基于机器视觉的烤烟鲜烟成熟度判别模型优选

doi:10.13733/j.jcam.issn.2095-5553.2023.08.016

摘要/Abstract

摘要： 为解决目前靠人为主观经验判别鲜烟成熟度并不准确的问题，对不同成熟度鲜烟叶进行图像处理、特征提取，并建立鲜烟叶成熟度判别模型，以实现鲜烟成熟度的智能判别。通过采集云烟87品种不同成熟度上部烟叶图像的10种颜色特征和纹理特征，分别进行变量聚类分析以及相关性分析，筛选出每类特征与成熟度相关性最强的1个特征组成特征子集，利用基于遗传算法的支持向量机(GA-SVM)、基于粒子群算法的反向传播(PSO-BP)神经网络和极限学习机(ELM)进行鲜烟成熟度的判别研究。结果表明：以优选后5个烟叶图像特征作为模型输入时，所建立的GA-SVM、PSO-BP、ELM模型的判别准确率分别为92.00%、90.00%、84.00%。证明利用机器视觉技术判别鲜烟成熟度是可行的，为之后烟叶智能采收提供理论基础和技术支持。

关键词: 烤烟, 鲜烟成熟度, 机器视觉, 图像特征, 判别模型

Abstract: In order to solve the problem of inaccurate judgment of fresh tobacco maturity based on subjective experience, image processing and feature extraction were carried out on fresh tobacco leaf with different maturity, and a fresh tobacco leaf maturity judgment model was established to realize intelligent judgment of fresh tobacco maturity. By collecting 10 color features and texture features of upper leaf images of Yunyan 87 varieties with different maturity, variable cluster analysis and correlation analysis were carried out respectively, and the one feature with the strongest correlation between each type of feature and maturity was selected to form a feature subset. In this paper, support vector machine based on genetic algorithm (GA-SVM), Back propagation neural network based on particle swarm algorithm (PSO-BP) and Extreme learning Machine (ELM) were used to identify the maturity of fresh tobacco. The results showed that the optimal five tobacco leaf image features were used as model inputs, the discrimination accuracy of the established GA-SVM、PSO-BP、ELM model was 92.00%、90.00%、84.00%. It is proved that it is feasible to discriminate the maturity of fresh tobacco by using machine vision technology, which provides theoretical basis and technical support for intelligent tobacco leaf harvesting.

Key words: fluecured tobacco, maturity of fresh tobacco, machine vision, image feature, discrimination model

中图分类号:

TP371.41：S2

刘浩, 孟令峰, 王松峰, 刘自畅, 杜海娜, 孙福山. 基于机器视觉的烤烟鲜烟成熟度判别模型优选[J]. 中国农机化学报, 2023, 44(8): 118-124.

Liu Hao, , Meng Lingfeng, Wang Songfeng, Liu Zichang, Du Haina, , Sun Fushan. Optimization of fresh fluecured tobacco maturity discrimination model based on machine vision[J]. Journal of Chinese Agricultural Mechanization, 2023, 44(8): 118-124.

参考文献

［1］　刘雅娴. 不同营养条件下的鲜烟素质与烘烤工艺［D］. 北京:中国农业科学院, 2020.
Liu Yaxian. Study on the fresh tobacco leaves quality and curing technology under different nutritional conditions ［D］. Beijing: Chinese Academy of Agricultural Sciences, 2020.
［2］　Chen Y, Bin J, Zou C, et al. Discrimination of fresh tobacco leaves with different maturity levels by nearinfrared (NIR) spectroscopy and deep learning ［J］. Journal of Analytical Methods in Chemistry, 2021, 2021.
［3］　高宪辉, 王松峰, 孙帅帅, 等. 鲜烟成熟度颜色值指标及其判别函数研究［J］. 中国烟草学报, 2017, 23(1): 77-85.
Gao Xianhui, Wang Songfeng, Sun Shuaishuai, et al. Study on color space databased discriminating functions of fresh tobacco at various mature stages ［J］. Acta Tabacaria Sinica, 2017, 23(1): 77-85.
［4］　刘辉, 祖庆学, 王松峰, 等. 不同成熟度对鲜烟素质和烤后烟叶质量的影响［J］. 中国烟草科学, 2020, 41(2): 66-71, 78.
Liu Hui, Zu Qingxue, Wang Songfeng, et al. Effect of different maturity on the quality features of fresh and cured tobacco ［J］. Chinese Tobacco Science, 2020, 41(2): 66-71, 78.
［5］　Kim W S, Lee D H, Kim Y J. Machine visionbased automatic disease symptom detection of onion downy mildew ［J］. Computers and Electronics in Agriculture, 2020, 168: 105099.
［6］　Hasan M J, Mahbub S, Alom M S, et al. Rice disease identification and classification by integrating support vector machine with deep convolutional neural network ［C］. 2019 1st international Conference on Advances in Science, Engineering and Robotics Technology (ICASERT). IEEE, 2019: 1-6.
［7］　李东洋, 谢琳. 基于计算机视觉的农业自动化技术研究［J］.农村实用技术, 2020(12): 19-20.
［8］　李颀, 王康, 强华, 等. 基于颜色和纹理特征的异常玉米种穗分类识别方法［J］. 江苏农业学报, 2020, 36(1): 24-31.
Li Qi, Wang Kang, Qiang Hua, et al. Classification and recognition method of abnormal corn ears based on color and texture features ［J］. Jiangsu Journal of Agricultural Sciences, 2020, 36(1): 24-31.
［9］　Bhargava A, Bansal A. Quality evaluation of Mono & biColored Apples with computer vision and multispectral imaging ［J］. Multimedia Tools and Applications, 2020, 79: 7857-7874.
［10］　刘翠翠, 杨涛, 马京晶, 等. 基于PCA-SVM的麦冬叶部病害识别系统［J］. 中国农机化学报, 2019, 40(8): 132-136.
Liu Cuicui, Yang Tao, Ma Jingjing, et al. Identification system for leaf diseases of ophiopogon japonicus based on PCA-SVM ［J］. Journal of Chinese Agricultural Mechanization, 2019, 40(8): 132-136.
［11］　牛晓伟. 基于机器视觉的番茄病害识别系统的研究［D］. 兰州: 兰州理工大学, 2021.
Niu Xiaowei. Research on tomato disease recognition system based on machine vision ［D］. Lanzhou: Lanzhou University of Technology, 2021.
［12］　彭明霞, 夏俊芳, 彭辉. 融合FPN的Faster R-CNN复杂背景下棉田杂草高效识别方法［J］. 农业工程学报, 2019, 35(20): 202-209.
Peng Mingxia, Xia Junfang, Peng Hui. Efficient recognition of cotton and weed in field based on Faster R-CNN by integrating FPN ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(20): 202-209.
［13］　赵立新, 侯发东, 吕正超, 等. 基于迁移学习的棉花叶部病虫害图像识别［J］. 农业工程学报, 2020, 36(7): 184-191.
Zhao Lixin, Hou Fadong, Lü Zhengchao, et al. Image recognition of cotton leaf diseases and pests based on transfer learning ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(7); 184-191.
［14］　李辉, 罗敏, 岳佳欣. 基于计算机视觉技术的水稻病害图像识别研究进展［J］. 湖北农业科学, 2022, 61(4): 9-15.
Li Hui, Luo min, Yue Jiaxin. Research progress of recognition of rice disease images based on computer vision technology ［J］. Hubei Agricultural Sciences, 2022, 61(4): 9-15.
［15］　付豪, 万鹏, 施家伟, 等. 基于机器视觉的玉米幼苗叶面积检测装置设计及试验［J］. 华中农业大学学报, 2020, 39(1): 161-170.
Fu Hao, Wan Peng, Shi Jiawei, et al. Design and test of nondestructive detecting device for corn seedling leaf area based on machine vision ［J］. Journal of Huazhong Agricultural University, 2020, 39(1): 161-170.
［16］　彭要奇, 肖颖欣, 郑永军, 等. 无人机光谱成像技术在大田中的应用研究进展［J］. 光谱学与光谱分析, 2020, 40(5): 1356-1361.
Peng Yaoqi, Xiao Yingxin, Zheng Yongjun, et al. Research progress in the application of UAV spectral imaging technology in field ［J］. Spectroscopy and Spectral Analysi, 2020, 40(5): 1356-1361.
［17］　史龙飞, 宋朝鹏, 贺帆, 等. 基于机器视觉技术的烤烟鲜烟叶成熟度检测［J］. 湖南农业大学学报(自然科学版), 2012, 38(4): 446-450.
Shi Longfei, Song Chaopeng, He Fan, et al. Determination of the maturity grades of fresh leaves for Fluecured tobacco ［J］. Journal of Hunan Agricultural University (Natural Sciences), 2012, 38(4): 446-450.
［18］　谢滨瑶, 祝诗平, 黄华. 基于BPNN和SVM的烟叶成熟度鉴别模型［J］. 中国烟草学报, 2019, 25(1): 45-50.
Xie Binyao, Zhu Shiping, Huang Hua. Model for identification of tobacco leaf maturity based on BPNN and SVM ［J］. Acta Tabacaria Sinica, 2019, 25(1): 45-50.
［19］　贾炳文. 基于机器视觉与深度学习的烟叶定级研究［D］. 昆明: 昆明理工大学, 2019.
Jia Bingwen. Based on machine vision and deep learning for the research of tobacco leaf grading ［D］. Kunming: Kunming University of Science and Technology, 2019.
［20］　郭朵朵. 基于机器视觉的烟草烘烤品质检测及控制系统的设计［D］. 咸阳: 西北农林科技大学, 2017.
Guo Duoduo. Detection of tobacco baking quality and design of control system based on machine vision ［D］. Xianyang: Northwest A & F University, 2017.
［21］　王士鑫. 基于卷积神经网络(CNN)的烤烟烟叶质量分级研究［D］. 昆明: 云南师范大学, 2020.
Wang Shixin. Quality classification of fluecured tobacco leaf based on Convolutional Neural Network (CNN) ［D］. Kunming: Yunnan Normal University, 2020.
［22］　许自成, 赵瑞蕊, 王龙宪, 等. 烟叶成熟度的研究进展［J］. 东北农业大学学报, 2014.
Xu Zicheng, Zhao Ruirui, Wang Longxian, et al. Research advance of maturity of fluecured tobacco leaves ［J］. Journal of Northeast Agricultural University,2014.
［23］　杨倩, 高晓阳, 武季玲, 等. 基于颜色和纹理特征的大麦主要病害识别研究［J］. 中国农业大学学报, 2013, 18(5): 129-135.
Yang Qian, Gao Xiaoyang, Wu Jiling, et al. Research on the identification of major barley diseases based on color and texture features ［J］. Journal of China Agricultural University, 2013, 18(5): 129-135.
［24］　朱超岩, 姚晓东. 基于遗传算法优化的支持向量机在变压器故障诊断中应用［J］. 仪表技术, 2019(3): 21-23, 32.
Zhu Chaoyan, Yao Xiaodong. Application of the support vector machine in the fault diagnosis on the transformer based on the optimal genetic algorithm ［J］. Instrumentation Technology, 2019(3): 21-23, 32.
［25］　马创, 王尧, 李林峰. 基于遗传算法与支持向量机的水质预测模型［J］. 重庆大学学报, 2021, 44(7): 108-114.
Ma Chuang, Wang Yao, Li Linfeng. A water quality prediction model based on genetic algorithm and SVM ［J］. Journal of Chongqing University, 2021, 44(7): 108-114.
［26］　杨旭, 纪玉波, 田雪. 基于遗传算法的SVM参数选取［J］. 辽宁石油化工大学学报, 2004, 24(1): 54-58.
Yang Xu, Ji Yubo, Tian Xue. Parameters selection of SVM Based on genetic algorithm ［J］. Journal of Liaoning Petrochemical University, 2004, 24(1): 54-58.
［27］　张丽英, 鲜兴明, 杨杰, 等. 烘烤过程中烟叶颜色特征参数与色素含量的关系［J］. 烟草科技, 2013(8): 85-90.
Zhang Liying, Xian Xingming, Yang Jie, et al. Relationship between pigment concentration and color attributive parameters of tobacco leaves during fluecuring ［J］. Tobacco Science & Technology, 2013(8): 85-90.
［28］　焦祉衡. 低照度多光谱彩色成像中色彩还原技术研究［D］. 长春: 长春理工大学, 2021.
Jiao Zhiheng. Research on color reduction technology in low illumination multispectral color imaging ［D］. Changchun: Changchun University of Science and Technology, 2021.
［29］　李瑶. 低照度下可见光与近红外图像真彩色复原研究［D］. 昆明: 云南师范大学, 2021.
Li Yao. Research on true color restoration of visible and near infrared image under low illumination ［D］. Kunming: Yunnan Normal University, 2021.
［30］　段史江. 图像处理技术在烤烟烘烤过程中的应用研究［D］. 郑州: 河南农业大学, 2012.
Duan Shijiang. Research on application of image processing technology during curing process of fluecured tobacco ［D］. Zhengzhou: Henan Agricultural University, 2012.
［31］　谢滨瑶. 基于图像处理的烟叶成熟度鉴别方法［D］. 重庆: 西南大学, 2020.
Xie Binyao. Identification methods of tobacco maturity based on image processing ［D］. Chongqing: Southwest University, 2020.
［32］　庄珍珍. 基于机器视觉的烟叶自动分级方法研究［D］. 重庆: 西南大学, 2016.
Zhuang Zhenzhen. Method for automatic grading of tobacco based on machine vision ［D］. Chongqing: Southwest University, 2016.
［33］　Yin Y, Xiao Y, Yu H. An image selection method for tobacco leave grading based on image information ［J］. Engineering in Agriculture, Environment and Food, 2015, 8(3): 148-154.
［34］　Saadatfar H, Khosravi S, Joloudari J H, et al. A new Knearest neighbors classifier for big data based on efficient data pruning ［J］. Mathematics, 2020, 8(2): 286.

[1]	姜来, 王文娣, 霍晓静, 王辉, 唐娟, 李丽华, (. 死鸡识别机器人系统设计与试验[J]. 中国农机化学报, 2023, 44(8): 81-87.
[2]	舒卓, , 陈立平, , 陈梅香, 张瑞瑞, 郭新宇, 温维亮. 单目多视角图像的美国白蛾三维模型重建系统与试验[J]. 中国农机化学报, 2023, 44(8): 168-173.
[3]	刘雯雯, 孙裕晶, 姜树辉, 姜鹏. 遮挡情况下的行人检测方法研究[J]. 中国农机化学报, 2023, 44(7): 179-186.
[4]	周红标, 朱亚文, 刘晓洋, 张国良, 李边豪. 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.
[5]	王建翠, 惠巧娟, 吴立国. 基于多尺度注意力和深度可分离卷积的农田杂草检测[J]. 中国农机化学报, 2023, 44(5): 182-187.
[6]	罗山, 侯俊涛, 郑彬. 基于机器视觉的石榴品质自动分级方法[J]. 中国农机化学报, 2023, 44(3): 117-122.
[7]	吴俊鹏, 黄光文, 李君, . 水果病害视觉与光谱检测技术研究现状及展望[J]. 中国农机化学报, 2023, 44(2): 112-118.
[8]	李志臣, 凌秀军, 李鸿秋. 基于机器视觉的槟榔分级方法研究[J]. 中国农机化学报, 2023, 44(1): 137-141.
[9]	王珊, 薛新宇, 郭祥雨. 基于机器视觉的油菜菌核病分级检测研究[J]. 中国农机化学报, 2022, 43(5): 47-53.
[10]	刘媛杰, 张泽亮, 张洪洲, 李勇, 李伟强. 基于机器视觉技术的棉籽破损检测[J]. 中国农机化学报, 2022, 43(5): 71-76.
[11]	郑如新, 孙青云, 肖国栋. 基于机器视觉的金银花图像识别处理算法研究[J]. 中国农机化学报, 2022, 43(4): 153-159.
[12]	冯凯, 王茂励, 何晓宁, 王东伟, 岳丹松, 初香港. 基于辅助线的农机视觉导航路径提取算法研究[J]. 中国农机化学报, 2022, 43(10): 167-175.
[13]	李昕, 陈泽君, 李立君, 谭季秋, 吴发展, . 一种基于偏好免疫网络多特征辨识的油茶果分选识别方法[J]. 中国农机化学报, 2021, 42(9): 187-194.
[14]	叶磊, 韦克苏, 李德仑, 张富贵, 吴雪梅, . 基于改进RF特征选择策略的烤烟油分高光谱特征分析[J]. 中国农机化学报, 2021, 42(8): 196-202.
[15]	白云龙;傅彬;史振华;王健;. 基于标记分水岭算法的插秧机器人导航路径检测[J]. 中国农机化学报, 2021, 42(7): 142-147.