基于高光谱成像的蓝莓内部品质检测 特征波长选择方法研究

【实例简介】
在特征波长选取方面有一些创新，可以作为参考。在特征波长选取方面有一些创新，可以作为参考。（基于高光谱成像的蓝莓内部品质检测 特征波长选择方法研究 古文君 1 ，田有文 1* ，张 芳 1 ，赖兴涛 1 ，何 宽 1 ，姚 萍 1 ，刘博林 2）
586- 48 20166 200 10~15mm 0.8~2.3g。 fone 3: (InSpector V10E, Spectral In Finland) 1392pix×1040pix CCD L CCD 2 (IGV-B141OM, IMPERX Incorporated, USA), 150W 1. CCD Camera; 2.Spectrometer; 3.Shot; 4. Light source; 5. Samples (3900 Illuminatior, Illumination Tech 6.Translationplatform7.Lightsourcecontroller;8.computer nologies inc.,USA)、 (IRCP0076-1 9. Translation platform controller COM,)、 (120cm×50cmx (DELL VoStro 5560D-1528 Figure 1 Schematic diagram of hyperspectral imaging cm system 400~1000nm, 472 2.8nm R R GY-4 (10mm) (DBR45 (successive projections algorithm, SPA (stepwise multiple linear regression, SMLR) (SPA) (SMLR) SPA SPA SMLR SPA-SPA、SMLR_SMLR、SPA- SMLRSMLR-SPA 21994-2018ChinaAcadcmicJournalElcctronicPublishingHousc.Allrightsrcscrved.http://www.cnki.nct 587 1.6 BP(error back propagation) BP 17 (correlation coeffiient of calibration, Re) (root mean square error of calibration set, RMSEC) correlation coeffiient of pre- diction, Rp) (root mean square error of prediction set, RMSEP) ENVI 4.8(Research System Inc, ), MATLAB 2014a(The Math Works Inc )、The Unscrambler9.7、 Excel2010(Ⅵ icrosoft d gle band d Wcve f. BP models for soluble solids The selected characteristic wavelength Curve of relative reflectance Extract the region of interes content and firmness prediction 2 figure 2 Flow chart of data processing 280mm, 68ms, 28mm·s-。 99% 20 2.2 600nm 600nm 2b 2c) 21994-2018ChinaAcadcmicJournalElcctronicPublishingHousc.Allrightsrcscrved.http://www.cnki.nct 588 48 23 (2f) BP Savitzky-Gola savitzky -golay Table 1 The effect of different spectra preprocessing Calibration set Predictio Spectrum type RMSEC RMSEP Original spcctrum 0.933/0.923 0.3510.404 0.9200.910 0.508/0.319 MSC The spectrum after MSC processing 0.940/0.945 0.56lO.312 0.9190.932 0.516/0.282 SN The spectrum after SNV processin 0.93709340.60210.24309220.9010.6320.462 Savitzky-golay The spectrum after Savitzky-Golay processing 0.955/0.955 0.3240.241 0.951/0.9490.400/0.278 2.5 SPA-SPA SMLR SMLR SPA-SMLR SMLR-SPA SPA-SPA SPA Savitzky-Golay SPA Table 2 The results of multi-stage characteristic wavelength selection method nm Characteristie wavelength selection method SPA-SPA 452,455,470,482,490,785,893,912,921,942,950 455,470,482,785,893.912 SMLR-SMLR 457,508,516,534,543,51,556,568,712,720.774,778 508,534,543,712,720,774 SPA-SMLR 452,455,470,482,490,785,893,912,921,942,950 452,470,482,490,893,912 SMLR-SPA 457,508,516,534,543,551,556,568,712,720,774,78 534,720 2.6 Savilzky-gola (FS)392 SPA-SPA SMLR-SMLR SMLR-SMLR SMLR-SPA BP BP 0.001 5000 21994-2018ChinaAcadcmicJournalElcctronicPublishingHousc.Allrightsrcscrved.http://www.cnki.nct 589 BP BP SPA-SPA Rp RMseP 0.9520.391°Brix, Rp RMSEP 0.9530.234Brix Table 3 Detection results of soluble solid content and firmness of blueberry based on different multi-stage characteristic wavelength selection methods Calibration set Prediction set Characteristic selection method Wavelength number RMSEC RMSEP 392 9550.955 0.324/0.241 0.9510.949 0.400/0.278 SPA-SPA 0.9590.956 0.3180.153 0.9520.953 0.391/0.234 SMLR-SMLR 0.9560.934 0.414/0.243 91210902 0.559/0.349 SPA SMLR 0.828/0.858 1.3670.585 8220809 1.440/0.719 SMLR- SPA 2 0.958/0.936 0.402/0.335 9320.928 0.435/0,404 1387nm1229 nm 91.5% BP R RMSEP 0.904215.163l BP 3 Rv0.84 V0.94 Rv0.83,SEV0.63。 400-1000nm Savitzky-Golay BP SPA-SPA SPA-SPA 21994-2018ChinaAcadcmicJournalElcctronicPublishingHousc.Allrightsrcscrved.http://www.cnki.nct 590 48 [1 KADER F,ROVEL. B Fractionation and identification of the phenolic compounds of highbush blueberries(Vaccinium corymbosum LUJ].Food Chemistry, 1996,55(1): 35-40 「J ,2012,33(1):340-342 ,2017,38(2):301-305. [4 MENDOZA F, LU R, ARIANA D,et al. Integrated spectral and image analysis of hyperspectral scattering data for prediction of ple [ruil firmness and soluble solids conlenl[J] Poslharvesl Biology and Technology, 2011, 62(2: 149-160 [5 SUN M J, ZHANG D, LIU L,et al. How to predict the sugariness and hardness of melons a near-infrared [J]. Food Chemistry, 2017,218(3:413-421 16 SIEDLISKA A, BARANOWSKI P, MAZUREK W, ct al. Classification models of bruise and cultivar detection on the basis of hy- perspectral imaging data[J]. Computers and Electronics in Agriculture, 2014, 106: 66-74 [7 LIU D, SUN D W, ZENG X N, el al. Recenl aDvances in wavelength seleclion lechniques for hyperspectral image processing in the food industry[J]. Food Bioprocess Technol, 2014, 7: 307-323 [8 ZHANG C, GUO C T, LIU F,et al. Hyperspectral imaging analysis for ripeness evaluation of strawberry with support vector ma- chine[j] Journal of Food Engincering, 2016, 179: 11-18 [9J ,2016,47(5:634-640 2009,29(:1611-1615 201536(12)171-176 12] J ,2012,32(11:3093 309 [13] LI B C, HOU B L, ZHANG D W,et al. Pears characteristics (soluble solids content and firmness prediction, varieties) testing Inethods based on visible-near infrared hyperspecTral imaging[J]. OpLik, 2016, 127: 2624-2630 [14] FAN S X, ZHANG B H,LI J B, et al. Prediction of soluble solids content of apple using the combination of spectra and textu ral features of hyperspectral reflectance imaging data[J. Postharvest Biology and Technology, 2016, 121: 51-61 [15 RAJKUMAR P, WANG N,EIMASRY G, et al.Studies on banana fruit quality and maturity stages using hyperspectral imaging[ JI Journal of Food Engineering 2012, 108: 194-200 ,2015,36(16):101 7 2015,35(8:2297-2302 [18] WANG N ,2007,23(2:151-155. 「19 2008,39(5):91-93 20」 201536(10:70-74. [21] WU D, SUN D WAdvanced applications of hyperspectral imaging technology for food quality and safety analysis and assess- ment a review part T[J]. Innovative Food Science and Emerging Technologies, 2013, 19(4): 1-14 J 2014,35(8:57-61 BP ,2012. 124」 13,44(2):142-146. 25] ,201523(6:1530-1537 M 011:41-48. [27 ,2013,24(10:1972-1976 2010,30(10):2729-2733 ?1994-2018ChinaAcadcmicJournaleLcctronicPublishingHousc.Allrightsreservedhttp://www.cnki.nct 【实例截图】
【核心代码】