Research on moulded peanut recognition technology based on deep learning

Authors

WANG Weina, Henan College of Transportation, Zhengzhou, Henan 451460, ChinaFollow
XU Shiwei, Xi'an University of Architecture and Technology, Xi'an, Shaanxi 710054, China
DENG Qinbo, Shaanxi University of Science & Technology, Xi'an, Shaanxi 710021, China
LI Bo, Shaanxi Fengrun Intelligent Manufacturing Research Institute Co., Ltd., Xi'an, Shaanxi 712000, China

Abstract

Objective: To identify mouldy peanuts in a fast and non-destructive way and improve the identification efficiency. Methods: Collected hyperspectral peanut data using a spectrometer, identify moldy peanuts using deep learning technology, and established a Hypernet PRMF model, which was compared with Deeplab v3+, Segnet, Unet, and Hypernet as control models. Integrated the proposed peanut recognition index into hyperspectral images as data feature pre extraction. Simultaneously integrating the constructed multi feature fusion blocks into the control model to improve the recognition efficiency of moldy peanuts. Results: The average pixel accuracy of all models exceeded 87%. the Hypernet-PRMF model had the highest detection accuracy of 90.35%, while for the whole peanut dataset, Hypernet-PRMF had a low false recognition rate and could effectively identify all mouldy peanuts in the figure. Conclusion: The Hypernet-PRMF model built based on deep learning has high pixel accuracy and detection precision, which can effectively identify mouldy peanuts and provide a reference basis for the identification and detection of other mouldy food and other hyperspectral objects.

Publication Date

10-20-2023

First Page

136

Last Page

141

DOI

10.13652/j.spjx.1003.5788.2023.60081

Recommended Citation

Weina, WANG; Shiwei, XU; Qinbo, DENG; and Bo, LI (2023) "Research on moulded peanut recognition technology based on deep learning," Food and Machinery: Vol. 39: Iss. 8, Article 21.
DOI: 10.13652/j.spjx.1003.5788.2023.60081
Available at: https://www.ifoodmm.cn/journal/vol39/iss8/21

References

[1] 王锐, 王桂英, 吴文福, 等. 基于仿生智能算法的高水分玉米收购定等系统研究[J]. 粮油食品科技, 2023, 31（2）: 74-82. WANG R, WANG G Y, WU W F, et al. Research on high-moisture corn acquisition and leveling system based on bionic intelligence algorithm[J]. Science and Technology of Cereals, Oils and Foods, 2023, 31（2）: 74-82.
[2] 熊春晖, 佘永新, 焦逊, 等. 高光谱成像技术在农产品无损检测中的应用[J]. 粮油食品科技, 2023, 31（1）: 109-122. XIONG C H, SHE Y X, JIAO X, et al. Application ofhyperspectral imaging technology in nondestructive testing of agricultural products[J]. Science and Technology of Cereals, Oils and Foods, 2023, 31（1）: 109-122.
[3] 王粒. 基于高光谱图像的花生品种分类、霉变检测及蛋白质含量预测[D]. 雅安: 四川农业大学, 2022: 40-41. WANG L. Peanut variety classification, mildew detection and protein content prediction based on hyperspectral images[D]. Ya'an: Sichuan Agricultural University, 2022: 40-41.
[4] QI X T, JIANG J B, CUI X M, et al. Identification of fungi-contaminated peanuts using hyperspectral imaging technology and joint sparse representation model[J]. Journal of Food Science and Technology, 2019, 56（7）: 3 195-3 204.
[5] 李明泽. 基于多光谱图像技术的梅干菜杂质检测研究与系统开发[D]. 无锡: 江南大学, 2021: 36-37. LI M Z. Research and system development on the detection of impurities in dried plum vegetables based on multispectral image technology[D]. Wuxi: Jiangnan University, 2021: 36-37.
[6] 李薇, 王晓涵, 陈燕, 等. 食品非定向筛查样品前处理方法及材料的研究进展[J]. 化学教育（中英文）, 2023, 44（10）: 1-5. LI W, WANG X H, CHEN Y, et al. Research progress on pretreatment methods and materials of food non directional screening samples[J]. Chinese Journal of Chemical Education, 2023, 44（10）: 1-5.
[7] 白一睿, 方辉, 张泽. 基于YOLO神经网络模型的花生智能精选系统设计[J]. 机械, 2023, 50（2）: 1-6. BAI Y R, FANG H, ZHANG Z. Design of an intelligent peanut selection system based on YOLO neural network model[J]. Machinery, 2023, 50（2）: 1-6.
[8] 孙晓荣, 田密, 刘翠玲, 等. 太赫兹衰减全反射技术对板栗果仁霉变程度判别研究[J]. 食品安全质量检测学报, 2022, 13（14）: 4 527-4 533. SUN X R, TIAN M, LIU C L, et al. A study on the discrimination of chestnut kernel moldy degree using terahertz attenuated total reflection technology[J]. Journal of Food Safety & Quality, 2022, 13（14）: 4 527-4 533.
[9] 许文娟, 赵晗, 王洪涛, 等. 电子鼻在食品安全检测领域的研究进展[J]. 食品工业, 2022, 43（2）: 255-260. XU W J, ZHAO H, WANG H T, et al. Research progress of electronic nose in the field of food safety detection[J]. The Food Industry, 2022, 43（2）: 255-260.
[10] 成亚倩, 高志贤, 周焕英, 等. 食品中黄曲霉毒素比色生物检测技术研究进展[J]. 分析试验室, 2021, 40（8）: 966-976. CHENG Y Q, GAO Z X, ZHOU H Y, et al. Research progress of Aspergillus flavus colorimetric biological detection technology in food[J]. Chinese Journal of Analysis Laboratory, 2021, 40（8）: 966-976.
[11] 王林, 王宇栋, 朱宝, 等. 仓储片烟中优势霉菌的分离鉴定及其霉变挥发性代谢产物研究[J]. 河南农业科学, 2023, 52（3）: 101-108. WANG L, WANG Y D, ZHU B, et al. Isolation and identification of dominant molds in warehouse tobacco and study on moldy volatile metabolites[J]. Journal of Henan Agricultural Sciences, 2023, 52（3）: 101-108.
[12] 戴松松, 殷勇. 基于高光谱信息特征选择的玉米霉变程度Fisher鉴别方法[J]. 食品与机械, 2018, 34（3）: 68-72. DAI S S, YIN Y. Fisher identification method of corn mildew degree based on Feature selection of hyperspectral information[J]. Food & Machinery, 2018, 34（3）: 68-72.
[13] 徐彦, 李忠海, 付湘晋, 等. 近红外光谱技术在稻米品质快速检测中的应用[J]. 食品与机械, 2011, 27（1）: 158-161, 174. XU Y, LI Z H, FU X J, et al. Application of near-infrared spectroscopy technology in rapid detection of rice quality[J]. Food & Machinery, 2011, 27（1）: 158-161, 174.
[14] 曾瑜, 谌委菊, 全珂, 等. 基于脱氧核酶的食品安全快速检测方法研究进展[J]. 食品与机械, 2022, 38（6）: 205-212. ZENG Y, CHEN W J, QUAN K, et al. Research progress on rapid detection methods for food safety based on deoxyribonuclease[J]. Food & Machinery, 2022, 38（6）: 205-212.
[15] 廉飞宇, 杨静, 付麦霞, 等. 玉米中黄曲霉毒素B₁的太赫兹时域光谱检测与识别[J]. 中国粮油学报, 2014, 29（8）: 111-116, 123. LIAN F Y, YANG J, FU M X, et al. Terahertz time-domain spectroscopy analysis for aflatoxin B₁ solution[J]. Journal of the Chinese Cereals and Oils Association, 2014, 29（8）: 111-116, 123.
[16] 郭志明, 王郡艺, 宋烨, 等. 果蔬品质劣变传感检测与监测技术研究进展[J]. 智慧农业（中英文）, 2021, 3（4）: 14-28. GUO Z M, WANG J Y, SONG Y, et al. Research progress in sensor detection and monitoring technology for quality deterioration of fruits and vegetables[J]. Smart Agriculture, 2021, 3（4）: 14-28.
[17] 马佳佳, 王克强. 水果品质光学无损检测技术研究进展[J]. 食品工业科技, 2021, 42（23）: 427-437. MA J J, WANG K Q. Research progress in optical non-destructive testing technology for fruit quality[J]. Science and Technology of Food Industry, 2021, 42（23）: 427-437.
[18] 张雨鑫. 高光谱成像技术在饲料及原料霉变检测中的应用[J]. 黑龙江粮食, 2022（12）: 53-55. ZHANG Y X. Application of hyperspectral imaging technology in the detection of moldy feed and raw materials[J]. Heilongjiang Grain, 2022（12）: 53-55.
[19] 李兴鹏, 姜洪喆, 蒋雪松, 等. 木本粮油林果品质的近红外光谱及成像无损检测研究进展[J]. 食品与发酵工业, 2022, 48（2）: 302-308. LI X P, JIANG H Z, JIANG X S, et al. Research progress in near-infrared spectroscopy and imaging non-destructive testing of woody grain, oil, forest and fruitquality[J]. Food and Fermentation Industries, 2022, 48（2）: 302-308.