Please wait a minute...
Journal of Integrative Agriculture  2023, Vol. 22 Issue (1): 279-291    DOI: 10.1016/j.jia.2022.09.019
Food Science Advanced Online Publication | Current Issue | Archive | Adv Search |
Visual learning graph convolution for multi-grained orange quality grading
GUAN Zhi-bin1, ZHANG Yan-qi1, CHAI Xiu-juan1, CHAI Xin1, ZHANG Ning1, 2, ZHANG Jian-hua1, 3, SUN Tan2, 3

1 Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, P.R.China

2 Key Laboratory of Agricultural Big Data, Ministry of Agriculture and Rural Affairs, Beijing 100081, P.R.China

3 National Nanfan Research Institute (Sanya), Chinese Academy of Agricultural Sciences, Sanya 572024, P.R.China

Download:  PDF in ScienceDirect  
Export:  BibTeX | EndNote (RIS)      


Abstract  The quality of oranges is grounded on their appearance and diameter.  Appearance refers to the skin’s smoothness and surface cleanliness; diameter refers to the transverse diameter size.  They are visual attributes that visual perception technologies can automatically identify.  Nonetheless, the current orange quality assessment needs to address two issues: 1) There are no image datasets for orange quality grading; 2) It is challenging to effectively learn the fine-grained and distinct visual semantics of oranges from diverse angles.  This study collected 12 522 images from 2 087 oranges for multi-grained grading tasks.  In addition, it presented a visual learning graph convolution approach for multi-grained orange quality grading, including a backbone network and a graph convolutional network (GCN).  The backbone network’s object detection, data augmentation, and feature extraction can remove extraneous visual information.  GCN was utilized to learn the topological semantics of orange feature maps.  Finally, evaluation results proved that the recognition accuracy of diameter size, appearance, and fine-grained orange quality were 99.50, 97.27, and 97.99%, respectively, indicating that the proposed approach is superior to others.
Keywords:  GCN       multi-view       fine-grained       visual feature       appearance       diameter size  
Received: 01 May 2021   Accepted: 06 September 2022

This work was supported by the National Natural Science Foundation of China (31901240 and 31971792), the Science and Technology Innovation Program of the Chinese Academy of Agricultural Sciences (CAAS-ASTIP-2016-AII), and the Central Public-interest Scientific Institution Basal Research Funds, China (Y2022QC17 and CAAS-ZDRW202107).

About author:  Received 31 May, 2022 Accepted 6 September, 2022 GUAN Zhi-bin, E-mail:; Correspondence CHAI Xiu-juan, Tel: +86-10-82106286, E-mail:; SUN Tan, Tel: +86-10-82105162, E-mail:

Cite this article: 

GUAN Zhi-bin, ZHANG Yan-qi, CHAI Xiu-juan, CHAI Xin, ZHANG Ning, ZHANG Jian-hua, SUN Tan. 2023. Visual learning graph convolution for multi-grained orange quality grading. Journal of Integrative Agriculture, 22(1): 279-291.

Azarmdel H, Jahanbakhshi A, Mohtasebi S S, Muñoz A R. 2020. Evaluation of image processing technique as an expert system in mulberry fruit grading based on ripeness level using artificial neural networks (ANNs) and support vector machine (SVM). Postharvest Biology and Technology, 166, 111201.
Ding X, Zhang X, Ma N, Han J, Ding G, Sun J. 2021. RepVGG: Making VGG-style convnets great again. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Institute of Electrical and Electronics Engineers (IEEE), Nashville, TN, USA. pp. 13728–13737.
Fan S, Liang X, Huang W, Zhang V J, Pang Q, He X, Li L, Zhang C. 2022. Real-time defects detection for apple sorting using NIR cameras with pruning-based YOLOV4 network. Computers and Electronics in Agriculture, 193, 106715.
Gurubelli Y, Ramanathan M, Ponnusamy P. 2019. Fractional fuzzy 2DLDA approach for pomegranate fruit grade classification. Computers and Electronics in Agriculture, 162, 95–105.
Hamza R, Chtourou M. 2020. Design of fuzzy inference system for apple ripeness estimation using gradient method. IET Image Processing, 14, 561–569.
He K, Zhang X, Ren S, Sun J. 2016. Deep residual learning for image recognition. In: 2016 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). Institute of Electrical and Electronics Engineers (IEEE), Las Vegas, NV, USA. pp. 770–778.
Hu J, Shen L, Sun G. 2018. Squeeze-and-excitation networks. In: 2018 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). Institute of Electrical and Electronics Engineers (IEEE), Salt Lake City, UT, USA. pp. 7132–7141.
Kumari N, Dwivedi R K, Bhatt A K, Belwal R. 2022. Automated fruit grading using optimal feature selection and hybrid classification by self-adaptive chicken swarm optimization: Grading of mango. Neural Computing and Applications, 34, 1285–1306.
Lu S, Chen W, Zhang X, Karkee M. 2022. Canopy-attention-YOLOv4-based immature/mature apple fruit detection on dense-foliage tree architectures for early crop load estimation. Computers and Electronics in Agriculture, 193, 106696.
Mon T O, ZarAung N. 2020. Vision based volume estimation method for automatic mango grading system. Biosystems Engineering, 198, 338–349.
Ortega-Sánchez N, Rodríguez-Esparza E, Oliva D, Pérez-Cisneros M, Mohamed A W, Dhiman G, Hernández-Montelongo R. 2022. Identification of apple diseases in digital images by using the Gaining-sharing knowledge-based algorithm for multilevel thresholding. Soft Computing, 26, 2587–2623.
Peng Z, Huang W, Gu S, Xie L, Wang Y, Jiao J, Ye Q. 2021. Conformer: local features coupling global representations for visual recognition. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Institute of Electrical and Electronics Engineers (IEEE), Montreal, QC, Canada. pp. 357–366.
Rodriguez M, Pastor F, Ugarte W. 2021. Classification of fruit ripeness grades using a convolutional neural network and data augmentation. In: 2021 28th Conference of Open Innovations Association (FRUCT). Institute of Electrical and Electronics Engineers (IEEE), Moscow, Russia.
Simonyan K, Zisserman A. 2015. Very deep convolutional networks for large-scale image recognition. In: Proceedings of the 3rd International Conference on Learning Representations (ICLR). Conference Track Proceedings, San Diego, CA, USA.
Tan M, Le Q V. 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the 36th International Conference on Machine Learning (ICML). Long Beach, California, USA. pp. 6105–6114.
Tang Y, Gao S, Zhuang J, Hou C, He Y, Chu X, Miao A, Luo S. 2020. Apple bruise grading using piecewise nonlinear curve fitting for hyperspectral imaging data. IEEE Access, 8, 147494–147506.
Tian S, Wang S, Xu H. 2022. Early detection of freezing damage in oranges by online Vis/NIR transmission coupled with diameter correction method and deep 1D-CNN. Computers and Electronics in Agriculture, 193, 106638.
Tripathi M K, Maktedar D D. 2021. Optimized deep learning model for mango grading: Hybridizing lion plus firefly algorithm. IET Image Processing, 15, 1940–1956.
Vu T, Kang H, Yoo C D. 2021. SCNet: Training inference sample consistency for instance segmentation. In: Proceedings of the 35th AAAI (Association for the Advancement of Artificial Intelligence) Conference on Artificial Intelligence. AAAI Press 2021. pp. 2701–2709.
Wang J, Sun K, Cheng T, Jiang B, Deng C, Zhao Y, Liu D, Mu Y, Tan M, Wang X, Liu W, Xiao B. 2021. Deep high-resolution representation learning for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43, 3349–3364.
Xie S, Girshick R, Dollár P, Tu Z, He K. 2017. Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Institute of Electrical and Electronics Engineers (IEEE), Honolulu, HI, USA. pp. 5987–5995.
Yuan L, Chen Y, Wang T, Yu W, Shi Y, Jiang Z, Tay F E H, Feng J, Yan S. 2021. Tokens-to-token ViT: training vision transformers from scratch on imageNet. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Institute of Electrical and Electronics Engineers (IEEE), Montreal, QC, Canada. pp. 538–547.
Zhang Y E, Liu Y P. 2021. Identification of navel orange diseases and pests based on the fusion of densenet and self-attention mechanism. Computational Intelligence and Neuroscience, 2021, doi: 10.1155/2021/5436729.

[1] ZHOU Li-jun, HUANG Run-huan, LIU Ting-han, LIU Wei-chao, CHEN Yun-yi, LU Pei-feng, LUO Le, PAN Hui-tang, YU Chao, ZHANG Qi-xiang. Volatile metabolome and transcriptome reveal fragrance release rhythm and molecular mechanisms of Rosa yangii[J]. >Journal of Integrative Agriculture, 2023, 22(7): 2111-2125.
[2] ZHANG Yu, LUO Shu-wen, HOU Li-e, GU Tian-tian, ZHU Guo-qiang, Wanwipa VONGSANGNAK, XU Qi, CHEN Guo-hong. Weighted gene co-expression network analysis identifies potential regulators in response to Salmonella Enteritidis challenge in the reproductive tract of laying ducks[J]. >Journal of Integrative Agriculture, 2022, 21(8): 2384-2398.
[3] ZHAO Dong-sheng, LIU Jin-yu, DING Ai-qiu, ZHANG Tao, REN Xin-yu, ZHANG Lin, LI Qian-feng, FAN Xiao-lei, ZHANG Chang-quan, LIU Qiao-quan. Improving grain appearance of erect-panicle japonica rice cultivars by introgression of the null gs9 allele[J]. >Journal of Integrative Agriculture, 2021, 20(8): 2032-2042.
[4] FU Fang-fang, PENG Ying-shu, WANG Gui-bin, Yousry A. EL-KASSABY, CAO Fu-liang. Integrative analysis of the metabolome and transcriptome reveals seed germination mechanism in Punica granatum L.[J]. >Journal of Integrative Agriculture, 2021, 20(1): 132-146.
[5] WANG Qian-nan, HUANG Pan-pan, ZHOU Shan-yue. Functional characterization of the catalytic and bromodomain of FgGCN5 in development, DON production and virulence of Fusarium graminearum[J]. >Journal of Integrative Agriculture, 2020, 19(10): 2477-2487.
[6] WANG Jing-lu, ZHANG Ying, PAN Xiao-di, DU Jian-jun, MA Li-ming, GUO Xin-yu. Discovery of leaf region and time point related modules and genes in maize (Zea mays L.) leaves by Weighted Gene Co-expression Network analysis (WGCNA) of gene expression profiles of carbon metabolism[J]. >Journal of Integrative Agriculture, 2019, 18(2): 350-360.
[7] GAO Fang-yuan, ZENG Li-hua, QIU Ling, LU Xian-jun, REN Juan-sheng, WU Xian-ting, SU Xiangwen, GAO Yong-ming, REN Guang-jun. QTL mapping of grain appearance quality traits and grain weight using a recombinant inbred population in rice (Oryza sativa L.)[J]. >Journal of Integrative Agriculture, 2016, 15(8): 1693-1702.
No Suggested Reading articles found!