Apple Bruise Grading Using Piecewise Nonlinear Curve Fitting for Hyperspectral Imaging Data

Apple fruits can be easily damaged, and bruises occur on peels during harvest, transportation and storage, which could decrease fruit quality. This paper proposed an apple bruise grading method based on hyperspectral imaging (HSI). The spectral information of sound apples (Yantai Fuji 8) was first captured using a hyperspectral reflectance imaging device (386-1016 nm). These apples were then mechanically damaged by the same impact forces, and the bruised regions were exposed to room temperature for at most 120 min. The spectral data of the bruised apples at four different exposure times (30 min, 60 min, 90 min and 120 min) were obtained. The spectral data were preprocessed using Procrustes analysis (PA) to enable a more diverse distribution of the spectra among different patterns. To both accurately maintain the spectral information of different patterns and reduce the dimensions of the spectra, piecewise nonlinear curve fitting (PWCF) was presented using the least squares algorithm, where the resultant fitting coefficients from different spectral intervals were catenated into a low-dimension feature descriptor. The feature descriptors were then fed to an error-correction output coding-based support vector machine (ECOC-SVM) to grade the bruised apples. To further evaluate the performance of the presented PWCF, conventional algorithms, including the successive projections algorithm (SPA), genetic algorithm (GA), principal component analysis (PCA) and kernel principal component analysis (KPCA), were introduced for comparison. Experimental results showed that the proposed method obtained the best grading accuracy (97.33%) compared to the other methods.

[1]  Weikang Gu,et al.  Computer vision based system for apple surface defect detection , 2002 .

[2]  A. Beyaz.  Harvest glove and LabView based mechanical damage determination on apples , 2018 .

[3]  Zhenyu Zhong,et al.  Assessment of External Properties for Identifying Banana Fruit Maturity Stages Using Optical Imaging Techniques , 2019, Sensors.

[4]  Daniel E. Guyer,et al.  Near-infrared hyperspectral reflectance imaging for detection of bruises on pickling cucumbers , 2006, Computers and Electronics in Agriculture.

[5]  Laijun Sun,et al.  Non-destructive classification of defective potatoes based on hyperspectral imaging and support vector machine , 2019, Infrared Physics & Technology.

[6]  Udantha R. Abeyratne,et al.  Ultrasonic technique for non-destructive quality evaluation of oranges , 2014 .

[7]  E. Mehinagic,et al.  Importance of fruit variability in the assessment of apple quality by sensory evaluation , 2013 .

[8]  Lembe S. Magwaza,et al.  A Review of Destructive and Non-destructive Methods for Determining Avocado Fruit Maturity , 2015, Food and Bioprocess Technology.

[9]  Fengchen Huang,et al.  Hyperspectral Imaging Target Detection Based on Improved Kernel Principal Component Analysis , 2012, Intell. Autom. Soft Comput..

[10]  Bankim Patel,et al.  Machine Vision based Fruit Classification and Grading - A Review , 2017 .

[11]  Dattatraya Londhe,et al.  Grader: A review of different methods of grading for fruits and vegetables , 2013 .

[12]  M. M. Pawar,et al.  Skin defect detection of pomegranates using color texture features and DWT , 2012, 2012 NATIONAL CONFERENCE ON COMPUTING AND COMMUNICATION SYSTEMS.

[13]  Cheng-Chien Kuo,et al.  Modified particle swarm optimization algorithm with simulated annealing behavior and its numerical verification , 2011, Appl. Math. Comput..

[14]  Mousa Shamsi,et al.  Using Statistical Histogram Based EM Algorithm for Apple Defect Detection , 2012 .

[15]  Baohua Zhang,et al.  Detection of Early Rottenness on Apples by Using Hyperspectral Imaging Combined with Spectral Analysis and Image Processing , 2015, Food Analytical Methods.

[16]  Ming Yang,et al.  An Intelligent Model Validation Method Based on ECOC SVM , 2018, ICCMS.

[17]  Thomas G. Dietterich,et al.  Solving Multiclass Learning Problems via Error-Correcting Output Codes , 1994, J. Artif. Intell. Res..

[18]  Ning Wang,et al.  Early detection of apple bruises on different background colors using hyperspectral imaging , 2008 .

[19]  Diane M. Barrett,et al.  Color, Flavor, Texture, and Nutritional Quality of Fresh-Cut Fruits and Vegetables: Desirable Levels, Instrumental and Sensory Measurement, and the Effects of Processing , 2010, Critical reviews in food science and nutrition.

[20]  Laijun Sun,et al.  Non-destructive classification of apple bruising time based on visible and near-infrared hyperspectral imaging. , 2018, Journal of the science of food and agriculture.

[21]  P. Baranowski,et al.  Supervised classification of bruised apples with respect to the time after bruising on the basis of hyperspectral imaging data , 2013 .

[22]  Wenyi Tan,et al.  Study on bruising degree classification of apples using hyperspectral imaging and GS-SVM , 2018 .

[23]  Yuzhen Lu,et al.  Histogram-based automatic thresholding for bruise detection of apples by structured-illumination reflectance imaging , 2017 .

[24]  Danilo Monarca,et al.  Feasibility of NIR spectroscopy to detect olive fruit infested by Bactrocera oleae , 2015 .

[25]  Josse De Baerdemaeker,et al.  Bruise detection on Jonagold apples by visible and near-infrared spectroscopy , 2004 .

[26]  Chandra B. Singh,et al.  Potential of Near-Infrared (NIR) Spectroscopy and Hyperspectral Imaging for Quality and Safety Assessment of Fruits: an Overview , 2019, Food Analytical Methods.

[27]  C. Goodall.  Procrustes methods in the statistical analysis of shape , 1991 .

[28]  Mingjie Tang,et al.  Detection of Hidden Bruise on Kiwi fruit Using Hyperspectral Imaging and Parallelepiped Classification , 2012 .

[29]  Ruoyu Zhang,et al.  Detection of early decayed oranges based on multispectral principal component image combining both bi-dimensional empirical mode decomposition and watershed segmentation method , 2019 .

[30]  Peter Goos,et al.  Glare based apple sorting and iterative algorithm for bruise region detection using shortwave infrared hyperspectral imaging , 2017 .

[31]  A. Gitelson,et al.  Reflectance spectral features and non-destructive estimation of chlorophyll, carotenoid and anthocyanin content in apple fruit , 2003 .

[32]  K. Tu,et al.  Near-Infrared Hyperspectral Imaging Rapidly Detects the Decay of Postharvest Strawberry Based on Water-Soluble Sugar Analysis , 2019, Food Analytical Methods.

[33]  Yong He,et al.  [Detection of Hawthorn Fruit Defects Using Hyperspectral Imaging]. , 2015, Guang pu xue yu guang pu fen xi = Guang pu.

[34]  Yong He,et al.  Hyperspectral Image-Based Variety Classification of Waxy Maize Seeds by the t-SNE Model and Procrustes Analysis , 2018, Sensors.

[35]  Veerle Van linden,et al.  Impact damage of apples during transport and handling , 2007 .

[36]  Baihai Zhang,et al.  Identifying Apple Surface Defects Based on Gabor Features and SVM Using Machine Vision , 2011, CCTA.

[37]  Yang Tao,et al.  Gabor feature-based apple quality inspection using kernel principal component analysis , 2007 .

[38]  Bayram Cetisli,et al.  Design of an automatic apple sorting system using machine vision , 2016, Comput. Electron. Agric..

[39]  Morteza Sadeghi,et al.  The effect of impact and fruit properties on the bruising of peach , 2010 .

[40]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.