Progress in Application of Machine Vision in Rice Seeds Recognition and Classification

doi:10.11924/j.issn.1000-6850.casb2024-0019

Abstract

Abstract:

The article first outlines two methods of image acquisition, namely, the capture of RGB images and spectral images. Subsequently, it explores image preprocessing techniques, including steps such as image denoising, enhancement, and segmentation. In terms of feature extraction, principal component analysis (PCA) and linear discriminant analysis (LDA) methods are employed to efficiently extract the color, texture, and shape features of rice seeds. Additionally, the article discusses the practical applications of machine learning and deep learning in processing spectral and RGB images of rice seeds, as well as the performance optimization and improvement methods of deep learning models in rice seed recognition and classification. Overall, machine vision technology demonstrates its efficiency and accuracy in the field of rice seed recognition. In the future, the development of a low-cost image acquisition platform and more lightweight rice seed recognition software can be anticipated, promoting rice seed data sharing and continuously exploring emerging deep learning techniques to further optimize the effectiveness of rice seed recognition.

Key words: classification of rice seeds, rice seed identification, machine learning, deep learning, image processing, feature extraction

LI Bianhao, ZHANG Guoliang, LI Pengcheng, ZHAO Hongliang, YAN Feiyu, HUANG Zhiwei, NIU Yuan, QI Bo, ZHANG Linqing, FAN Song. Progress in Application of Machine Vision in Rice Seeds Recognition and Classification[J]. Chinese Agricultural Science Bulletin, 2024, 40(31): 152-158.

Figures/Tables 3

References 54

[1]	国家统计局. 中国统计年鉴[M]. 北京: 中国统计出版社,2022:378.
[2]	田容才, 卢俊玮. 光谱技术在水稻品种鉴别中的应用[J]. 粮食科技与经济, 2019, 44(7):73-76.
[3]	董雁凯, 王玉超, 李博梾, 等. 基于改进YOLO v5的黄瓜霜霉病分级方法[J]. 江苏农业科学, 2023, 51(22):213-220.
[4]	贾诗音. 基于Android的稻米品种的识别系统设计与实现[D]. 武汉: 武汉轻工大学, 2020.
[5]	TSENG H H, YANG M D, SAMINATHAN R, et al. Rice seedling detection in UAV images using transfer learning and machine learning[J]. Remote sensing, 2022, 14(12):2837.
[6]	SEBE N. Machine learning in computer vision[M]. Germany: Applications of Machine Learning and Artificial Intelligence in Education,2022:48-72.
[7]	陈孟燕, 王敏娟, 宋青峰, 等. 基于ECA-FV-CNN的水稻单籽粒质量分级方法[J]. 农业机械学报, 2023, 54(S2):235-243.
[8]	VOS K, PENG Z, JENKINS C, et al. Vibration-based anomaly detection using LSTM/SVM approaches[J]. Mechanical systems and signal processing, 2022,169:108752.
[9]	HUANG F L. Alternatives to logistic regression models in experimental studies[J]. The journal of experimental education, 2022, 90(1):213-228.
[10]	HE S, WU J, WANG D, et al. Predictive modeling of groundwater nitrate pollution and evaluating its main impact factors using random forest[J]. Chemosphere, 2022,290:133388.
[11]	史岩. 从统计学习理论到应用领域与模型拓展:KNN综合探究[J]. 企业科技与发展, 2023(10):27-30.
[12]	冯新妍, 贾昕, 黄金泽, 等. ANN-BiLSTM模型在温带荒漠灌丛碳通量数据缺失值插补中的应用[J]. 北京林业大学学报, 2023, 45(9):62-72.
[13]	LIAO G, HE P, GAO X, et al. Land use optimization of rural production-living-ecological space at different scales based on the BP-ANN and CLUE-S models[J]. Ecological indicators, 2022,137:108710.
[14]	HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural computation, 2006, 18(7):1527-1554. doi: 10.1162/neco.2006.18.7.1527 pmid: 16764513
[15]	FAWAZ H I, LUCAS B, FORESTIER G, et al. Inceptiontime: Finding alexnet for time series classification[J]. Data mining and knowledge discovery, 2020, 34(6):1936-1962.
[16]	KAUR G, SINHA R, TIWARI P K, et al. Face mask recognition system using CNN model[J]. Neuroscience informatics, 2022, 2(3):100035.
[17]	AHAD M T, LI Y, SONG B, et al. Comparison of CNN-based deep learning architectures for rice diseases classification[J]. Artificial intelligence in agriculture, 2023,9:22-35.
[18]	ZHAO Y, ZHANG X, FENG W, et al. Deep learning classification by ResNet-18 based on the real spectral dataset from multispectral remote sensing images[J]. Remote sensing, 2022, 14(19):4883.
[19]	BATCHULUUN G, NAM S H, PARK K R. Deep learning-based plant-image classification using a small training dataset[J]. Mathematics, 2022, 10(17):3091.
[20]	陈进, 张帅, 李耀明, 等. 联合收获机水稻破碎籽粒及杂质在线识别方法[J]. 中国农机化学报, 2021, 42(6):2095-5553.
[21]	MADHAVI B G K, BASAK J K, PAUDEL B, et al. Prediction of strawberry leaf color using RGB mean values based on soil physicochemical parameters using machine learning models[J]. Agronomy, 2022, 12(5):981.
[22]	KUO T Y, CHUNG C L, CHEN S Y, et al. Identifying rice grains using image analysis and sparse-representation-based classification[J]. Computers and electronics in agriculture, 2016,127:716-725.
[23]	ANAMI B S, MALVADE N N, PALAIAH S. Automated recognition and classification of adulteration levels from bulk paddy grain samples[J]. Information processing in agriculture, 2019, 6(1):47-60.
[24]	周红标, 朱亚文, 刘晓洋, 等. 基于机器视觉的水稻印刷播种机成种率检测[J]. 中国农机化学报, 2023, 44(7):194-199.
[25]	王敬湧, 张明珍, 凌华荣, 等. 干旱胁迫下玉米叶片叶绿素含量与含水量高光谱成像反演方法[J]. 智慧农业, 2023, 5(3):142-153.
[26]	王小龙, 邓继忠, 黄华盛, 等. 基于高光谱数据的棉田虫害鉴别研究[J]. 华南农业大学学报, 2019, 40(3):97-103.
[27]	张嘉洪, 何林, 胡新军, 等. 基于高光谱成像技术的高粱农药残留种类检测研究[J]. 食品安全质量检测学报, 2023, 14(20):209-217.
[28]	李斌, 苏成涛, 殷海, 等. 高光谱成像技术结合机器学习的稻米霉变检测[J]. 光谱学与光谱分析, 2023, 43(8):2391-2396.
[29]	夏晨真, 姜艳艳, 张星宇, 等. 基于无人机高光谱影像的黑土区玉米农田土壤有机质估算[J]. 光谱学与光谱分析, 2023, 43(8):2617-2626.
[30]	杨欢, 罗斌, 张晗, 等. 基于高光谱成像技术和IRIV算法的玉米种子品种纯度识别[J]. 江苏大学学报, 2023, 44(2):159-165
[31]	SENDIN K, MANLEY M, BAETEN V, et al. Near infrared hyperspectral imaging for white maize classification according to grading regulations[J]. Food analytical methods, 2019,12:1612-1624.
[32]	VU H, TACHTATZIS C, MURRAY P, et al. Spatial and spectral features utilization on a hyperspectral imaging system for rice seed varietal purity inspection[A]. // In: IEEE RIVF Editorial Board[C]. 2016:169-174.
[33]	叶文超, 罗水洋, 李金豪, 等. 近红外光谱与图像融合的杂交水稻种子分类方法研究[J]. 光谱学与光谱分析, 2023, 43(9):2935-2941.
[34]	JIN B, QI H, JIA L, et al. Determination of viability and vigor of naturally-aged rice seeds using hyperspectral imaging with machine learning[J]. Infrared physics & technology, 2022,122:104097.
[35]	DONG W, MA X, LI H, et al. Detection of performance of hybrid rice pot-tray sowing utilizing machine vision and machine learning approach[J]. Sensors, 2019, 19(23):5332.
[36]	KIRATIRATANAPRUK K, TEMNIRANRAT P, SINTHUPINYO W, et al. Development of paddy rice seed classification process using machine learning techniques for automatic grading machine[J]. Journal of sensors,2020:1-14.
[37]	杨红云, 黄琼, 孙爱珍, 等. 基于卷积神经网络和支持向量机的水稻种子图像分类识别[J]. 中国粮油学报, 2021, 36(12):144-150.
[38]	黄琼, 杨红云, 万颖. 基于特征数据的水稻种子分类识别方法[J]. 江苏农业学报, 2021, 37(1):8-15.
[39]	阮殿旭. 基于机器视觉的粮食稻米检测系统设计[J]. 南方农机, 2021, 52(23):24-26.
[40]	MEDEIROS A D, SILVA L J, RIBEIRO J P O, et al. Machine learning for seed quality classification: An advanced approach using merger data from FT-NIR spectroscopy and X-ray imaging[J]. Sensors, 2020, 20(15):4319.
[41]	WAKHOLI C, KANDPAL L M, LEE H, et al. Rapid assessment of corn seed viability using short wave infrared line-scan hyperspectral imaging and chemometrics[J]. Sensors and actuators B: Chemical, 2018,255:498-507.
[42]	ANSARI N, RATRI S S, JAHAN A, et al. Inspection of paddy seed varietal purity using machine vision and multivariate analysis[J]. Journal of agriculture and food research, 2021,3:100-109.
[43]	FABIYI S D, VU H, TACHTATZIS C, et al. Comparative study of PCA and LDA for rice seeds quality inspection[A].// In: IEEE AFRICON Editorial Board[C]. 2019:1-4.
[44]	SINGH K R, CHAUDHURY S. A cascade network for the classification of rice grain based on single rice kernel[J]. Complex & intelligent systems, 2020, 6(1):321-334.
[45]	RUSLAN R, KHAIRUNNIZA-BEJO S, JAHARI M, et al. Weedy rice classification using image processing and a machine learning approach[J]. Agriculture, 2022, 12(5):645.
[46]	SAXENA P, PRIYA K, GOEL S, et al. Rice varieties classification using machine learning algorithms[J]. Journal of pharmaceutical negative results, 2022:3762-3772.
[47]	李秀昊, 马旭, 李泽华, 等. 基于特征融合和SVM的稻谷品种识别[J]. 中国农机化学报, 2019, 40(7):97-102. doi: 10.13733/j.jcam.issn.2095-5553.2019.07.18
[48]	KOKLU M, CINAR I, TASPINAR Y S. Classification of rice varieties with deep learning methods[J]. Computers and electronics in agriculture, 2021,187:106285.
[49]	LIN P, LI X L, CHEN Y M, et al. A deep convolutional neural network architecture for boosting image discrimination accuracy of rice species[J]. Food and bioprocess technology, 2018,11:765-773.
[50]	GILANIE G, NASIR N, BAJWA U I, et al. RiceNet: Convolutional neural networks-based model to classify Pakistani grown rice seed types[J]. Multimedia systems, 2021, 27(5):867-875.
[51]	IZQUIERDO M, LASTRA-MEJÍAS M, GONZÁLEZ-FLORES E, et al. Visible imaging to convolutionally discern and authenticate varieties of rice and their derived flours[J]. Food control, 2020,110:106971.
[52]	JIN B C, ZHANG C, JIA L Q, et al. Identification of rice seed varieties based on near-infrared hyperspectral imaging technology combined with deep learning[J]. ACS Omega, 2022, 7(6):4735-4749. doi: 10.1021/acsomega.1c04102 pmid: 35187294
[53]	接昭玮, 周世瑞, 王继芬, 等. 基于多特征算法选择的太赫兹时域光谱用于水稻种子掺假研究[J]. 分析测试学报, 2023, 42(2):158-165.
[54]	邱振军, 陈军, 赵玉英, 等. 高光谱成像结合卷积神经网络对单粒水稻种子品种进行鉴定[J]. 应用科学, 2018, 8(2):212-215.

编号	第一作者	发表年份	数据集/张	图片类型	网络框架	准确率/%
1	Temniranrat K	2020	3500	RGB	InceptionResNetV2	95.15
2	Koklu M	2021	75000	RGB	VGG16	100
3	Lin P	2018	5554	RGB	DCNN	92.1
4	Gilanie G	2021	1000	RGB	RiceNet	99
5	叶文超	2023	2500	光谱图像	2D-CNN	98
6	邱振军	2018	3000	光谱图像	CNN	90

编号	第一作者	发表年份	数据集/张	图片类型	网络框架	准确率/%
1	Temniranrat K	2020	3500	RGB	InceptionResNetV2	95.15
2	Koklu M	2021	75000	RGB	VGG16	100
3	Lin P	2018	5554	RGB	DCNN	92.1
4	Gilanie G	2021	1000	RGB	RiceNet	99
5	叶文超	2023	2500	光谱图像	2D-CNN	98
6	邱振军	2018	3000	光谱图像	CNN	90