Abstract
In this paper, different steps involved in harvesting and postharvest handling of mangoes are detailed and the possibilities of exploring Artificial Intelligence based solutions for each step are highlighted. A schematic diagram of overall post-harvesting is given. Various suitable methods of classical machine learning such as feature extraction methods, feature reduction methods, and classifiers are presented. Problems of classifying mangoes into mature, non- mature and matured class further into ripened and under-ripened are addressed with a proposal of machine learning approaches. Nevertheless, a hierarchical multi-classifiers fusion approach is designed for classification of ripened mangoes into perfect ripened, over ripened, over ripened with black spots on skin and without black spots on skin. Moreover, method of selecting the best wavelengths of NIR spectroscopy towards proposal of non-destructive method of finding internal defects in mangoes is also introduced. In addition, the most difficult issue of classifying ripened mangoes into naturally ripened and artificially ripened mangoes is also attempted, and a suitable classifier is presented. For each problem being addressed using classical machine learning methods, the corresponding counterparts from deep learning architectures are also highlighted. Results of extensive experimentation conducted to demonstrate the success of our approaches are presented on reasonably sized datasets of mango images created during the course of our research. A description on datasets along with difficulties faced while creating datasets are detailed. A comparative study on different approaches including deep learning based approaches is presented. Scope for future research in the similar directions is also explored. Overall, this paper is an attempt towards an integrated solution for postharvest handling of mangoes especially for automation of sorting and grading processes.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Raghavendra, A., Guru, D.S., Rao, M.K.: An automatic predictive model for sorting of artificially and naturally ripened mangoes. In: Bhateja, V., Peng, S.-L., Satapathy, S.C., Zhang, Y.-D. (eds.) Evolution in Computational Intelligence. AISC, vol. 1176, pp. 633–646. Springer, Singapore (2021). https://doi.org/10.1007/978-981-15-5788-0_60
Raghavendra, A., Guru, D.S., Rao, M.K.: Hierarchical approach for ripeness grading of mangoes. Artif. Intell. Agric. 4, 243–252 (2020). https://doi.org/10.1016/j.aiia.2020.10.003
Raghavendra, A., Guru, D.S., Rao, M.K.: Mango internal defect detection based on optimal wavelength selection method using NIR spectroscopy. Artif. Intell. Agric. 5, 43–51 (2021). https://doi.org/10.1016/j.aiia.2021.01.005
Raghavendra, A.: Machine learning approaches for quality evaluation of mangoes. Ph. D Dissertation, Electronics, University of Mysore, Karnataka. Accessed 18 Aug 2021
Nicolaï, B.M., Beullens, K., Bobelyn, E., Peirs, A., Saeys, W., Theron, K.I., Lammertyn, J.: Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy: a review. Postharvest Biol. Technol. 46(2), 99–118 (2007). https://doi.org/10.1016/j.postharvbio.2007.06.024
Nandi, C.S., Tudu, B., Koley, C.: Machine vision based techniques for automatic mango fruit sorting and grading based on maturity level and size. In: Mason, A., Mukhopadhyay, S.C., Jayasundera, K.P., Bhattacharyya, N. (eds.) Sensing Technology: Current Status and Future Trends II. SSMI, vol. 8, pp. 27–46. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-02315-1_2
Chhabra, M., Gaur, R., Reel, P.S.: Detection of fully and partially RIPED mango by machine vision. ICRTITCS Proceedings Published in IJCA 5, 25–31 (2012)
Duda, R.O., Hart, P.E., Stork. D.G.: Pattern Classification. A Wiley-Interscience Publication John Wiley & Sons, Inc. (2012)
Rezende, E., Ruppert, G., Carvalho, T., Ramos, F., de Geus, P.: Malicious software classification using transfer learning of ResNet-50 deep neural network. In: 16th IEEE International Conference on Machine Learning and Applications. 0-7695-6321-X/17/31.00 (2017)
Effect of ethrel spray on the ripening behaviour of mango (Mangiferaindica L.) variety ‘Dashehari’. J. Appl. Nat. Sci.
Saldana, E., Siche, R., Lujan, M., Quevedo, R.: Computers and electronics in postharvest technology - a review. Baz. J. Food Technol. 30(1–3), 109–124 (2001)
Goovaerts, P.: Estimation or simulation of soil properties? an optimization problem with conflicting criteria. Geoderma 3, 165–186 (2000)
https://www.mid-day.com/articles/cac2-may-cause-cancer-blindness-seizures/15346168
Inter Institutional Inclusive Innovations Centre. www.i4c.co.in/idea/getIdeaProfile/idea_id/2969
Nutritional Talk. https://nwg-works.blogspot.in/2013/04/how-to-identify-banana-ripened-using.html
LiveChennai.com. http://www.livechennai.com/healthnews.asp?newsid=10973
Kamilaris, A., Prenafeta-Boldú, F.X.: Deep learning in agriculture: a survey. Comput. Electron. Agric. (2018). https://doi.org/10.1016/j.compag.2018.02.016
Khoje, A.S., Bodhe, S.K.: Comparative performance evaluation of fast discrete curvelet transform and colour texture moments as texture features for fruit skin damage detection” Springer. J. Food Sci. Technol. (2015). https://doi.org/10.1007/s13197-015-1794-3
Khoje, A.S., Bodhe, S.K.: Application of colour texture moments to detect external skin damages in guavas (Psidium guajava L). World Appl. Sci. J. 27(5), 590–596 (2013)
Khoje, S., Bodhe, S.: Performance comparison of Fourier transform and its derivatives as shape descriptors for mango grading. Int. J. Comput. Appl. 53(3), 17–22 (2012)
Khoje, S., Bodhe, S.: Comparative performance evaluation of size metrics and classifiers in computer vision based automatic mango grading. Int. J. Comput. Appl. 61(9), 1–7 (2013)
LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time series. The Handbook of Brain Theory and Neural Networks, 3361(10) (1995)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature, Intell. Control Autom. 7(4), 521(7553), 436–444. LiveChennai.com http://www.livechennai.com/healthnews.asp?newsid=10973 (2015)
Mansor, A.R., et al.: Fuzzy ripening mango index using RGB color sensor model. Res. World-J. Arts Sci. Commer. 5(2) (2014). E-ISSN2229-4686 ISSN2231-4172
Moureen, A., Rao, M., Raghavendra, A.: An image segmentation comparison approach for lesion detection and area calculation in mangoes. Int. Res. J. Eng. Technol. (IRJET). 2(5) (2015)
Musale, S.S., Patil, P.M.: Identification of defective mangoes using Gabor wavelets: A non-destructive technique based on texture analysis. Int. J. Agric. Innov. Res. 2(6) (2014). ISSN 2319-1473
Nanna, K., et al.: Detecting mango fruits by using randomized Hough transform and backpropagation neural network. In: IEEE Conference (2014). https://doi.org/10.1109/IV.2014.54
Pauly, L., Sankar, D.: A New method for sorting and grading of mangoes based on computer vision system. IEEE Conf. (2015). https://doi.org/10.1109/IADCC.2015.715489
Rivea, N.V., Perez, J.J.C.: Description of maturity stages of mango ‘Manila’ by image analysis and ripening index
Roomi, M.M., et al.: Classification of mangoes by object features and contour modeling. IEEE (2012). https://doi.org/10.1109/MVIP.2012.6428786
Salunkhe, R.P., Patil, A.A.: Image processing for Mango ripening stage detection: RGB and HSV method. IEEE Conf. (2015). https://doi.org/10.1109/ICIIP.2015.7414796
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Ray, S.: Disease classification within dermascopic images using features extracted by ResNet50 and classification through deep forest. Comput. Vis. Pattern Recogn. (2018). arXiv:1807.05711
Ashok, V., Vinod, D.S.: Using K-means cluster and fuzzy C means for defect segmentation in fruits. Int. J. Comput. Eng. Technol. (2014)
MVyas, A., Talati, B., Naik, S.: Quality inspection and classification of mangoes using color and size features. Int. J. Comput. Appl. 98(1), 1–5 (2014)
Zheng, W., Zhao, L., Zou, C.: Locally nearest neighbor classifiers for pattern classification. Pattern Regonit. 37(6), 1307–1309 (2004)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Guru, D.S., Raghavendra, A., Rao, M.K. (2022). Post-harvest Handling of Mangoes: An Integrated Solution Using Machine Learning Approach. In: Raman, B., Murala, S., Chowdhury, A., Dhall, A., Goyal, P. (eds) Computer Vision and Image Processing. CVIP 2021. Communications in Computer and Information Science, vol 1568. Springer, Cham. https://doi.org/10.1007/978-3-031-11349-9_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-11349-9_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-11348-2
Online ISBN: 978-3-031-11349-9
eBook Packages: Computer ScienceComputer Science (R0)