A Multi-Feature Fusion Based on Transfer Learning for Chicken Embryo Eggs Classification

被引:14
作者
Huang, Lvwen [1 ,2 ,3 ]
He, Along [1 ]
Zhai, Mengqun [4 ]
Wang, Yuxi [1 ]
Bai, Ruige [1 ]
Nie, Xiaolin [1 ]
机构
[1] NorthWest A&F Univ, Coll Informat Engn, Yangling 712100, Shaanxi, Peoples R China
[2] Minist Agr & Rural Affairs, Key Lab Agr Internet Things, Yangling 712100, Shaanxi, Peoples R China
[3] Shaanxi Key Lab Agr Informat Percept & Intelligen, Yangling 712100, Shaanxi, Peoples R China
[4] NorthWest A&F Univ, Coll Mech & Elect Engn, Yangling 712100, Shaanxi, Peoples R China
来源
SYMMETRY-BASEL | 2019年 / 11卷 / 05期
关键词
Transfer learning; deep feature; SPF; embryo; SURF; HOG; DCNN; agriculture; FERTILE EGGS; DEEP; IDENTIFICATION; MACHINE; VISION;
D O I
10.3390/sym11050606
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
The fertility detection of Specific Pathogen Free (SPF) chicken embryo eggs in vaccine preparation is a challenging task due to the high similarity among six kinds of hatching embryos (weak, hemolytic, crack, infected, infertile, and fertile). This paper firstly analyzes two classification difficulties of feature similarity with subtle variations on six kinds of five- to seven-day embryos, and proposes a novel multi-feature fusion based on Deep Convolutional Neural Network (DCNN) architecture in a small dataset. To avoid overfitting, data augmentation is employed to generate enough training images after the Region of Interest (ROI) of original images are cropped. Then, all the augmented ROI images are fed into pretrained AlexNet and GoogLeNet to learn the discriminative deep features by transfer learning, respectively. After the local features of Speeded Up Robust Feature (SURF) and Histogram of Oriented Gradient (HOG) are extracted, the multi-feature fusion with deep features and local features is implemented. Finally, the Support Vector Machine (SVM) is trained with the fused features. The verified experiments show that this proposed method achieves an average classification accuracy rate of 98.4%, and that the proposed transfer learning has superior generalization and better classification performance for small-scale agricultural image samples.
引用
收藏
页数:16
相关论文
共 33 条
[1]  
[Anonymous], P 3 INT C LEARNING R
[2]  
[Anonymous], OPTICS NATURAL RESOU
[3]  
[Anonymous], PROC CVPR IEEE
[4]  
[Anonymous], 2015, PROCIEEE CONFCOMPUT, DOI DOI 10.1109/CVPR.2015.7298594
[5]   Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification [J].
Arnal Barbedo, Jayme Garcia .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2018, 153 :46-53
[6]  
Baoming Shan, 2010, Proceedings Second International Workshop on Education Technology and Computer Science (ETCS 2010), P95, DOI 10.1109/ETCS.2010.540
[7]   Speeded-Up Robust Features (SURF) [J].
Bay, Herbert ;
Ess, Andreas ;
Tuytelaars, Tinne ;
Van Gool, Luc .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2008, 110 (03) :346-359
[8]   HOG-assisted deep feature learning for pedestrian gender recognition [J].
Cai, Lei ;
Zhu, Jianqing ;
Zeng, Huanqiang ;
Chen, Jing ;
Cai, Canhui ;
Ma, Kai-Kuang .
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2018, 355 (04) :1991-2008
[9]   Histograms of oriented gradients for human detection [J].
Dalal, N ;
Triggs, B .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :886-893
[10]   Weed detection in soybean crops using ConvNets [J].
Ferreira, Alessandro dos Santos ;
Freitas, Daniel Matte ;
da Silva, Gercina Goncalves ;
Pistori, Hemerson ;
Folhes, Marcelo Theophilo .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2017, 143 :314-324