Abstract
Bruise is a typical kind of fruit damage that often occurred during fruit harvesting, packaging, transportation, processing, and storage. The detection of fruit bruise, especially for early detection, has received extensive attentions of global interest. In this study, fluorescence hyperspectral imaging technique was used to detect surface bruise of pears. After data preprocessing and feature extraction, machine learning methods of support vector machine and random forest were used for qualitative modeling to distinguish sample bruise levels (sound, minor, severe) and bruised time (immediate, 15 min, 24 h, 48 h, 72 h). Cross-validation, genetic algorithm, particle swarm optimization, and network search algorithms were used and compared for SVM model optimization. The results showed that different bruise levels can be identified 15 min later after bruised, with an accuracy of 93.33%. And the accuracy was as high as 99.33% when discriminating all samples into sound and bruised. It can be concluded that fluorescence hyperspectral imaging has certain feasibility in the early bruise detection of fruits. In the future, studies can be conducted to enhance the fluorescence signal intensity and reduce detection time.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Berk Z (2016) Citrus fruit processing. e-Book, Elsevier Academic Press. https://doi.org/10.1016/c2014-0-03617-9
Bron IU, Ribeiro RV, Azzolini M, Jacomino AP, Machadoc EC (2004) Chlorophyll fluorescence as a tool to evaluate the ripening of ‘Golden’ papaya fruit. Postharvest Biol Technol 33(2):163–173. https://doi.org/10.1016/j.postharvbio.2004.02.004
Celik HK (2017) Determination of bruise susceptibility of pears (Ankara variety) to impact load by means of FEM-based explicit dynamics simulation. Postharvest Biol Technol 128:83–97. https://doi.org/10.1016/j.postharvbio.2017.01.015
Chiu Y, Chou X, Grift TE, Chen MT (2015) Automated detection of mechanically induced bruise areas in golden delicious apples using fluorescence imagery. Trans ASABE 58:215–225. https://doi.org/10.13031/trans.58.10578
Cho BK, Kim MS, Baek IS, Kim DY, Lee WH, Kim JK, Bae HH, Kim YS (2013) Detection of cuticle defects on cherry tomatoes using hyperspectral fluorescence imagery. Postharvest Biol Technol 76:40–49. https://doi.org/10.1016/j.postharvbio.2012.09.002
Du D, Wang B, Wang J, Yao F, Hong X (2019) Prediction of bruise susceptibility of harvested kiwifruit (Actinidia chinensis) using finite element method. Postharvest Biol Technol 152:36–44. https://doi.org/10.1016/j.postharvbio.2019.02.013
Gao F, Dong YJ, Xiao WM, Bin Y, Yan CS, He SL (2016) LED induced fluorescence spectroscopy technique for apple freshness and quality detection. Postharvest Biol Technol 119:27–32. https://doi.org/10.1016/j.postharvbio.2016.04.020
Gu Q, Sheng L, Zhang TH, Lu YW, Zhang ZJ, Zheng KF, Hu H, Zhou HK (2019) Early detection of tomato spotted wilt virus infection in tobacco using the hyperspectral imaging technique and machine learning algorithms. Comput Electron Agric 167:105066. https://doi.org/10.1016/j.compag.2019.105066
Jiang H, Zhang C, He Y, Chen XX, Liu F, Liu YD (2016) Wavelength selection for detection of slight bruises on pears based on hyperspectral imaging. Appl Sci-BASEL 6(12):450. https://doi.org/10.3390/app6120450
Laguna L, Casado GC, Heredia H (1999) Flavonoid biosynthesis in tomato fruit cuticles after in vivo incorporation of H-phenylalanine precursor. Physiol Plant 105(3):491–498. https://doi.org/10.1034/j.1399-3054.1999.105314.x
Li JB, Luo W, Wang ZL, Fan SX (2019) Early detection of decay on apples using hyperspectral reflectance imaging combining both principal component analysis and improved watershed segmentation method. Postharvest Biol Technol 149:235–246. https://doi.org/10.1016/j.postharvbio.2018.12.007
Liu Q, Zhou DS, Tu SY, Xiao H, Tu K (2020) Quantitative visualization of fungal contamination in peach fruit using hyperspectral imaging. Food Anal Meth 13(6):1262–1270. https://doi.org/10.1007/s12161-020-01747-x
Lu YZ, Li R, Lu RF (2016) Fast demodulation of pattern images by spiral phase transform in structured-illumination reflectance imaging for detection of bruises in apples. Comput Electron Agric 127:652–658. https://doi.org/10.1016/j.compag.2016.07.012
Lu YZ, Lu RF (2020) Enhancing chlorophyll fluorescence imaging under structured illumination with automatic vignetting correction for detection of chilling injury in cucumbers. Comput Electron Agric 168:105145. https://doi.org/10.1016/j.compag.2019.105145
Luo W, Zhang HL, Liu XM (2019) Hyperspectral/Multispectral reflectance imaging combining with watershed segmentation algorithm for detection of early bruises on apples with different peel colors. Food Anal Meth 12(5):1218–1228. https://doi.org/10.1007/s12161-019-01456-0
Shevade SK, Keerthi SS, Bhattacharyya C (2000) Improvements to the SMO algorithm for SVM regression. IEEE Trans Neural Netw Learn Syst 11(5):1188–1193. https://doi.org/10.1109/72.870050
Siregar TH, Ahmad U, Sutrisno MA (2017) Mechanical damage detection of Indonesia local citrus based on fluorescence imaging. IOP Conf Ser: Earth Environ Sci 147:012006. https://doi.org/10.1088/1755-1315/147/1/012006
Tian Y, Sun J, Zhou X, Wu XH, Lu B, Dai CX (2020) Research on apple origin classification based on variable iterative space shrinkage approach with stepwise regression-support vector machine algorithm and visible-near infrared hyperspectral imaging. J Food Process Eng 43(8):e13432. https://doi.org/10.1111/jfpe.13432
Ullah R, Khan S, Bilal M, Nurjis F, Saleem M (2016) Non-invasive assessment of mango ripening using fluorescence spectroscopy. Optik 127(13):5186–5189. https://doi.org/10.1016/j.ijleo.2016.03.049
Vega F, Torres MC (2013) Automatic detection of bruises in fruit using Biospeckle techniques. Symposium of Signals, Images and Artificial Vision - 2013: STSIVA - 2013 https://doi.org/10.1109/stsiva.2013.6644916
Vinay Kumar BN, Löschel LA, Imhof HK, Löder MG, Laforsch C (2021) Analysis of microplastics of a broad size range in commercially important mussels by combining FTIR and Raman spectroscopy approaches. Environ Pollut 269:116147. https://doi.org/10.1016/j.envpol.2020.116147
Yan L, Liu JX, Men S (2017) The biospeckle method for early damage detection of fruits. Mod Phys Lett B 31(19–21):1740034. https://doi.org/10.1142/s0217984917400346
Zhang MY, Jiang Y, Li CY, Yang FZ (2020) Fully convolutional networks for blueberry bruising and calyx segmentation using hyperspectral transmittance imaging. Biosyst Eng 192:159–175. https://doi.org/10.1016/j.biosystemseng.2020.01.018
Zhu XL, Li GH (2019) Rapid detection and visualization of slight bruise on apples using hyperspectral imaging. Int J Food Prop 22(1):1709–1719. https://doi.org/10.1080/10942912.2019.1669638
Funding
This work was supported by the National Natural Science Fund of China (32071904), the Natural Science Fund of Zhejiang Province (LY20C130008), and the Science Foundation of Zhejiang Sci-Tech Univ. (ZSTU) (Grant No. 16022177-Y).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethical Approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Informed Consent
Not applicable in this study.
Conflict of Interest
Xiaping Fu declares that she has no conflict of interest. Mengyao Wang declares that he has no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Fu, X., Wang, M. Detection of Early Bruises on Pears Using Fluorescence Hyperspectral Imaging Technique. Food Anal. Methods 15, 115–123 (2022). https://doi.org/10.1007/s12161-021-02092-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12161-021-02092-3