Freshness determination of winter jujube based on improved Faster R-CNN

Authors

DAI Haotian, School of Computer Science, Hubei University of Technology, Wuhan, Hubei 430068, China
LIU Wenlian, School of Food Science and Engineering, South China University of Technology University, Guangzhou, Guangdong 510640, China
ZHU Meiyan, School of Food Science and Engineering, South China University of Technology University, Guangzhou, Guangdong 510640, China
ZHANG Ling, College of Biology and Food Engineering, Guangdong University of Petrochemical Technology, Maoming, Guangdong 525000, China
ZHU Liang, School of Food Science and Engineering, South China University of Technology University, Guangzhou, Guangdong 510640, ChinaFollow

Corresponding Author(s)

朱良（1975—），男，华南理工大学副教授，硕士生导师，博士。E-mail：zhuliang@scut.edu.cn

Abstract

[Objective] To propose a deep learning-based method for the freshness determination of winter jujube by dividing the fruit into five freshness stages, aiming to improve determination accuracy and reduce the influence of light reflection. [Methods] In this study, a freshness determination method is proposed for winter jujube by combining an efficient ResNet, an attention mechanism, and Faster R-CNN. First, ResNet is used for convolutional processing on the image to extract the global feature map. Next, key features are enhanced through a channel attention module, and multi-scale features are extracted using a feature pyramid network (FPN). Then, Faster R-CNN selects candidate regions from the features, followed by region of interest (ROI) pooling before inputting to fully connected layers. Therefore, the model performance is optimized through a multi-angle loss function. The model’s effectiveness is validated using physicochemical indicators such as hardness, conductivity, as well as vitamin C (VC) and polyphenol content. [Results] In freshness determination, the improved Faster R-CNN model achieves an accuracy of 98.60%. [Conclusion] The improved Faster R-CNN model outperforms existing methods in small-scale samples.

Publication Date

1-23-2026

First Page

93

Last Page

100

DOI

10.13652/j.spjx.1003.5788.2024.81175

Recommended Citation

Haotian, DAI; Wenlian, LIU; Meiyan, ZHU; Ling, ZHANG; and Liang, ZHU (2026) "Freshness determination of winter jujube based on improved Faster R-CNN," Food and Machinery: Vol. 42: Iss. 1, Article 13.
DOI: 10.13652/j.spjx.1003.5788.2024.81175
Available at: https://www.ifoodmm.cn/journal/vol42/iss1/13

References

[1] LU Y,BAO T,MO J L,et al.Research advances in bioactive components and health benefits of jujube (Ziziphus jujuba Mill.) fruit[J].Journal of Zhejiang University-Science B,2021,22(6):431-449.
[2] CAI W T,ZHUANG H N,WANG X Y,et al.Functional nutrients and jujube-based processed products in Ziziphus jujuba[J].Molecules,2024,29(14):3 437.
[3] HUA Y,XU X X,GUO S,et al.Wild jujube (Ziziphus jujuba var.spinosa ):a review of its phytonutrients,health benefits,metabolism,and applications [J].Journal of Agricultural and Food Chemistry,2022,70(26):7 871-7 886.
[4] 王铁伟,赵瑶,孙宇馨,等.基于数据平衡深度学习的不同成熟度冬枣识别 [J].农业机械学报,2020,51(S1):457-463,492.WANG T W,ZHAO Y,SUN Y X,et al.Recognition approach based on data-balanced Faster R-CNN for winter jujube with different levels of maturity [J].Transactions of the Chinese Society for Agricultural Machinery,2020,51(S1):457-463,492.
[5] 韩乃瑄,曹颖,刘晓敏,等.冬枣保鲜技术的研究进展 [J].食品工业科技,2022,43(21):414-421.HAN N X,CAO Y,LIU X M,et al.Research progress on preservation technology of Ziziphus jujuba Mill.cv.Dongzao [J].Science and Technology of Food Industry,2022,43(21):414-421.
[6] WU J M,WU C Y,GUO H Y,et al.Research on red jujubes recognition based on a convolutional neural network [J].Applied Sciences-Basel,2023,13(11):6 381.
[7] DOU J F,KOU X H,WU C E,et al.Recent advances and development of postharvest management research for fresh jujube fruit:a review [J].Scientia Horticulturae,2023,310:111769.
[8] BAN Z J,FANG C Y,LIU L L,et al.Detection of fundamental quality traits of winter jujube based on computer vision and deep learning [J].Agronomy-Basel,2023,13(8):2 095.
[9] MAHMOOD A,SINGH S K,TIWARI A K.Pre-trained deep learning-based classification of jujube fruits according to their maturity level [J].Neural Computing and Applications,2022,34(16):13 925-13 935.
[10] ZHANG J J,WANG W H,CHE Q L.Innovative research on intelligent recognition of winter jujube defects by applying convolutional neural networks [J].Electronics,2024,13(15):2 941.
[11] ZHENG Z Z,HU Y H,QIAO Y C,et al.Real-time detection of winter jujubes based on improved YOLOX-nano network [J].Remote Sensing,2022,14(19):4 833.
[12] LU Z H,ZHAO M F,LUO J,et al.Design of a winter-jujube grading robot based on machine vision [J].Computers and Electronics in Agriculture,2021,186:106170.
[13] ZHANG B,LIN X D,ZHANG X M,et al.Research on jujube storage and preservation system based on Internet of Things (IoT)[J].Scientific Reports,2024,14(1):19808.
[14] 周诗捷,王玉槐,沈思橙,等.基于改进型 Faster R-CNN 的仓储 环 境 物 体 识 别 技 术 研 究 [J].计 算 技 术 与 自 动 化,2024,43(2):187-191.ZHOU S J,WANG Y H,HEN S C,et al.Research on object recognition in warehouse environment based on improved Faster R-CNN [J].Computing Technology and Automation,2024,43(2):187-191.
[15] 黎 冠,李 志 伟,陈 浩,等.基 于 改 进 YOLOv 5s的 轻 量 化 安 全帽佩戴检测算法 [J].华北科技学院学报,2024,21(3):32-41.LI G,LI Z W,CHEN H,et al.Lightweight helmet wearing detection algorithm based on improved YOLOv 5s[J].Journal of North China Institute of Science and Technology,2024,21(3):32-41.
[16] 谭 鹤 群,李 玉 祥,朱 明,等.通 过 图 像 增 强 与 改 进 Faster-RCNN 网络的重叠鱼群尾数检测 [J].农业工程学报,2022,38(13):167-176.TAN H Q,LI Y X,ZHU M,et al.Detecting overlapping fish population using image enhancement and improved Faster-RCNN networks [J].Transactions of the Chinese Society of Agricultural Engineering,2022,38(13):167-176.
[17] SHAFIQ M,GU Z Q.Deep residual learning for image recognition:a survey [J].Applied Sciences-Basel,2022,12(18):8 972.
[18] WANG Q L,WU B G,ZHU P F,et al.ECA-Net:Efficient channel attention for deep convolutional neural networks [C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR ).Seattle,WA:IEEE,2020:11 531-11 539.
[19] HU J,SHEN L,SUN G.Squeeze-and-excitation networks [C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR ).Salt Lake City,UT:IEEE,2018:7 132-7 141.
[20] LIN T Y,DOLLÁR P,GIRSHICK R,et al.Feature pyramid networks for object detection [C]// 2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR ).Honolulu,HI:IEEE,2017:936-944.
[21] LI S L,ZHANG S J,XUE J X,et al.A fast neural network based on attention mechanisms for detecting field flat jujube[J].Agriculture-Basel,2022,12(5):717.
[22] GUO X H,GUO Y D,YU J T,et al.X-ray irradiation-nonthermal processing and preservation of fresh winter jujube (Zizyphus jujuba Mill.cv.Dalidongzao ) [J].Innovative Food Science & Emerging Technologies,2022,81:103151.
[23] NAVEED F,NAWAZ A,ALI S,et al.Xanthan gum coating delays ripening and softening of jujube fruit by reducing oxidative stress and suppressing cell wall polysaccharides disassembly [J].Postharvest Biology and Technology,2024,209:112689.
[24] WANG L M,ZHANG J,YUN X Y,et al.Effect of poly (L-lactic acid )/poly (ethylene glycol )-poly (L-lactic acid ) block copolymer blend film on preservation of Chinese winter jujube (Ziziphus jujuba Mill.cv.Dongzao ) [J].International Journal of Biological Macromolecules,2023,253:126216.
[25] YU Y Y,XU Y J,WEN J,et al.Prunus mume polyphenols maintains the quality and nutrient values of winter jujube (Zizyphus jujuba Mill.) fruits during storage [J].CYTA-Journal of Food,2021,19(1):552-559.
[26] MAHMOOD A,TIWARI A K,SINGH S K.Maturity grading of jujube for industrial applications harnessing deep learning[J].Engineering Computations,2024,41(5):1 171-1 184.