Fly facial recognition based on deep convolutional neural network

被引:0
作者
Chen Y.-T. [1 ]
Chen W.-N. [1 ]
Zhang X.-Z. [1 ]
Li Y.-Y. [1 ]
Wang J.-S. [1 ]
机构
[1] College of information science and technology, Dalian Maritime University, Dalian
来源
Guangxue Jingmi Gongcheng/Optics and Precision Engineering | 2020年 / 28卷 / 07期
关键词
Deep convolutional neural network; Face recognition of fly; Inception-ResNet; Multi-task convolutional neural network; Reduction network;
D O I
10.37188/OPE.20202807.1558
中图分类号
学科分类号
摘要
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. © 2020, Science Press. All right reserved.
引用
收藏
页码:1558 / 1567
页数:9
相关论文
共 17 条
[1]  
LIU Y, ZHANG Q N, WANG F P, Et al., Classification algorithm of prospecting image based on color channel fusion feature, Modern Electronics Technique, 43, 4, pp. 67-72, (2020)
[2]  
HUANG H, LI ZH Y, SHI G Y, Et al., Multi-feature manifold discriminant embedding for hyperspectral image classification, Opt. Precision Eng, 27, 3, pp. 726-738, (2019)
[3]  
WU X Y, LI R, WU SH X., Behavior recognition algorithm based on CNN and bi-directional LSTM, Computer Engineering & Design, 41, 2, pp. 361-366, (2020)
[4]  
HUANG LAN, YANG, Et al., Deep learning versus Object-based Image Analysis (OBIA) in weed mapping of UAV imagery, International Journal of Remote Sensing, 41, 9, pp. 221-227, (2020)
[5]  
KANG B N, KIM Y, KIM D., Deep convolutional neural network using triplets of faces, deep ensemble, and score-level fusion for face recognition, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 76-84, (2017)
[6]  
HE K, ZHANG X, REN S, Et al., Deep residual learning for image recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, (2016)
[7]  
SHI W W, GONG Y H, TAO X Y, Et al., Fine-grained image classification using modified DCNNs Trained by cascaded softmax and generalized large-margin losses, IEEE transactions on neural networks and learning systems, 30, 3, pp. 683-694, (2019)
[8]  
WANG CH ZH, AN J SH, JIANG X J, Et al., Candidate region optimization algorithm based on convolutional neural network, Chinese Optics, 12, 6, pp. 1348-1361, (2019)
[9]  
ZHANG K, ZHANG Z, LI Z, Et al., Joint face detection and alignment using multitask cascaded convolutional networks, IEEE Signal Processing Letters, 23, 10, pp. 1499-1503, (2016)
[10]  
CHEN X T, LU T., An efficient face recognition algorithm based on global depth separation convolution residual network, Journal of Wuhan Institute of Technology, 41, 3, pp. 276-282, (2019)