1.昆明理工大学 理学院,云南 昆明 650500
2.云南警官学院 刑事侦查学院,云南 昆明 650223
吴加权,博士,高级工程师,研究方向:结构振动无损检测,E-mail:710866288@qq.com
收稿:2025-02-05,
修回:2025-03-08,
录用:2025-03-26,
纸质出版:2025-11-15
移动端阅览
鲁晓权,马琨,李帆,张建强,张馨予,吴加权,李自超,张津豪,任慧慧,陈航.基于高光谱成像技术和随机森林的原子印油种类识别[J].分析测试学报,2025,44(11):2339-2345.
LU Xiao-quan,MA Kun,LI Fan,ZHANG Jian-qiang,ZHANG Xin-yu,WU Jia-quan,LI Zi-chao,ZHANG Jin-hao,REN Hui-hui,CHEN Hang.Study on Identification of Atomic Oil Types Based on Hyperspectral Imaging Technology and Random Forest Algorithm[J].Journal of Instrumental Analysis,2025,44(11):2339-2345.
鲁晓权,马琨,李帆,张建强,张馨予,吴加权,李自超,张津豪,任慧慧,陈航.基于高光谱成像技术和随机森林的原子印油种类识别[J].分析测试学报,2025,44(11):2339-2345. DOI: 10.12452/j.fxcsxb.25020568.
LU Xiao-quan,MA Kun,LI Fan,ZHANG Jian-qiang,ZHANG Xin-yu,WU Jia-quan,LI Zi-chao,ZHANG Jin-hao,REN Hui-hui,CHEN Hang.Study on Identification of Atomic Oil Types Based on Hyperspectral Imaging Technology and Random Forest Algorithm[J].Journal of Instrumental Analysis,2025,44(11):2339-2345. DOI: 10.12452/j.fxcsxb.25020568.
该文采用高光谱成像技术获取多品牌原子印油的光谱数据,并运用Savitzky-Golay(SG)方法进行预处理。在此基础上,构建了基于随机森林(RF)算法的原子印油种类鉴别模型。为验证模型性能,研究将RF模型与反向传播神经网络(BP)和多层感知器(MLP)等传统方法构建的模型进行了系统性对比分析。同时,采用网格搜索结合五倍交叉验证方法对模型参数进行优化,以提升模型的性能和泛化能力。实验结果表明,RF分类模型(决策数目为20,叶节点数为3)在精确率、灵敏度、特异性和F1-score等评价指标上均优于BP和MLP模型,其训练集和测试集分类准确率分别达到99.77%和98.66%。所提出的高光谱成像技术与RF算法相结合,可以快速、无损、准确地识别印油种类,为原子印章色痕检验提供了新的技术参考。
The identification of stamp pad ink types is a critical component in the field of forensic document examination,holding significant practical value for the analysis of seal impressions. In this study,hyperspectral imaging technology was employed to acquire spectral data from multiple brands of stamp pad inks,followed by preprocessing using the Savitzky-Golay(SG) method. Subsequently,a stamp pad ink type identification model was constructed based on the random forest (RF) algorithm. To validate the model's performance,the RF model was systematically compared with traditional methods such as the backpropagation neural network(BP) and the multilayer perceptron (MLP). Additionally,grid search combined with five-fold cross-validation was utilized to optimize model parameters,thereby enhancing the model’s performance and generalization capability. Experimental results demonstrated that the RF classification model(with 20 decision trees and 3 leaf nodes) outperformed the BP and MLP models across evaluation metrics including precision,sensitivity,specificity,and F1-score,achieving classification accuracies of 99.77% and 98.66% on the training and test sets,respectively. The proposed method,integrating hyperspectral imaging technology with the RF algorithm,enables rapid,non-destructive,and accurate identification of stamp pad ink types,offering a novel technical reference for the analysis of atomic seal ink traces.
GA/T 1449 - 2017 . Code of Practice for Examination of Seals in Forensics. National Technical Committee on Forensic Science of Standardization Administration of China Document Examination Sub-technical Committee(法庭科学印章检验技术规范.全国法庭科学标准化技术委员会文件检验分技术委员会) .
Silva C S , Borba F S L , Pimentel M F , Pontes M J C , Honorato R S , Pasquini C . Microchem. J. , 2013 , 109 : 122 - 127 .
Wang X F , Yu J , Xie M X , YaoY T , Han J . Forensic Sci. Int. , 2008 , 180 ( 1 ) : 43 - 49 .
Adam C D , Sherratt S L , Zholobenko V L . Forensic Sci. Int. , 2008 , 174 ( 1 ): 16 - 25 .
Dirwono W , Park J S , Agustin-Camacho M R , Kim J , Park H M , Lee Y , Lee K B . Forensic Sci. Int. , 2010 , 199 ( 1/3 ): 6 - 8 .
Sharma S , Garg D , Chophi R , Singh R . Forensic Chem. , 2021 , 26 : 100377 .
Fu P , Cui L , Li S . Chin . J. Inorg. Anal. Chem. (付沛,崔岚,李硕. 中国无机分析化学), 2024 , 14 ( 6 ): 836 - 841 .
Shen F Z , Deng H H , Yu L J , Cai F H . Forensic Chem. , 2022 , 280 : 121504 .
Reed G , Savage K , Edwards D , Nic Daeid N . Sci. Justice , 2014 , 54 ( 1 ): 71 - 80 .
Wang M J , Dai X J , Tang C Q , Lu Z Y . Infrared Technol. (王鸣久,代雪晶,汤澄清,卢兆一 .红外技术), 2023 , 45 ( 1 ): 56 - 63 .
Melit Devassy B , George S . Forensic Sci. Int. , 2020 , 311 : 110194 .
Chen W L , Wang Q B , Lu H X , Yang H H , Liu T , Xu D Z , Du W C . J. Instrum. Anal. (陈文丽,王其滨,路皓翔,杨辉华,刘彤,许定舟,杜文川. 分析测试学报), 2020 , 39 ( 10 ): 1267 - 1273 .
Ding S , Shen T R , Zhang Y F , Du H Z , Wu Y , Zou X Y . J. Instrum. Anal. (丁莎,申涛榕,张艳飞,杜欢哲,吴榆,邹小勇. 分析测试学报), 2023 , 42 ( 11 ): 1510 - 1516 .
Wen Z , Yuan L N , Huang W , Huang W Y , Mo J Y , Feng W G . Guangxi Sci. (文竹,袁立宁,黄伟,黄琬雁,莫嘉颖,冯文刚. 广西科学), 2023 , 30 ( 5 ): 942 - 950 .
Asadi S , Roshan S , Kattan M W . J. Biomed. Inf. , 2021 , 115 : 103690 .
Bian X H , Liu Y , Wang Y , Zhang Q , Zhang Y . J. Instrum. Anal. (卞希慧,刘雨,王瑶,张强,张妍. 分析测试学报), 2025 , 44 ( 2 ): 229 - 237 .
Zhou M , Feng H , Liu J , Pi J Y , Wang H X , Zhou T H , Peng Q Z , Zhang L . J. Instrum. Anal. (周密,冯灏,刘杰,皮江一,王会霞,周陶鸿,彭青枝,张莉. 分析测试学报), 2021 , 40 ( 7 ): 1011 - 1017 .
0
浏览量
89
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
