Establishment of Non-Destructive Discriminant Model for Eggs Freshness Grade Based on Fusion Technology of Image and Spectral Features of Hyperspectral

被引:0
作者
Liu C. [1 ]
Qin D. [1 ]
Sun X. [1 ]
Wu J. [1 ]
Yang Y. [1 ,2 ]
Hu H. [3 ]
Li J. [1 ]
Zan J. [1 ]
机构
[1] School of Artificial Intelligence, Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing
[2] Faculty of Information Technology, Beijing University of Technology, Beijing
[3] Institute of Digital Agriculture, Zhejiang Academy of Agricultural Sciences, Hangzhou
来源
Journal of Food Science and Technology (China) | 2022年 / 40卷 / 06期
关键词
egg freshness grade; fusion of image and spectral features; hyperspectral imaging technology; successive projections algorithm; support vector machine;
D O I
10.12301/spxb202200122
中图分类号
学科分类号
摘要
Egg freshness grade evaluation is an important technical indicator in process of egg quality inspection. Egg samples from different storage environment were prepared, the hyperspectral image information and spectral information of eggs were collected, and the image features and spectral features were extracted. The image features and spectral features were integrated with parallel integration method, and the features were extracted based on successive projections algorithm and gray-level co-occurrence matrix method. The support vector machine egg freshness discriminant model was built. The model was optimized by particle swarm optimization algorithm, the accuracy rate of training set reached up to 85%, and the accuracy rate of prediction set reached up to 76. 67% . In order to solve the occasional misjudgment of single model, the progressive features integration method was used, and the multi-model consensus strategy and deep residual network ResNet 50 analysis method were introduced. The multi-model consensus strategy based on successive projections algorithm-histogram of oriented gradients features extraction method was built, the accuracy rate of training set of the model increased to 89%, and the accuracy rate of prediction set increased to 88% . Meanwhile, the deep residual network ResNet 50 model based on successive projections algorithm-histogram of oriented gradients features extraction method was built, the accuracy rate of training set of the model increased to 89%, and the accuracy rate of prediction set increased to 86. 67% . The image features and spectral features integration modelling analysis indicated that both parallel integration method and progressive integration method had a certain identifiability for egg freshness grade discrimination, and the multi-model consensus strategy of progressive integration method showed better discrimination effect. © 2022 Beijing Technology and Business University, Department of Science and Technology. All rights reserved.
引用
收藏
页码:172 / 182
页数:10
相关论文
共 25 条
  • [1] SOLTANI M, OMID M., Detection of poultry egg freshness by dielectric spectroscopy and machine learning techniques, LWT-Food Science and Technology, 62, 2, pp. 1034-1042, (2015)
  • [2] SUN J, LIU B, MAO H P, Et al., Non-destructive identification of different egg varieties vased on dielectric properties, Food Science, 38, 6, pp. 282-286, (2017)
  • [3] PENG L, KANG T., Prediction of TVB-N content in eggs based on electronic nose, Food Control, 23, 1, pp. 177-183, (2012)
  • [4] DENG F F, WANG J, CHEN W., Et al., Fabrication of sensor array based on quartz crystal microbalance and its detection for egg shelf life, Transactions of the Chinese Society of Agricultural Engineering, 33, 20, pp. 292-299, (2017)
  • [5] WANG F, WEN Y X, TAN Z J, Et al., Nondestructive detecting cracks of preserved eggshell using polarization technology and cluster analysis, Transactions of the Chinese Society of Agricultural Engineering, 30, 9, pp. 249-255, (2014)
  • [6] LIANG D, LI P, LIANG D T, Et al., Integrated inspecting and grading system of the egg quality based on machine vision, Journal of Chinese Institute of Food Science and Technology, 20, 11, pp. 247-254, (2020)
  • [7] FU D D, WANG Q H, GAO S, Et al., Analysis of sovalbumin content of different varieties of eggs during storage and its nondestructive testing model by visible-near infrared spectroscopy, Chinese Journal of Analytical Chemistry, 48, 2, pp. 289-297, (2020)
  • [8] YANG X Y, DING J X, FANG M M, Et al., Nondestructive determination of eggs freshness by Vis/ NIR hyperspectral imaging technology, Food & Machinery, 33, 11, pp. 131-136, (2017)
  • [9] WANG Q H, ZHOU K, WU L L, Et al., Egg freshness detection based on hyperspectra, Spectroscopy and Spectral Analysis, 36, 8, pp. 2596-2600, (2016)
  • [10] Fresh egg grading: NY / T 1758—2009, (2009)