Professional Documents
Culture Documents
Original papers
a r t i c l e i n f o a b s t r a c t
Article history: The aim of this work was to evaluate the performance of hyperspectral data coupled with chemometrics
Received 7 April 2015 methods in characterizing and detecting the non-visible mechanical damage of blueberries with time
Received in revised form 1 December 2015 evolution. Reflectance and transmittance as well as interactance hypercubes were automatically seg-
Accepted 9 January 2016
mented by the region growing based algorithms. The maximum-normalized spectra were pretreated
Available online 23 January 2016
by the Standard Normal Variate algorithm, and subsequently the Competitive Adaptive Reweighted
Sampling algorithm was applied to extract the damage-specific wavelengths. Based on confusion matri-
Keywords:
ces and area under Receiver Operating Characteristics curves, transmittance showed relatively superior
Hyperspectral imaging
Mechanical damage
performance to reflectance and interactance. Application of new sample set subjected to impact tests
Physical property with time evolution, results demonstrated that it was especially difficult to distinguish fresh damage
Classification model in blueberry. At 2 days after impacted, several transmittance-based classifiers obtained satisfactory accu-
Chemometrics racies for classifying damaged (sound) blueberries: logistic regression 79.1% (85.7%), multilayer
perceptron-back propagation 74.4% (92.1%) and logistic function tree 72.1% (95.2%). Furthermore, the
physical property preliminarily proved to be more pronounced than the absorbed impact energy for
damage incidence and severity of blueberry via the use of multiple comparison.
2016 Elsevier B.V. All rights reserved.
http://dx.doi.org/10.1016/j.compag.2016.01.015
0168-1699/ 2016 Elsevier B.V. All rights reserved.
20 M.-H. Hu et al. / Computers and Electronics in Agriculture 122 (2016) 1928
Fig. 1. The definition of blueberry damage degrees: (a) sound; (b) minor damage; and (c) (major) damage.
Fig. 3. Hypercube processing and classifier descriptions: (a) reflectance and transmittance hypercubes; (b) procedures of hypercube processing; (c) procedure of spectral
processing; (d) classifier descriptions. Note: 1 = region growing of seed (1, 1) with threshold 400; interactance images are segmented by the same operation of reflectance,
expect that the threshold to eliminate bright pixels is set as 800.
humidity of approximate 85%. Mature samples with dark blue or berries were applied to induce the impact damage, and analyzed
purple skin were selected for further analysis (Yang et al., 2014). by hyperspectral imaging with respect to the time evolution
Among 737 samples, 304 sound and 253 damaged berries were measurements were carried out before impact and immediately
used for establishing classification models. The rest of 180 sound after impact (fresh damage), followed by 12 h, 1 and 2 days.
22 M.-H. Hu et al. / Computers and Electronics in Agriculture 122 (2016) 1928
SR SD
Sr 10a 2
RW RD
Table 2
Confusion matrices of five classifiers for distinguishing sound and damaged blueberries with the use of CARS selected reflectance, transmittance and interactance spectra.
!
2A w
y w2 c 4
p 4x xc 2
Table 3
Results of multiple comparison of sound and affected blueberries using offset in transmittance on successive measurement times.
Note: within the same column, values not followed by the same letter are significantly different (p < 0.05).
26 M.-H. Hu et al. / Computers and Electronics in Agriculture 122 (2016) 1928
Table 4
Confusion matrices of transmittance-based classifiers for detecting sound and damaged blueberries with respect to the times.
were selected for reflectance, transmittance and interactance, interactance models, reflectance models had relatively low AUC
respectively. values (between 0.85 and 0.92). AUC values of transmittance and
CARS algorithm was used to select the wavelengths informative interactance models were very high and ranged from 0.96 to
with mechanical damage to reduce the redundant data in spectra, 1.00. Logistic model in interactance and tree.LMT model in trans-
thus enhancing accuracy and robustness of classifier. Mean CARS mittance as well as interactance obtained the AUC value of 1.00.
weights are illustrated in Fig. 6. The CARS weight peaks or valleys This observation referring to AUC could explain the fact that trans-
for reflectance concentrated on the spectral range from 795.28 nm mitted and interacted spectra contain more internal information
to 899.24 nm, indicating that this very Near Infrared in reflectance than reflected spectra (Fu et al., 2007; Wu and Sun, 2013). Based
could interpret most of damage information. However, the interac- on AUC values in combination with confusion matrices, classifiers
tance range of 1016.831085.67 nm might be sensitive to blue- in transmittance were considered to outperform these in
berry mechanical damage. Particularly, in the case of reflectance and interactance.
transmittance, the sharp valley and peak occurred at 802.52 nm
and 803.32 nm, respectively. According to the mean weight of 3.3. Factors for impact incidence of blueberries
every wavelength, a total of 27, 32 and 40 wavelengths were cho-
sen as damaged-specific spectra for reflectance, transmittance and The mechanical damage incidence and severity of fruit are
interactance, respectively (Table 1). affected by several factors including physical properties, drop
height and compression degree (Knee, 2002; Opara and Pathare,
3.2. Classification models based on selected spectra 2014). In present work, physical property and absorbed impact
energy was analyzed, and the other factors such as variety and
Confusion matrices of five classification models are summarized maturity were to great extent kept consistent from berry to berry.
in Table 2. For all classifiers, the discrimination accuracies of sound Before impact experiments, when the testing blueberries were
blueberries in prediction (calibration) sample sets were beyond simultaneously identified as damage by four transmittance-based
93.4% (90.4%) and 89.5% (91.2%) for reflectance and transmittance, classifiers built in Section 3.2, they were regarded as prior-
respectively. In addition to 69.7% accuracy for logistic model, inter- damaged samples. A total of 11 prior-damaged samples were elim-
actance could also predict sound blueberries with accuracy beyond inated from the following analysis. After impact treatments, due to
85.5%. In terms of reflectance, the best classification accuracy of the individual variability among blueberries, the dropped berries
77.8% (85.3%) were observed for MP-ANN and trees.LMT models were categorized into three groups viz. damage (43 cases), minor
in damaged sample sets of prediction (calibration), followed by damage (67 cases) and sound (59 cases) by manual evaluation.
trees.FT 76.2% (85.3%), SMO 74.6% (75.8%) and logistic A double Y axis plot of these two factors is displayed in Fig. 8 for
71.4% (90.0%). Compared with reflectance, four transmittance three affected groups. No significant difference was observed
models viz. SMO, MP-ANN, trees.FT and trees.LMT achieved 100% between absorbed impact energy and severity of impact damage
accuracy for recognizing damaged samples in prediction set. Mean- (p > 0.05). Highly significant effect of physical property was found
while, accuracies of these models in calibration set were accept- for impact damage occurrence and severity of blueberry (p < 0.01).
able (>81.6%). For interactance, no misclassification was found for As could be seen from Fig. 8, the increase in physical property, as
five established classifiers in damaged prediction set; however, expressed by spectral predicted hardness, would lead to high dam-
these model performances (>77.4%) in calibration set were not as age susceptibility of blueberry. Previous studies of Abedi and
good as transmittance models. In conclusion, as shown in Table 2, Ahmadi (2014) and Ahmadi et al. (2010) also reported that the
transmittance-based classifiers showed superior performances physical properties affected apple and peach bruise susceptibilities
than reflectance and interactance. significantly. From this point of view, above results demonstrated
AUC is an important statistical parameter for evaluating classi- the potential of using physical property parameters to estimate
fier performance: the closer AUC is to 1, the better overall diagnos- the damage susceptibility of blueberry in further study. Conse-
tic performance of established classifier (Fawcett, 2006; Siedliska quently, we preliminarily concluded that the physical properties
et al., 2014). Fig. 7 presents ROC curves of classifiers and the corre- i.e. hardness is the main factor affecting blueberry damage suscep-
sponding AUC values. Overall, compared to transmittance and tibility, particularly for impact damage.
M.-H. Hu et al. / Computers and Electronics in Agriculture 122 (2016) 1928 27
3.4. Spectral behavior of sound and impacted blueberries satisfactory accuracies for predicting both sound and damaged
blueberries. This research will greatly benefit the blueberry indus-
As results reported in Section 3.2, only transmittance behavior try such as the elimination of the damaged berries allowing the
of affected blueberry was evaluated during cold storage. Mean berries up to one year in the freezer.
transmittance spectra measured on successive times were shown
in Fig. 9 for three affected groups. To quantitatively analyze spec-
tral changes, the multiple comparison was conducted and the Acknowledgements
results were listed in Table 3. In the case of sound group, the signif-
icant differences were found between 12 h measurement time and This study was supported by the National Natural Science Foun-
the others (p < 0.05). This was also observed in minor damage dation of China (NSFC31271896), the Innovation Fund Project for
group; however, there were no significant difference between Graduate Student of Shanghai (JWCXSL1401) and the Shanghai
1 day and 2 days measurements, either between 1 day and imme- Municipal Natural Science Foundation (12ZR1420500). The authors
diate measurements (p > 0.05). For damage group, no notable dif- gratefully acknowledge Dr. Renfu Lu for his help in experimental
ference existed between 2 days and 1 day measurements, either design.
between 2 days and 12 h measurements (p < 0.05). Overall, the
results presented in Table 3 were consistent with change tenden- References
cies in Fig. 9 by visual inspection. Further experiments are required
for interpreting why the considerable spectral amplitudes occurred Abedi, G., Ahmadi, E., 2014. Bruise susceptibilities of Golden Delicious apples as
in 12 h measurement time after impacted. affected by mechanical impact and fruit properties. J. Agric. Sci. 152, 439447.
Ahmadi, E., Ghassemzadeh, H.R., Sadeghi, M., Moghaddam, M., Neshat, S.Z., 2010.
The effect of impact and fruit properties on the bruising of peach. J. Food Eng.
97, 110117.
3.5. Classified accuracies of damaged blueberries with time evolution
Allan-Wojtas, P.M., Forney, C.F., Carbyn, S.E., Nicholas, K., 2001. Microstructural
indicators of quality-related characteristics of blueberries an integrated
Table 4 shows confusion matrices of transmittance-based mod- approach. LWT Food Sci. Technol. 34, 2332.
Baranowski, P., Mazurek, W., Pastuszka-Wozniak, J., 2013. Supervised classification
els for identifying sound and damaged blueberries over a period of
of bruised apples with respect to the time after bruising on the basis of
time after mechanically impacted. Generally, sound blueberries hyperspectral imaging data. Postharvest Biol. Technol. 86, 249258.
were better classified than damaged except at 12 h measurement Baranowski, P., Mazurek, W., Witkowska-Walczak, B., Sawinski, C., 2009. Detection
where 106 and 55 sound berries were identified as damaged of early apple bruises using pulsed-phase thermography. Postharvest Biol.
Technol. 53, 91100.
respectively for logistic and MP-ANN models. The possible reason Baranowski, P., Mazurek, W., Wozniak, J., Majewska, U., 2012. Detection of early
for this might be that more berries of aged damages were used dur- bruises in apples using hyperspectral data and thermal imaging. J. Food Eng.
ing the modeling procedures. On immediate measurement time, in 110, 345355.
Cen, H., Lu, R., Ariana, D.P., Mendoza, F., 2014. Hyperspectral imaging-based
addition to 58.1% accuracy for logistic, the other models did not classification and wavebands selection for internal defect detection of pickling
perform well for damaged blueberries with prediction accuracies cucumbers. Food Bioprocess Technol. 7, 16891700.
below 30.2%. Though prediction accuracies higher than 88% were Cessie, L.S., Houwelingen, J.C.V., 1992. Ridge estimators in logistic regression. Appl.
Stat. 41, 191201.
obtained for logistic and MP-ANN models on 12 h measurement, Coelho, P.A., Soto, M.E., Torres, S.N., Sbarbaro, D.G., Pezoa, J.E., 2013. Hyperspectral
their performances were inferior in classifying sound blueberries. transmittance imaging of the shell-free cooked clam Mulinia edulis for parasite
Interestingly, trees.LMT model achieved acceptable accuracies of detection. J. Food Eng. 117, 408416.
Chen, X., Liu, K., Cai, J., Zhu, D., Chen, H., 2015. Identification of heavy metal-
80.2% and 76.7%, respectively, for sound and damaged blueberries
contaminated Tegillarca granosa using infrared spectroscopy. Anal. Methods 7,
on 12 h after impacted. Nonetheless, models performances became 21722181.
inferior at 1 day measurement time with accuracies not exceeding Demir, N., Ferraz, A.C.O., Sargent, S.A., Balaban, M.O., 2011. Classification of
impacted blueberries during storage using an electronic nose. J. Sci. Food
62.8% in damaged sample classifications. At 2 days after impacted,
Agric. 91, 17221727.
the satisfactory results were obtained for all models in classifying Elks, C.M., Francis, J., Stull, A.J., Cefalu, W.T., Shukitt-Hale, B., Ingram, D.K., 2013.
damaged (sound) blueberries and listed in descending order based Overview of the Health Properties of Blueberries, Bioactives in Fruit. John Wiley
on damaged prediction accuracies: logistic 79.1% (85.7%), MP- & Sons, Ltd., pp. 251271.
ElMasry, G., Wang, N., Vigneault, C., Qiao, J., ElSayed, A., 2008. Early detection of
ANN 74.4% (92.1%), trees.LMT 72.1% (95.2%), trees.FT 62.7% apple bruises on different background colors using hyperspectral imaging. LWT
(94.4%) and SMO 58.1% (97.6%). Among them, 3 sound and 9 Food Sci. Technol. 41, 337345.
damaged samples were misclassified by SMO and logistic models, ElMasry, G., Wold, J.P., 2008. High-speed assessment of fat and water content
distribution in fish fillets using online imaging spectroscopy. J. Agric. Food
respectively. The MP-ANN and trees.LMT classifiers were suitable Chem. 56, 76727677.
for both sample groups owing to the relatively high sound and Fawcett, T., 2006. An introduction to ROC analysis. Pattern Recogn. Lett. 27, 861
damaged prediction accuracies. 874.
Fu, X., Ying, Y., Lu, H., Xu, H., 2007. Comparison of diffuse reflectance and
transmission mode of visible-near infrared spectroscopy for detecting brown
heart of pear. J. Food Eng. 83, 317323.
4. Conclusion Gama, J., 2004. Functional trees. Mach. Learn. 55, 219250.
Gomez-Sanchis, J., Lorente, D., Soria-Olivas, E., Aleixos, N., Cubero, S., Blasco, J., 2014.
In conclusion, hyperspectral transmittance spectra were identi- Development of a hyperspectral computer vision system based on two liquid
crystal tuneable filters for fruit inspection. Application to detect citrus fruits
fied to be more sensitive to blueberry mechanical damage than decay. Food Bioprocess Technol. 7, 10471056.
reflectance and interactance. Classifiers based on CARS selected Gou, P., Santos-Garcs, E., Hy, M., Wold, J., Liland, K., Fulladosa, E., 2013. Feasibility
transmittance showed superior performances in classifying sound of NIR interactance hyperspectral imaging for on-line measurement of crude
composition in vacuum packed dry-cured ham slices. Meat Sci. 95, 250255.
and damaged blueberries according to the relatively high classifi- Hillmann, U., Schimmack, W., Jacob, P., Bunzl, K., 1996. In situ c-spectrometry
cation accuracies and AUC values. In impact damage experiments, several years after deposition of radiocesium. Radiat. Environ. Biophys. 35, 297
the physical property preliminarily proved to be more pronounced 303.
Huang, M., Wan, X., Zhang, M., Zhu, Q., 2013. Detection of insect-damaged vegetable
than the absorbed impact energy for damage incidence and sever-
soybeans using hyperspectral transmittance image. J. Food Eng. 116, 4549.
ity of blueberry. In addition, established transmittance-based clas- Hu, M.H., Dong, Q.L., Liu, B.L., Opara, U.L., Chen, L., 2015. Estimating blueberry
sifiers were tested with new sample sets with time evolution, and mechanical properties based on random frog selected hyperspectral data.
results demonstrated that it was especially difficult to distinguish Postharvest Biol. Technol. 106, 110.
Hu, M.H., Dong, Q.L., Liu, B.L., Opara, U.L., 2016. Prediction of mechanical properties
damaged blueberries on the immediate measurement time. At of blueberry using hyperspectral interactance imaging. Postharvest Biol.
2 days after impacted, all transmittance classifiers obtained Technol. 115, 122131.
28 M.-H. Hu et al. / Computers and Electronics in Agriculture 122 (2016) 1928
Huang, W.Q., Li, J.B., Wang, Q.Y., Chen, L.P., 2015. Development of a multispectral Opara, U.L., Pathare, P.B., 2014. Bruise damage measurement and analysis of fresh
imaging system for online detection of bruises on apples. J. Food Eng. 146, 62 horticultural produce a review. Postharvest Biol. Technol. 91, 924.
71. Patel, K.K., Khan, M.A., Kar, A., 2015. Recent developments in applications of MRI
Jimnez-Jimnez, F., Castro-Garca, S., Blanco-Roldn, G.L., Agera-Vega, J., Gil- techniques for foods and agricultural producean overview. J. Food Sci.
Ribes, J.A., 2012. Non-destructive determination of impact bruising on table Technol. 52, 126.
olives using VisNIR spectroscopy. Biosyst. Eng. 113, 371378. Pu, Y.-Y., Feng, Y.-Z., Sun, D.-W., 2015. Recent progress of hyperspectral imaging on
Jimenez-Jimenez, F., Castro-Garcia, S., Blanco-Roldan, G.L., Gonzalez-Sanchez, E.J., quality and safety inspection of fruits and vegetables: a review. Compr. Rev.
Gil-Ribes, J.A., 2013. Isolation of table olive damage causes and bruise time Food Sci. Food Safety 00, 113.
evolution during fruit detachment with trunk shaker. Span. J. Agric. Res. 11, 65 Retamales, J., 2012. Blueberries. Crop Production Science in Horticulture 21. CABI.
71. Rivera, N.V., Gomez-Sanchis, J., Chanona-Perez, J., Carrasco, J.J., Millan-Giralolo, M.,
Keerthi, S.S., Shevade, S.K., Bhattacharyya, C., Murthy, K.R.K., 2001. Improvements to Lorente, D., Cubero, S., Blasco, J., 2014. Early detection of mechanical damage in
Platts SMO algorithm for SVM classifier design. Neural Comput. 13, 637649. mango using NIR hyperspectral images and machine learning. Biosyst. Eng. 122,
Knee, M., 2002. Fruit Quality and its Biological Basis. CRC Press. 9198.
Landwehr, N., Hall, M., Frank, E., 2005. Logistic model trees. Mach. Learn. 59, 161 Shen, X., Sun, X., Xie, Q., Liu, H., Zhao, Y., Pan, Y., Hwang, C.-A., Wu, V.C.H., 2014.
205. Antimicrobial effect of blueberry (Vaccinium corymbosum L.) extracts against
Li, H., Liang, Y., Xu, Q., Cao, D., 2009. Key wavelengths screening using competitive the growth of Listeria monocytogenes and Salmonella Enteritidis. Food Control
adaptive reweighted sampling method for multivariate calibration. Anal. Chim. 35, 159165.
Acta 648, 7784. Siedliska, A., Baranowski, P., Mazurek, W., 2014. Classification models of bruise and
Lee, H., Kim, M.S., Jeong, D., Delwiche, S.R., Chao, K., Cho, B.K., 2014. Detection of cultivar detection on the basis of hyperspectral imaging data. Comput. Electron.
cracks on tomatoes using a hyperspectral near-infrared reflectance imaging Agric. 106, 6674.
system. Sensors 14, 1883718850. Sivertsen, A.H., Heia, K., Hindberg, K., Godtliebsen, F., 2012. Automatic nematode
Lee, W.-H., Kim, M.S., Lee, H., Delwiche, S.R., Bae, H., Kim, D.-Y., Cho, B.-K., 2014. detection in cod fillets (Gadus morhua L.) by hyperspectral imaging. J. Food Eng.
Hyperspectral near-infrared imaging for the detection of physical damages of 111, 675681.
pear. J. Food Eng. 130, 17. Van Zeebroeck, M., Van linden, V., Ramon, H., De Baerdemaeker, J., Nicolai, B.M.,
Leiva-Valenzuela, G.A., Aguilera, J.M., 2013. Automatic detection of orientation and Tijskens, E., 2007. Impact damage of apples during transport and handling.
diseases in blueberries using image analysis to improve their postharvest Postharvest Biol. Technol. 45, 157167.
storage quality. Food Control 33, 166173. Wang, H., Li, C., Wang, M., 2013. Quantitative determination of onion internal
Leiva-Valenzuela, G.A., Lu, R., Aguilera, J.M., 2014. Assessment of internal quality of quality using reflectance, interactance, and transmittance modes of
blueberries using hyperspectral transmittance and reflectance images with hyperspectral imaging. Trans. ASABE 56, 16231635.
whole spectra or selected wavelengths. Innov. Food Sci. Emerg. Technol. 24, 2 Wu, D., Sun, D.-W., 2013. Advanced applications of hyperspectral imaging
13. technology for food quality and safety analysis and assessment: a review
Li, C., Krewer, G.W., Ji, P., Scherm, H., Kays, S.J., 2010. Gas sensor array for blueberry Part I: fundamentals. Innov. Food Sci. Emerg. Technol. 19, 114.
fruit disease detection and classification. Postharvest Biol. Technol. 55, 144 Wu, G.F., Wang, C.G., 2014. Investigating the effects of simulated transport vibration
149. on tomato tissue damage based on vis/NIR spectroscopy. Postharvest Biol.
Li, H., Lee, W.S., Wang, K., 2014. Identifying blueberry fruit of different growth Technol. 98, 4147.
stages using natural outdoor color images. Comput. Electron. Agric. 106, 91 Xing, J., Bravo, C., Jancsk, P.T., Ramon, H., De Baerdemaeker, J., 2005. Detecting
101. bruises on Golden Delicious apples using hyperspectral imaging with multiple
Li, Z., Thomas, C., 2014. Quantitative evaluation of mechanical damage to fresh wavebands. Biosyst. Eng. 90, 2736.
fruits. Trends Food Sci. Technol. 35, 138150. Xing, J., Guyer, D., 2008. Detecting internal insect infestation in tart cherry using
Lu, R., Peng, Y., 2006. Hyperspectral scattering for assessing peach fruit firmness. transmittance spectroscopy. Postharvest Biol. Technol. 49, 411416.
Biosyst. Eng. 93, 161171. Yang, C., Lee, W.S., Gader, P., 2014. Hyperspectral band selection for detecting
Ma, Y., Huang, M., Yang, B., Zhu, Q., 2014. Automatic threshold method and optimal different blueberry fruit maturity stages. Comput. Electron. Agric. 109, 2331.
wavelength selection for insect-damaged vegetable soybean detection using Yu, K.Q., Zhao, Y.R., Li, X.L., Shao, Y.N., Zhu, F.L., He, Y., 2014. Identification of crack
hyperspectral images. Comput. Electron. Agric. 106, 102110. features in fresh jujube using Vis/NIR hyperspectral imaging combined with
Manley, M., 2014. Near-infrared spectroscopy and hyperspectral imaging: non- image processing. Comput. Electron. Agric. 103, 110.
destructive analysis of biological materials. Chem. Soc. Rev. 43, 82008214. Yu, P., Li, C., Takeda, F., Krewer, G., 2014a. Visual bruise assessment and analysis of
Martinsen, P., Oliver, R., Seelye, R., McGlone, V.A., Holmes, T., Davy, M., Johnston, J., mechanical impact measurement in southern highbush blueberries. Appl. Eng.
Hallett, I., Moynihan, K., 2014. Quantifying the diffuse reflectance change Agric. 30, 2937.
caused by fresh bruises on apples. Trans. ASABE 57, 565572. Yu, P., Li, C., Takeda, F., Krewer, G., Rains, G., Hamrita, T., 2014b. Measurement of
Mazhar, M., Joyce, D., Cowin, G., Brereton, I., Hofman, P., Collins, R., Gupta, M., 2015. mechanical impacts created by rotary, slapper, and sway blueberry mechanical
Non-destructive 1H-MRI assessment of flesh bruising in avocado (Persea harvesters. Comput. Electron. Agric. 101, 8492.
americana M.) cv. Hass. Postharvest Biol. Technol. 100, 3340. Zhang, B.H., Huang, W.Q., Gong, L., Li, J.B., Zhao, C.J., Liu, C.L., Huang, D.F., 2015.
Mehra, L., MacLean, D., Savelle, A., Scherm, H., 2013. Postharvest disease Computer vision detection of defective apples using automatic lightness
development on southern highbush blueberry fruit in relation to berry flesh correction and weighted RVM classifier. J. Food Eng. 146, 143151.
type and harvest method. Plant Dis. 97, 213221. Zhang, H., Su, J., 2006. Learning probabilistic decision trees for AUC. Pattern Recogn.
Mollazade, K., Omid, M., Tab, F.A., Mohtasebi, S.S., 2012. Principles and applications Lett. 27, 892899.
of light backscattering imaging in quality evaluation of agro-food products: a Zhou, R., Su, S., Yan, L., Li, Y., 2007. Effect of transport vibration levels on mechanical
review. Food Bioprocess Technol. 5, 14651485. damage and physiological responses of Huanghua pears (Pyrus pyrifolia Nakai,
Nicola, B.M., Beullens, K., Bobelyn, E., Peirs, A., Saeys, W., Theron, K.I., Lammertyn, J., cv. Huanghua). Postharvest Biol. Technol. 46, 2028.
2007. Nondestructive measurement of fruit and vegetable quality by means of
NIR spectroscopy: a review. Postharvest Biol. Technol. 46, 99118.