whhgxyxb201903014 .

X T CHEN , T LU . An efficient face recognition algorithm based on global depth separation convolution residual network . Journal of Wuhan Institute of Technology , 2019 . 41 ( 3 ): 276 - 282 . http://d.old.wanfangdata.com.cn/Periodical/whhgxyxb201903014 http://d.old.wanfangdata.com.cn/Periodical/whhgxyxb201903014 .

杜振龙 , 沈海洋 , 宋国美 , 等 . 基于改进CycleGAN的图像风格迁移 . 光学精密工程 , 2019 . 27 ( 8 ): 1836 - 1844 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201908019 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201908019 .

ZH L DU , H Y SHEN , G M SONG , 等 . Image style migration based on improved CycleGAN . Opt. Precision Eng. , 2019 . 27 ( 8 ): 1836 - 1844 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201908019 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201908019 .

B CHARLES , L PIERRE , A M PIERRE . Exact dimensionality selection for Bayesian PCA . Scandinavian Journal of Statistics , 2020 . 47 ( 1 ): 196 - 211 .

S MARCO , E G CATHARINA , M G JOSE . Who learns better Bayesian network structures: Accuracy and speed of structure learning algorithms . International Journal of Approximate Reasoning , 2019 . 115 ( 1 ): 235 - 253 .

X CAO, D WIPF, F WEN, et al.. A practical transfer learning algorithm for face verification.[C] 2013 IEEE International Conference on Computer Vision , 2013: 3208-3215.

O R IGOR , T X IBAN , T W JONAS , A UULKE , 等 . A Deep Learning-based correction to EPID dosimetry for attenuation and scatter in the Unity MR-Linac system . Physica Medica , 2020 . 71 ( 2 ): 124 - 131 .

DENG J, GUO J, XUE N, et al.. Arcface: Additive angular margin loss for deep face recognition.[C] 2019 IEEE Conference on Computer Vision and Pattern Recognition. IEEE , 2019: 482-493.

张小荣 , 胡炳樑 , 潘志斌 , 等 . 基于张量表示的高光谱图像目标检测 . 光学精密工程 , 2019 . 27 ( 2 ): 488 - 498 . http://d.old.wanfangdata.com.cn/Thesis/D01335243 http://d.old.wanfangdata.com.cn/Thesis/D01335243 .

X R ZHANG , B Y HU , ZH B PAN , 等 . Target detection in hyperspectral images based on tensor representation . Opt. Precision Eng. , 2019 . 27 ( 2 ): 488 - 498 . http://d.old.wanfangdata.com.cn/Thesis/D01335243 http://d.old.wanfangdata.com.cn/Thesis/D01335243 .

Views

908

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Survey of target detection based on deep convolutional neural networks

Related Author

Li-li FAN

Huang-shui HU

Hao-yu ZHAO

Zhen WANG

Related Institution

College of Computer Science and Technology, Jilin University

School of Computer Science and Engineering, Changchun University of Technology

Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University

Editorial Department of Journal(Engineering and Technology Edition), Jilin University

School of Computer Science and Technology, Shandong University of Technology

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@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