光谱学与光谱分析
光譜學與光譜分析
광보학여광보분석
SPECTROSCOPY AND SPECTRAL ANALYSIS
2015年
4期
1020-1024
,共5页
丁希斌%张初%刘飞%宋星霖%孔汶汶%何勇
丁希斌%張初%劉飛%宋星霖%孔汶汶%何勇
정희빈%장초%류비%송성림%공문문%하용
高光谱成像%草莓%可溶性固形物%特征提取
高光譜成像%草莓%可溶性固形物%特徵提取
고광보성상%초매%가용성고형물%특정제취
Hyperspectral imaging%Strawberry%Soluble solid content%Feature extraction
采用高光谱成像技术结合不同的特征提取方法,实现了对草莓可溶性固形物含量的检测。通过提取154颗成熟无损伤草莓的高光谱图像的874~1734 nm范围光谱信息,对941~1612 nm光谱采用移动平均法(moving average ,M A )进行预处理。基于残差法剔除19个异常样本后将剩余135个样本分为建模集(n=90)和预测集(n=45)。采用连续投影算法(successive projections algorithm ,SPA ),遗传偏最小二乘算法(genetic algorithm‐partial least squares ,GAPLS)结合连续投影算法(GAPLS‐SPA),加权回归系数(weighted regression coefficient ,Bw )以及CARS法(competitive adaptive reweighted sampling )选择特征波长分别提取14,17,24与25个特征波长,并采用主成分分析(principal component analysis ,PCA)与小波变换(wavelet transform ,WT )分别提取20与58个特征信息。分别基于全波段光谱、特征波长与特征信息建立PLS模型。所有模型都取得了较好的效果,基于全波段光谱的PLS模型与基于WT提取的特征信息的PLS模型的效果最优,建模集相关系数(rc )与预测集相关系数(rp )均高于0.9。结果表明高光谱成像技术结合特征提取方法可用于草莓可溶性固形物含量的检测。
採用高光譜成像技術結閤不同的特徵提取方法,實現瞭對草莓可溶性固形物含量的檢測。通過提取154顆成熟無損傷草莓的高光譜圖像的874~1734 nm範圍光譜信息,對941~1612 nm光譜採用移動平均法(moving average ,M A )進行預處理。基于殘差法剔除19箇異常樣本後將剩餘135箇樣本分為建模集(n=90)和預測集(n=45)。採用連續投影算法(successive projections algorithm ,SPA ),遺傳偏最小二乘算法(genetic algorithm‐partial least squares ,GAPLS)結閤連續投影算法(GAPLS‐SPA),加權迴歸繫數(weighted regression coefficient ,Bw )以及CARS法(competitive adaptive reweighted sampling )選擇特徵波長分彆提取14,17,24與25箇特徵波長,併採用主成分分析(principal component analysis ,PCA)與小波變換(wavelet transform ,WT )分彆提取20與58箇特徵信息。分彆基于全波段光譜、特徵波長與特徵信息建立PLS模型。所有模型都取得瞭較好的效果,基于全波段光譜的PLS模型與基于WT提取的特徵信息的PLS模型的效果最優,建模集相關繫數(rc )與預測集相關繫數(rp )均高于0.9。結果錶明高光譜成像技術結閤特徵提取方法可用于草莓可溶性固形物含量的檢測。
채용고광보성상기술결합불동적특정제취방법,실현료대초매가용성고형물함량적검측。통과제취154과성숙무손상초매적고광보도상적874~1734 nm범위광보신식,대941~1612 nm광보채용이동평균법(moving average ,M A )진행예처리。기우잔차법척제19개이상양본후장잉여135개양본분위건모집(n=90)화예측집(n=45)。채용련속투영산법(successive projections algorithm ,SPA ),유전편최소이승산법(genetic algorithm‐partial least squares ,GAPLS)결합련속투영산법(GAPLS‐SPA),가권회귀계수(weighted regression coefficient ,Bw )이급CARS법(competitive adaptive reweighted sampling )선택특정파장분별제취14,17,24여25개특정파장,병채용주성분분석(principal component analysis ,PCA)여소파변환(wavelet transform ,WT )분별제취20여58개특정신식。분별기우전파단광보、특정파장여특정신식건립PLS모형。소유모형도취득료교호적효과,기우전파단광보적PLS모형여기우WT제취적특정신식적PLS모형적효과최우,건모집상관계수(rc )여예측집상관계수(rp )균고우0.9。결과표명고광보성상기술결합특정제취방법가용우초매가용성고형물함량적검측。
Hyperspectral imaging combined with feature extraction methods were applied to determine soluble sugar content (SSC) in mature and scatheless strawberry .Hyperspectral images of 154 strawberries covering the spectral range of 874~1 734 nm were captured and the spectral data were extracted from the hyperspectral images ,and the spectra of 941~1 612 nm were preprocessed by moving average (MA) .Nineteen samples were defined as outliers by the residual method ,and the remaining 135 samples were divided into the calibration set (n=90) and the prediction set (n=45) .Successive projections algorithm (SPA) , genetic algorithm partial least squares (GAPLS ) combined with SPA ,weighted regression coefficient (Bw ) and competitive adaptive reweighted sampling (CARS) were applied to select 14 ,17 ,24 and 25 effective wavelengths ,respectively .Principal component analysis (PCA) and wavelet transform (WT) were applied to extract feature information with 20 and 58 features ,re‐spectively .PLS models were built based on the full spectra ,the effective wavelengths and the features ,respectively .All PLS models obtained good results .PLS models using full spectra and features extracted by WT obtained the best results with correla‐tion coefficient of calibration (rc ) and correlation coefficient of prediction (rp ) over 0.9 .The overall results indicated that hyper‐spectral imaging combined with feature extraction methods could be used for detection of SSC in strawberry .