GMOPNet: A GAN-MLP two-stage network for optical properties measurement of kiwifruit and peaches with spatial frequency domain imaging.

Journal: Food chemistry
PMID: 39546990

Abstract

Spatial frequency domain imaging (SFDI) is an imaging technique using spatially modulated illumination for measurement of optical properties. Conventional SFDI methods require capturing at least six images, making it time-consuming. This study presents a Generative Adversarial Network-Multi-Layer Perceptron (GAN-MLP) two-stage network (GMOPNet) for extracting high-precision optical properties of kiwifruit and peaches from a single SFDI image, enabling real-time continuous wide-band SFDI. The GMOPNet we proposed leverages the GAN to predict diffuse reflectance, followed by the MLP with Monte Carlo prior knowledge to predict optical properties. Our method achieves mean absolute percentage errors (MAPE) of 5.91% for the absorption coefficient (μ) and 5.23% for the reduced scattering coefficient ( [Formula: see text] ), reducing acquisition and processing time significantly, with single inference taking 31.13 ms. The MAPE of the μ and the [Formula: see text] were 6.73% and 6.34% for kiwifruit and 5.80% and 6.65% for peaches, respectively.

Authors

  • Yuan Gao
    Engineering Research Center of EMR and Intelligent Expert System, Ministry of Education, Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases, College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou Zhejiang Province, China.
  • Zhizhong Sun
    College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, Zhejiang, China; The National Key Laboratory of Agricultural Equipment Technology, Beijing 100083, PR China; Key Laboratory of Intelligent Equipment and Robotics for Agriculture of Zhejiang Province, Science Technology Department of Zhejiang Province, China; College of Chemistry and Materials Engineering, Zhejiang A&F University, Hangzhou 311300, Zhejiang, China.
  • Dong Hu
    School of Medicine, Anhui University of Science and Technology, Huainan, PR China; Anhui Province Engineering Laboratory of Occupational Health and Safety, Anhui University of Science and Technology, Huainan, PR China; Key Laboratory of Industrial Dust Prevention and Control & Occupational Safety and Health of the Ministry of Education, Anhui University of Science and Technology, Huainan, PR China. Electronic address: austhudong@126.com.
  • Lijuan Xie
    School of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, PR China; The National Key Laboratory of Agricultural Equipment Technology, Hangzhou, Zhejiang 310058, PR China; Key Laboratory of on-Site Processing Equipment for Agricultural Products, Ministry of Agriculture and Rural Affairs, Hangzhou, Zhejiang 310058, PR China. Electronic address: ljxie@zju.edu.cn.
  • Yibin Ying
    College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou, Zhejiang, China.

Keywords

External Resources

Popular Topics
Recent Journals