基于PPF投影算法和高光谱技术的卷烟牌号识别模型
Cigarette brand identification model based on PPF projection algorithm and hyperspectral technology
-
摘要: 针对卷烟成分复杂、牌号识别难度大的问题,提出了一种基于PPF投影算法和高光谱技术的卷烟牌号识别模型。首先,采用PPF投影算法对原始光谱及经多元散射校正(MSC)、一阶微分(1stD)、二阶微分(2ndD)处理后的数据进行光谱相似度表征;然后,通过连续投影算法(SPA)和遗传算法(GA)进行特征波长选取,以利于后续分类性能的提升;最后,分别采用支持向量机(SVM)、极限梯度提升(XGBoost)算法建立牌号识别模型,并进行性能评价。结果表明:在高光谱技术结合PPF投影算法中,2ndD为最佳波段处理方法,能够显著增强光谱可分性;基于2ndD-SPA-SVM建立的识别模型为最佳模型,训练集、测试集的总体分类精度(OA)分别为94.58%、92.50%;不同牌号卷烟配方烟丝的叶丝和膨胀丝占比差异越大,类别之间的相似度越小,识别准确率越高。该模型可为不同牌号的卷烟提供一种新的高效快速、准确无损的分类判别方法,为高光谱技术在卷烟品牌维护、叶组配方设计等中的应用提供参考。Abstract: Addressing the complexity of cigarette ingredients and the challenges in brand identification, a cigarette brand identification model based on Projection Pursuit based on Fisher‘s Criterion (PPF) and hyperspectral technology was proposed. Firstly, the PPF projection algorithm was employed to conduct spectral similarity analysis on the original spectra as well as those processed with Multiplicative Scatter Correction (MSC), first-order derivative (1stD), and second-order derivative (2ndD). Secondly, feature wavelength selection was carried out using Successive Projections Algorithm (SPA) and Genetic Algorithm (GA) to enhance the classification performance in subsequent steps. Finally, cigarette brand identification models were established using Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) algorithms, and the personality of the model was evaluated. The results indicated that, in the combination of hyperspectral technology and the PPF projection algorithm, the second-order derivative (2ndD) served as the optimal band processing method, significantly enhancing the spectral separability. The recognition model established based on 2ndD-SPA-SVM emerged as the best model, achieving an overall classification accuracy of 94.58% and 92.50% for the training and test sets respectively. Moreover, a greater difference in the proportion of leaf silk and expanded silk among different brand formulations led to a lower similarity value between categories and a higher recognition accuracy. This model can provide a new efficient, fast, accurate, and non-destructive classification and discrimination method for cigarettes of different grades. It offered theoretical support for the application of hyperspectral technology in cigarette brand maintenance, tobacco blend formulation design, and other scenarios.
-
-
[1]
刘伟,刘波,马戎,等.基于卷烟品牌风格特征的配方构建及工艺技术[J].食品工业,2021,42(7):96-100.
-
[2]
祁林,乔俊峰,唐习书,等.卷烟制丝过程物料质量稳定性评价[J].轻工学报,2022,37(5):85-90
,97. -
[3]
罗登山,曾静,刘栋,等.叶片结构对卷烟质量影响的研究进展[J].郑州轻工业学院学报(自然科学版),2010,25(2):13-17.
-
[4]
徐秀娟,洪祖灿,柴国璧,等.基于香气活性值的烟草提取物成分分析及感官作用评价[J].轻工学报,2023,38(2):63-71.
-
[5]
郝捷,江彩艳,柴颖,等.基于GC-IMS的不同产地烟草中挥发性风味物质分析[J].轻工学报,2023,38(2):87-93
,117. -
[6]
高震宇,王安,董浩,等.基于卷积神经网络的烟丝物质组成识别方法[J].烟草科技,2017,50(9):68-75.
-
[7]
SAHOO R N,RAY S S,MANJUNATH K R.Hyperspectral remote sensing of agriculture[J].Current Science,2015,108(5):848-859.
-
[8]
张卫正,张伟伟,张焕龙,等.基于高光谱成像技术的甘蔗茎节识别与定位方法研究[J].轻工学报,2017,32(5):95-102.
-
[9]
黄敏,夏超,朱启兵,等.融合高光谱图像技术与MS-3DCNN的小麦种子品种识别模型[J].农业工程学报,2021,37(18):153-160.
-
[10]
孙俊,靳海涛,武小红,等.基于低秩自动编码器及高光谱图像的茶叶品种鉴别[J].农业机械学报,2018,49(8):316-323.
-
[11]
CHEN H D,PU H Y,WANG B,et al.Image Euclidean distance-based manifold dimensionality reduction algorithm for hyperspectral imagery[J].Journal of Infrared and Millimeter Waves,2013,32(5):450.
-
[12]
郑田甜.花生种子品质可见-近红外光谱的特征提取与分类识别[D].烟台:烟台大学,2014.
-
[13]
王同晖.基于红外光谱的白酒鉴伪及溯源系统设计与实现[D].武汉:华中科技大学,2015.
-
[14]
CHAVDA P,MANDAL S,MITRA S K.Dimensionality reduction by consolidated sparse representation and fisher criterion with initialization for recognition[C]//SINGH SK,ROY P,RAMAN B,et al.International Conference on Computer Vision and Image Processing.Singapore:Springer,2021:332-343.
-
[15]
CAI J Y,LIANG M,WEN Y D,et al.Analysis of tobacco color and location features using visible-near infrared hyperspectral data[J].Spectroscopy and Spectral Analysis,2014,34(10):2758-2763.
-
[16]
米津锐,马翔,张雅娟,等.基于近红外光谱投影及蒙特卡洛方法的烟叶配方比例上限分析[J].光谱学与光谱分析,2011,31(4):915-919.
-
[17]
SHU H C,GONG Z,TIAN X C.Fault-section identification for hybrid distribution lines based on principal component analysis[J].CSEE Journal of Power and Energy Systems,2021,7(3):591-603.
-
[18]
CHANG H Y,ZHANG F L,MA S,et al.Unsupervised domain adaptation based on cluster matching and Fisher criterion for image classification[J].Computers & Electrical Engineering,2021,91:107041.
-
[19]
宁鸿章,谭鑫,李宇航,等.空-谱维联合Savitzky-Golay高光谱滤波算法及其应用[J].光谱学与光谱分析,2020,40(12):3699-3704.
-
[20]
邱彦,张血琴,郭裕钧,等.基于高光谱技术的绝缘子污秽等级检测方法[J].高电压技术,2019,45(11):3587-3594.
-
[21]
JIANG W,LI M,LIU Z Y,et al.Study on detection of potato starch content by optimum hyperspectral characteristic wavelength method[C]//WANG Y,MARTINSEN K,YU T,et al.International Workshop of Advanced Manufacturing and Automation.Singapore:Springer,2021:174-182.
-
[22]
ZHENG W L,WANG C J,CHANG S F,et al.Hyperspectral wide gap second derivative analysis for in vivo detection of cervical intraepithelial neoplasia[J].Journal of Biomedical Optics,2015,20(12):121303.
-
[23]
殷勇,王光辉.连续投影算法融合信息熵选择霉变玉米高光谱特征波长[J].核农学报,2020,34(2):356-362.
-
[24]
张帅堂,王紫烟,邹修国,等.基于高光谱图像和遗传优化神经网络的茶叶病斑识别[J].农业工程学报,2017,33(22):200-207.
-
[25]
黄林生,刘文静,黄文江,等.小波分析与支持向量机结合的冬小麦白粉病遥感监测[J].农业工程学报,2017,33(14):188-195.
-
[26]
杜豫川,都州扬,刘成龙.基于极限梯度提升的公路深层病害雷达识别[J].同济大学学报(自然科学版),2020,48(12):1742-1750.
-
[1]
-
点击查看大图
计量
- PDF下载量: 18
- 文章访问数: 716
- 引证文献数: 0
下载:
