Deep Learning for Automatic Classification of Fruits and Vegetables: Evaluation from the Perspectives of Efficiency and Accuracy

Year 2024, Volume: 5 Issue: 2, 151 - 171, 28.10.2024

Demet Parlak Sönmez , Şafak Kılıç

https://doi.org/10.70562/tubid.1520357

Abstract

Within the agricultural domain, accurately categorizing the freshness levels of fruits and vegetables holds immense significance, as this classification enables early detection of spoilage and allows for appropriate grouping of products based on their intended export destinations. These processes necessitate a system capable of meticulously classifying fruits and vegetables while minimizing labor expenditures. The current study concentrates on developing an advanced model that can effectively categorize the freshness status of each fruit and vegetable as 'good,' 'medium,' or 'spoiled.' To achieve this objective, various artificial intelligence models, including CNN, AlexNet, ResNet50, GoogleNet, VGG16, and EfficientB3, have been implemented, attaining remarkable success rates of 99.75%, 97.97%, 96.71%, 99.49%, 98.75%, and 99.81%, respectively.

Keywords

CNN, AlexNet, ResNet50, GoogleNet, VGG16, EfficientB3.

Meyve ve Sebzelerin Otomatik Sınıflandırılması için Derin Öğrenme: Verimlilik ve Doğruluk Açısından Değerlendirme

Abstract

Tarım alanında, meyve ve sebzelerin tazelik seviyelerinin doğru bir şekilde kategorize edilmesi büyük önem taşımaktadır. Bu sınıflandırma, bozulmanın erken tespit edilmesini sağlar ve ürünlerin ihracat hedeflerine göre uygun şekilde gruplandırılmasına olanak tanır. Bu süreçler, meyve ve sebzeleri titizlikle sınıflandırabilen ve işgücü maliyetlerini en aza indirebilen bir sistem gerektirir. Mevcut çalışma, her bir meyve ve sebzenin tazelik durumunu 'iyi', 'orta' veya 'bozulmuş' olarak etkili bir şekilde kategorize edebilen gelişmiş bir modelin geliştirilmesine odaklanmaktadır. Bu amacı gerçekleştirmek için CNN, AlexNet, ResNet50, GoogleNet, VGG16 ve EfficientB3 dahil olmak üzere çeşitli yapay zeka modelleri uygulanmış ve sırasıyla %99.75, %97.97, %96.71, %99.49, %98.75 ve %99.81 gibi dikkat çekici başarı oranları elde edilmiştir.

Keywords

CNN, AlexNet, ResNet50, GoogleNet, VGG16, EfficientB3.

References

• 1. Ozdemir C, Dogan Y. Advancing brain tumor classification through MTAP model: an innovative approach in medical diagnostics. Medical & Biological Engineering & Computing 2024;.1(12): 2165–2176. Available from: https://doi.org/10.1007/s11517-024-03064-5
• 2. Ozdemir C, Dogan Y. Advancing early diagnosis of Alzheimer’s disease with next-generation deep learning methods. Biomedical Signal Processing and Control 2024; 96, 106614.3. Arens AA. Auditing in Australia : an integrated approach. 5th ed. Frenchs Forest: Pearson Education Australia; 2002.
• 3. Naranjo-Torres J, Mora M, Hernández-García R, Barrientos RJ, Fredes C, Valenzuela A. A review of Convolutional Neural Network applied to fruit image processing. Applied Science 2020.
• 4. Liu F, Snetkov L, Lima D. Summary on Fruit identification methods: a literature review. In: Proceedings of the 2017 3rd International Conference on Economics, Social Science, Arts, Education and Management Engineering (ESSAEME 2017). Atlantis Press, July 2017; Huhhot, China.
• 5. Sa I, Ge Z, Dayoub F, Upcroft B, Perez T, McCoo C. Deep Fruits: A fruit detection system using deep neural networks. Sensors 2016; 16(1222).
• 6. Sonwani E, Bansal U, Alroobaea R, Baqasah A.M, Hedabou M. An artificial intelligence approach toward food spoilage detection and analysis. Frontiers in Public Health 2021; 9.
• 7. Yuan Y, Chen X. Vegetable and fruit freshness detection based on deep features and principal component analysis. Current Research in Food Science 2024; 8. Available from: https://doi.org/10.1016/j.crfs.2023.100656
• 8. Abayomi-Alli O.O, Damaševičius R, Misra S, Abayomi-Alli A. FruitQ: a new dataset of multiple fruit images for freshness evaluation. 2023. Available from: https://doi.org/10.1007/s11042-023- 16058-6
• 9. Amin U, Shahzad M.I, Shahzad A, Shahzad M, Khan U, Mahmood Z. Automatic fruits freshness classification using CNN and transfer learning. Applied Sciences 2023; 13(8087). Available from: https://doi.org/10.3390/app13148087
• 10. Kumar T.B, Prashar D, Vaidya G, Kumar V, S. D. Kumar S.D, Sammy F. A novel model to detect and classify fresh and damaged fruits to reduce food waste using a deep learning technique. Hindawi Journal of Food Quality 2022. Available from: https://doi.org/10.1155/2022/4661108
• 11. Mukhiddinov M, Muminov A, Cho J. Improved classification approach for fruits and vegetables freshness based on deep learning. Sensors 2022. 22. Available from: https://doi.org/10.3390/s22218192
• 12. Kazi A, Panda S.P. Determining the freshness of fruits in the food industry by image classification using transfer learning. Multimedia Tools and Applications 2022. 81; p. 7611-7624. Available from: https://doi.org/10.1007/s11042-022-12150-5
• 13. Palakodati SSS, Chirra VRR, Dasari Y, Bulla S. Fresh and rotten fruits classification using CNN and transfer learning. Revue d'Intelligence Artificielle 2020. 34(5); p. 617-622. Available from: https://doi.org/10.18280/ria.340512
• 14. Valentino F, Cenggoro TW, Pardamean B. A design of deep learning experimentation for fruit freshness detection. IOP Conference Series: Earth and Environmental Science 2021. 794. doi= 10.1088/1755-1315/794/1/012110
• 15. Tanuia Nerella JNVD, Nippulapalli VK, Nancharla S, Vellanki LP, Suhasini PS. Performance comparison of deep learning techniques for classification of fruits as fresh and rotten. In: International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI), 2023. doi= 10.1109/RAEEUCCI57140.2023.10134242
• 16. Kukačka J, Golkov V, Cremers D. Regularization for deep learning: a taxonomy. ArXiv 2017. 1710.10686v1.
• 17. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 2014. 15.
• 18. Tompson J, Goroshin R, Jain A, LeCun Y, Bregler C. Efficient object localization using convolutional networks. ArXiv 2015. 1411.4280v3
• 19. Necmettin Ç. Derin öğrenme uygulamalarında başarım iyileştirme yöntemleri (Regularization). Linkedin 2017. Available from: https://www.linkedin.com/pulse/derin-%C3%B6%C4%9Frenme- uygulamlar%C4%B1nda-ba%C5%9Far%C4%B1m-iyile%C5%9Ftirme-necmettin- %C3%A7arkac%C4%B1/
• 20. Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv 2015. 1502.03167v3.
• 21. Zehra. Batch normalization. Medium 2021. Available from: https://zerzavot.medium.com/batch- normalization-b7d73c9cc6df
• 22. Weiss K, Khoshgoftaar TM, Wang D. A survey of transfer learning. Journal of Big Data 2016. (9). doi: 10.1186/s40537-016-0043-6.
• 23. Shao L, Zhu F, Li X. Transfer learning for visual categorization: a survey. IEEE Trans Neural Netw Learn Syst. 26(5), doi: 10.1109/TNNLS.2014.2330900
• 24. Deng J, Dong W, Socher R, Li-Jia Li, Li K, Fei-Fei L. ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), Miami, Florida, USA, 2009. doi: 10.1109/CVPR.2009.5206848
• 25. Zamir A, Sax A, Shen W, Guibas L, Malik J, Savarese S. Taskonomy: disentangling task transfer learning. arXiv 2018. 1804.08328v1.
• 26. Yosinski J, Clune J, Bengio Y, Lipson H. How transferable are features in deep neural networks?". ArXiv 2014, 1411.1792v1.
• 27. Yiğit G, Yeğin MN. Öğrenme aktarımı/transfer learning. Nova Research Lab. 2020. Available from: https://medium.com/novaresearchlab/%C3%B6%C4%9Frenme-aktar%C4%B1m%C4%B1- transfer-learning-c0b8126965c4
• 28. Erhan D, Bengio Y, Courville A, Manzagol P-A, Vincent P, Bengio S. Why does unsupervised pre- training help deep learning?. Journal of Machine Learning Research 2010. (11); p. 625—660.
• 29. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv 2014. 1409.1556v6.
• 30. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. arXiv 2015. 1512.03385v1, 2015.
• 31. Yılmaz AO. Data augmentation: veri artırma yöntemleri ve uygulamaları. Medium 2023. Available from: https://aoyilmaz.medium.com/data-augmentation-veri-art%C4%B1rma-y%C3%B6ntemleri- ve-uygulamalar%C4%B1-4dd33e12bf1d
• 32. Ozdemir C, Dogan Y, Kaya Y. RGB-Angle-Wheel: A new data augmentation method for deep learning models. Knowledge-Based Systems 2024. 291(111615).
• 33. Özden S. Confusion matrix (Karışıklık matrisi). Medium 2024. Available from: https://medium.com/@serapozden922/confusion-matrix kar%C4%B1%C5%9F%C4%B1kl%C4%B1k-matrisi- 62c43b8ad2b0#:~:text=Kar%C4%B1%C5%9F%C4%B1kl%C4%B1k%20matrisi%2C%20bir%20 modelin%20performans%C4%B1n%C4%B1,daha%20derin%20bir%20anlay%C4%B1%C5%9F% 20sa%C4%9Flar.
• 34. Horea M, Mihai O. Fruit recognition from images using deep learning. Acta Universitatis Sapientiae, Informatica 2018. 10(1).
• 35. Kılıç Ş, Askerzade İ, Kaya Y. Using ResNet transfer deep learning methods in person identification according to physical actions. IEEE 2020. 8. doi=10.1109/ACCESS.2020.3040649
• 36. Tüfekçi M, Karpat F. Derin öğrenme mimarilerinden konvolüsyonel sinir ağları (CNN) üzerinde görüntü işleme-sınıflandırma kabiliyetininin arttırılmasına yönelik yapılan çalışmaların incelenmesi. In: International Conference on Human-Computer Interaction. Optimization and Robotic Applications, 2019.
• 37. Joseph JL, Kumar VA, Mathew SP. Fruit classification using deep learning. Springer 2021.
• 38. Arrabelly SBR, S. Juliet S. Transfer learning with ResNet-50 for malaria cell-image classification. In: Proceedings of the International Conference on Communication and Signal Processing (ICCSP), 2019; Melmaruvathur, India,
• 39. Ulusoy O, Akgül CB, Anarım E. Improving image captioning with language modeling regularizations. In: 2019 Innovations in Intelligent Systems and Applications Conference (ASYU), 2019; İzmir.
• 40. Tan M, Le QV. Efficientnet: rethinking model scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning, Long Beach, 2019; United States of America.
• 41. Mahadeokar J, Pesavento G. Open sourcing a deep learning solution for detecting NSFW images. Yahoo Engineering Blog, 2016. Available from: https://yahooeng.tumblr.com/post/151148689421/open-sourcing-a-deep-learning-solution-for
• 42. You Y, Zhang Z, Cho-Jui Hsieh, Demmel J, Keutzer K. ImageNet training in minutes. arXiv 2018. 1709.05011, 2018.
• 43. A. Krizhevsky A, Sutskever I, G. E. Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 2012; 25.
• 44. Barua A, AlexNet. 2019. Available from: https://arnabfly.github.io/arnab_blog/alexnet/
• 45. Doğan F, Türkoğlu İ. Derin öğrenme modelleri ve uygulama alanlarına ilişkin bir derleme. DÜMF Mühendislik Dergisi, 2019. doi= https://doi.org/10.24012/dumf.411130