SeeFruits: Design and evaluation of a cloud-based ultra-portable NIRS system for sweet cherry quality detection

Abstract Recent researches have shown that spectroscopy is a valid non-destructive technique for fruit quality detection. Yet the high cost, large volume, and complicated operation of the traditional spectral system makes it hard to be adapted to real field applications. In this paper, a low-cost, cloud-based portable Near Infrared (NIR) system called ‘SeeFruits’ was designed for fruit quality detection. The system was developed based on two integrated modules, DLP® NIRscan Nano EVM and ESP12-F. Main structures of hardware and software as well as the operation and workflow of the system were described in detail. A total of 240 sweet cherries were chosen as our fruit samples in order to evaluate the performance of ‘SeeFruits’. By targeting maturity level as a qualitative index and total soluble solids content as a quantitative index, we compared the results between ‘SeeFruits’ and a benchtop NIR-hyperspectral imaging system. The ‘SeeFruits’ system achieved F1-score of 0.89 on qualitative task and R 2 of 0.83 on quantitative task. Overall, with the features of ultra-portability, cloud computing and Internet of things feasibility, ‘SeeFruits’ can provide a fast, flexible and friendly application for sweet cherry quality detection to nonprofessionals with satisfactory accuracy.

[1]  Marcus Nagle,et al.  Robust NIRS models for non-destructive prediction of postharvest fruit ripeness and quality in mango , 2016 .

[2]  A. Peirs,et al.  Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy: A review , 2007 .

[3]  L. Buydens,et al.  Facilitating the application of Support Vector Regression by using a universal Pearson VII function based kernel , 2006 .

[4]  S. Jha,et al.  Non-destructive prediction of quality of intact apple using near infrared spectroscopy , 2010, Journal of food science and technology.

[5]  Chao Yang,et al.  Linear and nonlinear multivariate regressions for determination sugar content of intact Gannan navel orange by Vis-NIR diffuse reflectance spectroscopy , 2010, Math. Comput. Model..

[6]  Lazhar Khriji,et al.  Non-destructive measurement of total soluble solid (TSS) content of dates using near infrared (NIR) imaging - , 2014 .

[7]  Xiaoli Li,et al.  Hyperspectral Imaging for Determining Pigment Contents in Cucumber Leaves in Response to Angular Leaf Spot Disease , 2016, Scientific Reports.

[8]  Carlos H. Crisosto,et al.  Consumer acceptance of ‘Brooks’ and ‘Bing’ cherries is mainly dependent on fruit SSC and visual skin color , 2003 .

[9]  M. Di Matteo,et al.  Physicochemical and sensory fruit characteristics of two sweet cherry cultivars after cool storage , 2002 .

[10]  Alexander Scheeline,et al.  Teaching, Learning, and Using Spectroscopy with Commercial, Off-the-Shelf Technology , 2010, Applied spectroscopy.

[11]  Dolores Pérez-Marín,et al.  Internal and external quality assessment of mandarins on-tree and at harvest using a portable NIR spectrophotometer , 2013 .

[12]  Timo Mantere,et al.  A Review of Optical Nondestructive Visual and Near-Infrared Methods for Food Quality and Safety , 2013 .

[13]  L. Buydens,et al.  Comparing support vector machines to PLS for spectral regression applications , 2004 .

[14]  Jesús Hernán Camacho-Tamayo,et al.  Near-infrared (NIR) diffuse reflectance spectroscopy for the prediction of carbon and nitrogen in an Oxisol Espectroscopia de reflectancia difusa por infrarrojo cercano (NIR) para la predicción de carbono y nitrógeno de un Oxisol , 2014 .

[15]  Gamal ElMasry,et al.  Non-destructive prediction and visualization of chemical composition in lamb meat using NIR hyperspectral imaging and multivariate regression , 2012 .

[16]  B. B. P. Rao,et al.  Cloud computing for Internet of Things & sensing based applications , 2012, 2012 Sixth International Conference on Sensing Technology (ICST).

[17]  Ömür Dündar,et al.  Effect of preharvest gibberellic acid treatments on postharvest quality of sweet cherry , 2006 .

[18]  Paul J.R. Cronje,et al.  Evaluation of Fourier transform-NIR spectroscopy for integrated external and internal quality assessment of Valencia oranges , 2013 .

[19]  Lembe S. Magwaza,et al.  Non-destructive evaluation of avocado fruit maturity using near infrared spectroscopy and PLS regression models , 2016 .

[20]  Mitsuyoshi Horl,et al.  Application of Cloud Computing to Agriculture and Prospects in Other Fields , 2010 .

[21]  Sylvain Arlot,et al.  A survey of cross-validation procedures for model selection , 2009, 0907.4728.

[22]  Sylvie Bureau,et al.  Comparison of NIRS approach for prediction of internal quality traits in three fruit species. , 2014, Food chemistry.

[23]  E. Sabio,et al.  INFLUENCE OF STORAGE DELAY ON QUALITY OF VAN SWEET CHERRY , 2003 .

[24]  Roman M. Balabin,et al.  Comparison of linear and nonlinear calibration models based on near infrared (NIR) spectroscopy data for gasoline properties prediction , 2007 .

[25]  Ramesh Raskar,et al.  Ultra-portable, wireless smartphone spectrometer for rapid, non-destructive testing of fruit ripeness , 2016, Scientific Reports.

[26]  Daniel Valero,et al.  Postharvest sweet cherry quality and safety maintenance by Aloe vera treatment: A new edible coating , 2006 .

[27]  C. Hurburgh,et al.  Near-Infrared Reflectance Spectroscopy–Principal Components Regression Analyses of Soil Properties , 2001 .

[28]  Pramod K. Varshney,et al.  Logistic Regression for Feature Selection and Soft Classification of Remote Sensing Data , 2006, IEEE Geoscience and Remote Sensing Letters.

[29]  Mehdi Khojastehpour,et al.  Non-destructive evaluation of maturity and quality parameters of pomegranate fruit by visible/near infrared spectroscopy , 2017 .

[30]  Luis E. Rodriguez-Saona,et al.  Application of Portable and Handheld Infrared Spectrometers for Determination of Sucrose Levels in Infant Cereals , 2014, Food Analytical Methods.

[31]  Andrea Bellincontro,et al.  Portable NIR-AOTF spectroscopy combined with winery FTIR spectroscopy for an easy, rapid, in-field monitoring of Sangiovese grape quality. , 2014, Journal of the science of food and agriculture.

[32]  Lorenzo Bruzzone,et al.  Classification of hyperspectral remote sensing images with support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[33]  Jon Atli Benediktsson,et al.  SVM- and MRF-Based Method for Accurate Classification of Hyperspectral Images , 2010, IEEE Geoscience and Remote Sensing Letters.

[34]  Alessandro Torricelli,et al.  Nondestructive measurement of fruit and vegetable quality. , 2014, Annual review of food science and technology.

[35]  Gerrit Polder,et al.  Hyperspectral image analysis for measuring ripeness of tomatoes. , 2000 .

[36]  Liping Chen,et al.  Comparative analysis of models for robust and accurate evaluation of soluble solids content in ‘Pinggu’ peaches by hyperspectral imaging , 2017 .

[37]  Maria Fernanda Pimentel,et al.  Rapid and non-destructive determination of quality parameters in the 'Tommy Atkins' mango using a novel handheld near infrared spectrometer. , 2016, Food chemistry.

[38]  Daniel Valero,et al.  The use of natural antifungal compounds improves the beneficial effect of MAP in sweet cherry storage , 2005 .

[39]  A. E. Hoerl,et al.  Ridge regression: biased estimation for nonorthogonal problems , 2000 .