Influences of the feature extraction area of duck egg image for the identification accuracy on the unfertilized duck eggs on the hatching tray

被引:2
作者
Dong, Jun [1 ]
He, Ke [1 ]
Sun, Qinming [1 ]
Tang, Xiuying [1 ]
机构
[1] China Agr Univ, Coll Engn, 17 Qinghua East Rd, Beijing 100083, Peoples R China
关键词
DETECTING FERTILITY; MACHINE VISION; CLASSIFICATION; SYSTEM;
D O I
10.1111/jfpe.13813
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
However, feature parameter extraction region of duck egg image could affect the identification results of model and the speed of image processing. Therefore, the image skeleton-maximum inscribed circle algorithm and Hough gradient algorithm (2-1HT) were proposed to segment duck egg image feature paramer region. Support vector machine (SVM) and naive bayes (NB) models were established to evaluate accuracy of feature parameters extracted by different algorithms. The comparison shows that the SVM model based on feature parameters extracted by image skeleton maximum inscribed circle algorithm has the best discriminant performance, with the value of Q, SE, and SP being 98.81%, 98.44%, and 100.00%, respectively. Moreover, the process speed and prediction accuracy of image skeleton-maximum inscribed circle algorithm were much higher than that of Hough gradient algorithm. Practical Applications Therefore, optimizing the image feature parameter extraction algorithm of a single duck egg in grouped duck eggs was of great significance to improve the discrimination accuracy of the model and realize the automatic recognition of infertile duck eggs.
引用
收藏
页数:8
相关论文
共 19 条
[1]   Decision support system for fatty liver,disease using GIST descriptors extracted from ultrasound images [J].
Acharya, U. Rajendra ;
Fujita, Hamido ;
Bhat, Shreya ;
Raghavendra, U. ;
Gudigar, Anjan ;
Molinari, Filippo ;
Vijayananthan, Anushya ;
Ng, Kwan Hoong .
INFORMATION FUSION, 2016, 29 :32-39
[2]  
Caglayan A, 2013, LECT NOTES COMPUT SC, V8157, P161, DOI 10.1007/978-3-642-41184-7_17
[3]  
Chen X, 2011, AUTOMATION PANORAMA, V28, P86
[4]  
DAS K, 1992, T ASAE, V35, P1335, DOI 10.13031/2013.28738
[5]  
DAS K, 1992, T ASAE, V35, P2035, DOI 10.13031/2013.28832
[6]   Hatching eggs classification based on deep learning [J].
Geng, Lei ;
Yan, Tingyu ;
Xiao, Zhitao ;
Xi, Jiangtao ;
Li, Yuelong .
MULTIMEDIA TOOLS AND APPLICATIONS, 2018, 77 (17) :22071-22082
[7]   A Machine Vision System for Detecting Fertile Eggs in the Incubation Industry [J].
Hashemzadeh, Mahdi ;
Farajzadeh, Nacer .
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2016, 9 (05) :850-862
[8]   A Multi-Feature Fusion Based on Transfer Learning for Chicken Embryo Eggs Classification [J].
Huang, Lvwen ;
He, Along ;
Zhai, Mengqun ;
Wang, Yuxi ;
Bai, Ruige ;
Nie, Xiaolin .
SYMMETRY-BASEL, 2019, 11 (05)
[9]  
Jia Chao Jia Chao, 2011, Dongbei Nongye Daxue Xuebao, V42, P77
[10]   mRMR-based feature selection for classification of cotton foreign matter using hyperspectral imaging [J].
Jiang, Yu ;
Li, Changying .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2015, 119 :191-200