YU Youjiang,YU Caili,SHANG Yuanhang,et al.Classification and Recognition of Jujube Varieties Based on Stacking Model Fusion[J].Northern Horticulture,2022,(08):139-148.[doi:10.11937/bfyy.20214005]
基于Stacking模型的红枣品种分类识别
- Title:
- Classification and Recognition of Jujube Varieties Based on Stacking Model Fusion
- Keywords:
- model fusion; cultivar classification; jujube; neural network; base learner
- 文献标志码:
- A
- 摘要:
- 新疆红枣品种较多，在进行红枣加工过程中需要对不同品种进行区分。针对当前人工分类效率低成本高、机械分类难以确保综合品质的问题，提出了基于Stacking模型融合的红枣品种分类识别方法。试验采集5个品类的红枣图像11 280张，进行预处理，建立数据集。构建以VGG 16、ResNet 50、Densenet 121 3种不同的卷积神经网络为基学习器，逻辑回归为次级学习器的Stacking集成学习模型，进行了集成模型与单一神经网络模型以及不同基学习器组合的集成模型间的对比试验。结果表明:在红枣分类识别任务中，采用单一模型的最高准确率为88.30%,该研究提出的融合模型能够达到92.38%的准确率，分类准确率提升了4.60个百分点。
- Abstract:
- There are many varieties of jujube in Xinjiang,so it is necessary to distinguish different varieties before processing.Aiming at the problems of low efficiency and high cost of manual classification and difficult to ensure the comprehensive quality of mechanical classification,a classification and identification method of jujube varieties based on Stacking model fusion was proposed.11 280 jujube images of 5 categories were collected and preprocessed to establish a data set.A model that three different convolution neural network (VGG 16,ResNet 50,DenseNet 121) as base learner and logistic regression as secondary learner were constructed.The comparative experiments were carried out between the integrated model and single neural network model,as well as the integrated model with different combinations of base learners.The results showed that the accuracy of the proposed Stacking model was 92.38%,which was improved by 4.60 percentage points compared with that of the best single model (88.30%).This method can effectively improve the identification accuracy of jujube varieties and provide reference for Xinjiang jujube from manual sorting to automatic machine identification.
参考文献/References:
[1]任继海.枣树管理与红枣贮藏加工[M].北京：中国科学技术出版社,1998.[2]钟小华,曹玉华,张永清,等.基于机器视觉技术的红枣全表面信息无损分拣系统研究与实现[J].食品与机械,2017,33(5):114-118.[3]YU W,DONG F W,HUI F W,et al.A microfluidic robot for rare cell sorting based on machine vision identification and multi-step sorting strategy[J].Talanta,2021,226:122-136.[4]MON T,ZARAUNG N.Vision based volume estimation method for automatic mango grading system[J].Biosystems Engineering,2020,198(10):338-349.[5]EREZ A P,EREZ C P,JUAN V,et al.Evaluation of the ripening stages of apple (Golden Delicious) by means of computer vision system[J].Biosystems Engineering,2017,159:46-58.[6]TRAFFANO S M V,CASTRO G M,COLOM R J,et al.New Spectrophotometric system to segregate tissues in aandarin fruit[J].Food and Bioprocess Technology,2018,11(2):399-406.[7]HUANG M,HE C,ZHU Q,et al.Maize seed variety classification using the integration of spectral and image features combined with feature transformation based on hyperspectral imaging[J].Applied Sciences,2016,6(6):183.[8]HUANG K Y,CHIEN M.A novel method of identifying paddy seed varieties[J].Multidisciplinary Digital Publishing Institute,2017,17(4):809.[9]王红军,熊俊涛,黎邹邹,等.基于机器视觉图像特征参数的马铃薯质量和形状分级方法[J].农业工程学报,2016,32(8):272-277.[10]刘广强,于欣,舒振宇,等.基于稀疏表示的枸杞分类研究[J].中国农机化学报,2016,37(3):250-254.[11]吴尚智,周运,王欢欢,等.利用粗糙集和双隐层BP神经网络的小麦籽粒品种分类[J].沈阳农业大学学报,2020,51(5):576-585.[12]苏军,饶元,张敬尧,等.基于GA优化SVM的干制红枣品种分类方法[J].洛阳理工学院学报(自然科学版),2018,28(4):65-69.[13]PANGAL D J,KUGENER G,SHAHRESTANI S,et al.A guide to annotation of neurosurgical intraoperative video for machine learning analysis and computer vision[J].World Neurosurgery,2021,150:26-30.[14]黄盛,李菲菲,陈虬.基于改进深度残差网络的计算断层扫描图像分类算法[J].光学学报,2020,40(3):56-64.[15]储岳中,汪佳庆,张学锋,等.基于改进深度残差网络的图像分类算法[J].电子科技大学学报,2021,50(2):243-248.[16]陈洋.基于卷积神经网络的农作物病虫害图像分类研究[D].南昌:江西农业大学,2019.[17]张笑铭,王志君,梁利平.一种适用于卷积神经网络的Stacking算法[J].计算机工程,2018,44(4):243-247.[18]LI L,WANG Y.Improved LeNet-5 convolutional neural network traffic sign recognition[J].International Core Journal of Engineering,2021,7(4):114-121.[19]CHEN L,HAO C,NING X,et al.A review for cervical histopathology image analysis using machine vision approaches[J].Artificial Intelligence Review,2020,53(2):4821-4862.[20]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].IEICE Transactions on Fundamentals of Electronics,Communications and Computer Sciences,2014,1409:1097-1105.[21]NAR A,YLDRM M,EROLU Y.Classification of pneumonia cell images using improved ResNet 50 model[J].Traitement du Signal,2021,38(1):165-173.[22]WU J,YANG H.Linear regression-based efficient SVM learning for large-scale classification[J].IEEE Transactions on Neural Networks and Learning Systems,2015,26(10):2357-2369.[23]MIRANDA J S,PICHARDO L O.Lecture notes of computer science[M].Berlin:Springer Verlag,2017.[24]ANBARASAN K.AI innovation in medical imaging diagnostics[M].Hershey:IGI Global,2020.[25]YU D,YANG J,ZHANG Y,et al.Additive densenet：Dense connections based on simple addition operations[J].Journal of Intelligent & Fuzzy Systems,2020,40(5):1-11.[26]WOLPERT D H.Stacked generalization[J].Neural Networks,1992,5(2):241-259.[27]CHANG X,WU J,LIU H,et al.Travel mode choice：A data fusion model using machine learning methods and evidence from travel diary survey data[J].Transportmetrica,2019,15(2):1587-1612.[28]袁培森,杨承林,宋玉红,等.基于Stacking集成学习的水稻表型组学实体分类研究[J].农业机械学报,2019,50(11):144-152.[29]数据分析与知识发现.Facebook宣布正式推出PyTorch 1.0稳定版[J].数据分析与知识发现,2018,2(12):88.[30]尚远航,余游江,吴刚.基于混合注意力机制的植物病害识别[J].塔里木大学学报,2021,33(2):94-103.[31]JANI V,OSTOVANEH M R,CHAMERA E,et al.Automatic segmentation of left ventricular myocardium and scar from lge-cmr images utilizing deep learning with weighted categorical cross entropy loss function weight initialization[J].Circulation,2019,140:1347-1353.
相似文献/References:
[1]王振启,陈洪国.咸宁桂花品种分类调查研究[J].北方园艺,2012,36(17):101.
WANG Zhen-qi,CHEN Hong-guo.The Investigation and Classification of Osmanthus fragrans in Xianning[J].Northern Horticulture,2012,36(08):101.
[2]管晓庆,王奎玲,刘庆华,等.RAPD技术在我国观赏植物中的应用[J].北方园艺,2007,31(04):0.[doi:10.11937/bfyy.200704030]
[J].Northern Horticulture,2007,31(08):0.[doi:10.11937/bfyy.200704030]
[3]邵金彩,刘玉霞,徐兴龙,等.北京鹫峰国家森林公园蜡梅品种调查及其园林应用[J].北方园艺,2017,41(11):90.[doi:10.11937/bfyy.201711019]
SHAO Jincai,LIU Yuxia,XU Xinglong,et al.Chimonanthus praecox Resource Survey and Application in the Jiufeng National Forest Park in Beijing[J].Northern Horticulture,2017,41(08):90.[doi:10.11937/bfyy.201711019]
备注/Memo
第一作者简介：余游江（1992-），男，硕士研究生，研究方向为园艺信息技术。E-mail:931529146@qq.com.责任作者：吴刚（1978-），男，硕士，副教授，现主要从事信息处理与智慧农业等研究工作。E-mail:wgdem_lt@126.com.基金项目：国家自然科学基金地区基金资助项目（42061046）；新疆生产建设兵团科技攻关与成果转化资助项目（2015AC023）；塔里木大学校级研究生创新资助项目（TDGRI202047）。收稿日期：2021-09-27