Comprehensive quality detection method for tomatoes combining machine vision and spectral techniques

Authors

GUO Dechao, Guangzhou University of Chinese Medicine , Guangzhou , Guangdong 510006 , China
RAO Yuanli, Guangzhou University of Chinese Medicine , Guangzhou , Guangdong 510006 , China
ZHANG Hao, Guangzhou Center for Disease Control and Prevention , Guangzhou , Guangdong 510440 , ChinaFollow
LI Chunfeng, Guangdong University of Technology , Guangzhou , Guangdong 510006 , China
ZHAO Qiang, South China Agricultural University , Guangzhou , Guangdong 510642 , China

Corresponding Author(s)

张豪（1979—），女，广州市疾病预防控制中心教授，硕士。E-mail：gdcjnu@126.com

Abstract

［［Objective ］］ To realize rapid and accurate measurement of both internal and external quality of tomatoes,and improve the efficiency and quality of tomato grading.［［Methods ］］ Based on machine vision and spectroscopy technology,proposed a tomato comprehensive quality grading method which combined external and internal quality.By optimizing the YOLOv 8 model in four aspects (lightweight convolution,small object detection layer,CBAM attention mechanism,and loss function ),external defect detection was completed,and external quality grading was achieved by combining fruit shape index and tomato size.Complete tomato internal quality grading through preprocessing methods,feature extraction methods,and improved particle swarm optimization using least squares support vector machine.Analyzed the performance of the proposed grading detection method through experiments.［［Results ］］ The proposed method could achieve comprehensive quality testing of tomatoes with high accuracy and efficiency.The accuracy of external quality grading >93.00%,the accuracy of internal quality grading >86.00%,the accuracy of fusion quality grading >96.00%,and the average grading time <0.25 s.［［Conclusion ］］ Combining machine vision and spectral detection technology can achieve rapid,non -destructive,and accurate evaluation of tomato comprehensive quality.

Publication Date

2-18-2025

First Page

123

Last Page

130

DOI

10.13652/j.spjx.1003.5788.2024.60090

Recommended Citation

Dechao, GUO; Yuanli, RAO; Hao, ZHANG; Chunfeng, LI; and Qiang, ZHAO (2025) "Comprehensive quality detection method for tomatoes combining machine vision and spectral techniques," Food and Machinery: Vol. 40: Iss. 9, Article 18.
DOI: 10.13652/j.spjx.1003.5788.2024.60090
Available at: https://www.ifoodmm.cn/journal/vol40/iss9/18

References

[1] 孙潇鹏,刘灿灿,陆华忠,等.基于近红外透射光谱与机器视觉的蜜柚汁胞粒化分级检测 [J].食品科学技术学报,2021,39(1):37-45.SUN X P,LIU C C,LU H Z,et al.Detection of honey pomelo in different granulation levels based on near-infrared transmittance spectroscopy combined with machine vision [J].Journal of Food Science and Technology,2021,39(1):37-45.
[2] 刘美辰,薛河儒,刘江平,等.牛奶蛋白质含量的 SSA-SVM 高光 谱 预 测 模 型 [J].光 谱 学 与 光 谱 分 析,2022,42(5):1 601-1 606.LIU M C,XUE H R,LIU J P,et al.Hyperspectral analysis of milk protein content using SVM optimized by sparrow search algorithm [J].Spectroscopy and Spectral Analysis,2022,42(5):1 601-1 606.
[3] 殷坤,刘金明,张东杰,等.基于近红外光谱的大米蛋白质含量快速检测 [J].食品与机械,2021,37(5):82-88,175.YIN K,LIN J M,ZHANG D J,et al.Rapid detection of protein contentin rice based on near infrared spectroscopy [J].Food & Machinery,2021,37(5):82-88,175.
[4] 韩子馨,张丽丽,张博,等.新型无损检测技术在番茄品质检测中的研究与应用进展 [J].食品科学,2024,45(1):289-300.HAN Z X,ZHANG L L,ZHANG B,et al.Progress on research and application of new non-destructive testing techniques in tomato quality inspection [J].Food Science,2024,45(1):289-300.
[5] 孟庆龙,尚静,黄人帅,等.基于主成分回归的猕猴桃可溶性固形物无损检测 [J].包装工程,2021,42(3):19-24.MENG Q L,SHANG J,HUANG R S,et al.Nondestructive detection for soluble solids content of kiwifruits based on principal component regression [J].Packaging Engineering,2021,42(3):19-24.
[6] 许丽佳,陈铭,王玉超,等.高光谱成像的猕猴桃糖度无损检测方法 [J].光谱学与光谱分析,2021,41(7):2 188-2 195.XU L J,CHEN M,WANG Y C,et al.Study on non-destructive detection method of kiwifruit sugar content based on hyperspectral imaging technology [J].Spectroscopy and Spectral Analysis,2021,41(7):2 188-2 195.
[7] 高 升,徐 建 华,王 伟,等.光 纤 光 谱 技 术 结 合 SNV-CARS-GWO-SVR 模 型 的 樱 桃 番 茄 SSC 无 损 检 测 [J/OL ].现 代 食 品科 技.(2024 -04-30) [2024 -08-10].https://doi.org/10.13982 /j.mfst.1673 -9078.2024.8.0808.GAO S,XU J H,WANG W,et al.Nondestructive detection about SSC of cherry tomatoes based on fiber optic spectroscopy followed by SNV-CARS-GWO-SVR model [J/OL ].Modern Food Science and Technology.(2024 -04-30) [2024 -08-10].https://doi.org/10.13982 /j.mfst.1673 -9078.2024.8.0808.
[8] 孙宇朝,李守豪,夏秀波,等.利用改进 YOLOv 5s 模型检测番茄果实成熟度及外观品质 [J].园艺学报,2024,51(2):396-410.SUN Y C,LI S H,XIA X B,et al.Detecting tomato fruit ripeness and appearance quality based on improved YOLOv 5s[J].Acta Horticulturae Sinica,2024,51(2):396-410.
[9] 康明月,王成,孙鸿雁,等.基于改进的 WOA-LSSVM 樱桃番茄 内 部 品 质 检 测 方 法 研 究 [J].光 谱 学 与 光 谱 分 析,2023,43(11):3 541-3 550.KANG M Y,WANG C,SUN H Y,et al.Research on internal quality detection method of cherry tomatoes based on improved WOA-LSSVM [J].Spectroscopy and Spectral Analysis,2023,43(11):3 541-3 550.
[10] 崔天宇,卢中领,薛琳,等.基于近红外反射光谱的番茄糖分快 速 检 测 模 型 研 究 [J].光 谱 学 与 光 谱 分 析,2023,43(4):1 218-1 224.CUI T Y,LU Z L,XUE L,et al.Research on the rapid detection model of tomato sugar based on near-infrared reflectance spectroscopy [J].Spectroscopy and Spectral Analysis,2023,43(4):1 218-1 224.
[11] 李 慧 琴,宋 赵 铭,刘 存 祥,等.基 于 YOLOv 8n的 番 茄 果 实 检测模型改进 [J/OL ].河南农业大学学报.(2024 -05-13) [2024 -09-29].https://doi.org/10.16445 /j.cnki.1000 -2340.20240511.002.LI H Q,SONG Z M,LIU C X,et al.Improvement of tomato fruit detection model based on YOLOv 8n[J/OL ].Journal of Henan Agricultural University.(2024 -05-13) [2024 -09-29].https://doi.org/10.16445 /j.cnki.1000 -2340.20240511.002.
[12] 马冬菁,刘怡菲,王宇,等.丹东地区 4种软枣猕猴桃果实中多糖特性研究 [J].辽宁林业科技,2020 (1):11-13,45.MA D J,LIU Y F,WANG Y,et al.Study on the polysaccharide characteristics of four varieties of Actinidia arguta fruits in Dandong area [J].Liaoning Forestry Science and Technology,2020 (1):11-13,45.
[13] 孙兴盛,顾思彤,蒋海峰,等.软枣猕猴桃后熟过程中生理及品质变化规律 [J].包装工程,2021,42(5):45-54.SUN X S,GU S T,JIANG H F,et al.Physiology and quality change laws of Actinidia arguta during late ripening [J].Packaging Engineering,2021,42(5):45-54.
[14] 王立扬,张瑜,沈群,等.基于改进型 LeNet- 5的苹果自动分级方法 [J].中国农机化学报,2020,41(7):105-110.WANG L Y,ZHANG Y,SHEN Q,et al.Automatic detecting and grading method of apples based on improved LeNet- 5[J].Journal of Chinese Agricultural Mechanization,2020,41(7):105-110.
[15] 杨志锐,郑宏,郭中原,等.基于网中网卷积神经网络的红枣缺陷检测 [J].食品与机械,2020,36(2):140-145,181.YANG Z R,ZHENG H,GUO Z Y,et al.Detection of jujube defects based on the neural network with network convolution[J].Food & Machinery,2020,36(2):140-145,181.
[16] 沈海军,张汤磊,许振兴,等.基于 Fisher 判别分析对苹果新鲜度的识别研究 [J].食品工业科技,2023,44(4):361-368.SHEN H J,ZHANG T L,XU Z X,et al.Recognition of apple freshness based on fisher discriminant analysis [J].Science and Technology of Food Industry,2023,44(4):361-368.
[17] 刘 雪,沈 长 盈,吕 学 泽,等.基 于 改 进 MobileNetV 3-Large 的鸡 蛋 新 鲜 度 识 别 模 型 [J].农 业 工 程 学 报,2022,38(17):196-204.LIU X,SHEN C Y,LU X Z,et al.Recognizing egg freshness using an improved MobileNetV 3-Large [J].Journal of Agricultural Engineering,2022,38(17):196-204.
[18] 焦俊,王文周,侯金波,等.基于改进残差网络的黑毛猪肉新鲜度识别方法 [J].农业机械学报,2019,50(8):364-371.JIAO J,WANG W Z,HOU J B,et al.Freshness identification of iberico pork based on improved residual network [J].Journal of Agricultural Machinery,2019,50(8):364-371.
[19] 索婷,杨书林,林娜,等.小麦粉特性与生湿面品质的关系研究[J].食品与生物技术学报,2024,43(3):54-65.SUO T,YANG S L,LIN N,et al.Study on relationship between wheat flour characteristics and quality of fresh wet noodles [J].Journal of Food Science and Biotechnology,2024,43(3):54-65.
[20] 文韬,代兴勇,李浪,等.基于机器视觉与光谱融合的柑橘品质无损检测分级系统设计与试验 [J].江苏大学学报 (自然科学版 ),2024,45(1):38-45.WEN T,DAI X Y,LI L,et al.Design and experiment of non-destructive testing and grading system for citrus quality based on machine vision and spectral fusion [J].Journal of Jiangsu University (Natural Science Edition ),2024,45(1):38-45.