基于GA-RELM多特征优选的烟叶多部位正反面识别方法  

Multi-site front and back recognition method of tobacco leaf based on multi-feature optimization using GA-RELM

作　　者：陈婷[1] 赵晓琳 张冀武 盖小雷 张晓伟 刘宇晨 王燕 龙杰 CHEN Ting;ZHAO Xiaolin;ZHANG Jiwu;GAI Xiaolei;ZHANG Xiaowei;LIU Yuchen;WANG Yan;LONG Jie(Factory of Mechanical and Electrical Engineering,Kunming University of Science and Technology,Kunming,Yunnan 650500,China;Yunnan Tobacco Quality Supervision and Testing Station,Kunming,Yunnan 650106,China;Yunnan Tobacco Company,Kunming,Yunnan 650217,China)

机构地区：[1]昆明理工大学机电工程学院,云南昆明650500 [2]云南省烟草质量监督监测站,云南昆明650106 [3]云南省烟草烟叶公司,云南昆明650217

出　　处：《湖南农业大学学报(自然科学版)》2025年第1期113-122,共10页Journal of Hunan Agricultural University(Natural Sciences)

基　　金：云南省重大科技专项计划(202002AC080001);中国烟草总公司云南省烟草公司科技计划重点项目(2020530000241003、2021530000241012)。

摘　　要：针对现有烟叶分级模型多基于平整烟叶的正面特征构建,分级模型准确率和实用性较低的问题,提出一种基于遗传算法-正则化极限学习机(GA-RELM)多特征优选的烟叶多部位正反面识别方法。首先,对自然状态下的烟叶进行多尺度正反面特征提取,构建正反面数据集,根据特征重要性和特征间的潜在关系,实现特征降维并构建新特征组合。其次,对正则化极限学习机(RELM)进行隐藏层偏置寻优,以提高模型实际应用性和分类精度。结果表明:与原极限学习机(ELM)相比,GA-RELM对自然状态下的烟叶正反面和多部位正反面的分类精度分别提高了0.84%和7.88%,运算时间分别减少2.56 s和5.72 s;与其他烟叶分级算法相比,GA-RELM在准确率、精确率、召回率、F1评分等多个指标上表现出明显优势。To address the issues of low accuracy and practicality in existing tobacco leaf grading models,which are mostly built upon the front-side features of flattened tobacco leaves,a multi-site front and back recognition method was proposed using a genetic algorithm-regularized extreme learning machine(GA-RELM).Firstly,multi-scale features from both side of tobacco leaves in their natural state were extracted to construct dataset.Feature importance and relationships were analyzed to reduce dimensionality and construct optimized feature combinations.Secondly,the hidden layer biases of the regularized extreme learning machine(RELM)were optimized to enhance model accuracy and applicability.The results showed that compared with the original extreme learning machine(ELM),GA-RELM improved classification accuracy by 0.84%and 7.88%for front/back leaves and other parts,respectively,while reducing the computation time by 2.56 s and 5.72 s,respectively.GA-RELM outperformed other grading algorithms in accuracy,precision,recall and F1-score.

关 键 词：烤烟 烟叶分级 多特征优选 遗传算法 正则化极限学习机 

分 类 号：TS42[农业科学—烟草工业]