An Automatic Light Stress Grading Architecture Based on Feature Optimization and Convolutional Neural Network

Xia Hao, Man Zhang, Tianru Zhou, Xuchao Guo, Federico Tomasetto, Yuxin Tong and Minjuan Wang
Additional contact information
Xia Hao: College of Information Science and Engineering, Shandong Agricultural University, Tai’an 271000, China
Man Zhang: Key Laboratory of Modern Precision Agriculture System Integration Research, Ministry of Education, China Agricultural University, Beijing 100083, China
Tianru Zhou: College of Animal Science and Veterinary Medicine, Shandong Agricultural University, Tai’an 271000, China
Xuchao Guo: College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China
Federico Tomasetto: AgResearch Limited, Christchurch 8140, New Zealand
Yuxin Tong: Institute of Environment and Sustainable Development in Agriculture, Chinese Academy of Agricultural Sciences, Beijing 100089, China
Minjuan Wang: Key Laboratory of Modern Precision Agriculture System Integration Research, Ministry of Education, China Agricultural University, Beijing 100083, China

Agriculture, 2021, vol. 11, issue 11, 1-17

Abstract: The identification of light stress is crucial for light control in plant factories. Image-based lighting classification of leafy vegetables has exhibited remarkable performance with high convenience and economy. Convolutional Neural Network (CNN) has been widely used for crop image analysis because of its architecture, high accuracy and efficiency. Among them, large intra-class differences and small inter-class differences are important factors affecting crop identification and a critical challenge for fine-grained classification tasks based on CNN. To address this problem, we took the Lettuce ( Lactuca sativa L.) widely grown in plant factories as the research object and constructed a leaf image set containing four stress levels. Then a light stress grading model combined with classic pre-trained CNN and Triplet loss function is constructed, which is named Tr-CNN. The model uses the Triplet loss function to constrain the distance of images in the feature space, which can reduce the Euclidean distance of the samples from the same class and increase the heterogeneous Euclidean distance. Multiple sets of experimental results indicate that the model proposed in this paper (Tr-CNN) has obvious advantages in light stress grading dataset and generalized dataset.

Keywords: light stress grading; fine-grained visual classification; inter-class variance; intra-class variance; feature mapping (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/11/11/1126/pdf (application/pdf)
https://www.mdpi.com/2077-0472/11/11/1126/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:11:y:2021:i:11:p:1126-:d:676449

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().