光谱学与光谱分析
光譜學與光譜分析
광보학여광보분석
SPECTROSCOPY AND SPECTRAL ANALYSIS
2014年
7期
1938-1942
,共5页
朱逢乐%章海亮%邵咏妮%何勇
硃逢樂%章海亮%邵詠妮%何勇
주봉악%장해량%소영니%하용
高光谱成像%多宝鱼%冷藏时间%偏最小二乘回归%IDL%可视化
高光譜成像%多寶魚%冷藏時間%偏最小二乘迴歸%IDL%可視化
고광보성상%다보어%랭장시간%편최소이승회귀%IDL%가시화
Hyperspectral imaging%Turbot%Chilling storage time%Partial least squares regression%IDL%Visualization
提出了一种应用可见-近红外高光谱成像技术快速无损检测多宝鱼肉冷藏时间并实现其可视化的新方法。采集8种不同冷藏时间的共160个鱼肉样本的高光谱图像,并提取样本感兴趣区域(RO I )的平均光谱。取120个建模集样本的光谱数据与其相应的冷藏时间建立偏最小二乘回归(PLSR)模型,对40个预测集样本的冷藏时间进行预测,预测决定系数(R2)为0.9662,预测均方根误差(RMSEP)为0.6799 d ,获得了满意的预测精度。最后,用所建模型对预测集图像上每个像素点的冷藏时间加以预测,采用ID L图像编程技术将不同的时间用不同的颜色表示,最终以伪彩图的形式实现多宝鱼肉冷藏时间的可视化。结果表明,高光谱成像技术与化学计量学结合可以准确预测鱼肉的冷藏时间,与图像处理方法结合可以实现预测时间的可视化,能形象、直观地展示出鱼肉的新鲜度状态和分布情况,为实现水产品加工的自动化奠定了基础。
提齣瞭一種應用可見-近紅外高光譜成像技術快速無損檢測多寶魚肉冷藏時間併實現其可視化的新方法。採集8種不同冷藏時間的共160箇魚肉樣本的高光譜圖像,併提取樣本感興趣區域(RO I )的平均光譜。取120箇建模集樣本的光譜數據與其相應的冷藏時間建立偏最小二乘迴歸(PLSR)模型,對40箇預測集樣本的冷藏時間進行預測,預測決定繫數(R2)為0.9662,預測均方根誤差(RMSEP)為0.6799 d ,穫得瞭滿意的預測精度。最後,用所建模型對預測集圖像上每箇像素點的冷藏時間加以預測,採用ID L圖像編程技術將不同的時間用不同的顏色錶示,最終以偽綵圖的形式實現多寶魚肉冷藏時間的可視化。結果錶明,高光譜成像技術與化學計量學結閤可以準確預測魚肉的冷藏時間,與圖像處理方法結閤可以實現預測時間的可視化,能形象、直觀地展示齣魚肉的新鮮度狀態和分佈情況,為實現水產品加工的自動化奠定瞭基礎。
제출료일충응용가견-근홍외고광보성상기술쾌속무손검측다보어육랭장시간병실현기가시화적신방법。채집8충불동랭장시간적공160개어육양본적고광보도상,병제취양본감흥취구역(RO I )적평균광보。취120개건모집양본적광보수거여기상응적랭장시간건립편최소이승회귀(PLSR)모형,대40개예측집양본적랭장시간진행예측,예측결정계수(R2)위0.9662,예측균방근오차(RMSEP)위0.6799 d ,획득료만의적예측정도。최후,용소건모형대예측집도상상매개상소점적랭장시간가이예측,채용ID L도상편정기술장불동적시간용불동적안색표시,최종이위채도적형식실현다보어육랭장시간적가시화。결과표명,고광보성상기술여화학계량학결합가이준학예측어육적랭장시간,여도상처리방법결합가이실현예측시간적가시화,능형상、직관지전시출어육적신선도상태화분포정황,위실현수산품가공적자동화전정료기출。
This study proposed a new method using visible and near infrared (Vis/NIR) hyperspectral imaging for the detection and visualization of the chilling storage time for turbot flesh rapid and nondestructively .A total of 160 fish samples with 8 differ-ent storage days were collected for hyperspectral image scanning ,and mean spectra were extracted from the region of interest (ROI) inside each image .Partial least squares regression (PLSR) was applied as calibration method to correlate the spectral data and storage time for the 120 samples in calibration set .Then the PLSR model was used to predict the storage time for the 40 pre-diction samples ,which achieved accurate results with determination coefficient (R2 ) of 0.966 2 and root mean square error of prediction (RMSEP) of 0.679 9 d .Finally ,the storage time of each pixel in the hyperspectral images for all prediction samples was predicted and displayed in different colors for visualization based on pseudo-color images with the aid of an IDL program . The results indicated that hyperspectral imaging technique combined with chemometrics and image processing allows the determi-nation and visualization of the chilling storage time for fish ,displaying fish freshness status and distribution vividly and laying a foundation for the automatic processing of aquatic products .