Abstract
The process of identifying apple varieties holds pivotal importance in pomology and agricultural science. This intricate task not only aids growers in optimizing orchard management, but also profoundly impacts consumers and the apple industry as a whole. Selecting the right apple varieties tailored to specific environmental conditions and market demands is instrumental for the sustainability and economic viability of apple cultivation. Accurate apple variety identification further contributes to maintaining product quality and ensuring consumer satisfaction. Traditional identification methods, however, are susceptible to human error given the vast diversity of apple cultivars. In response, the integration of advanced technologies, including image processing and machine learning, has emerged as a promising approach to enhance accuracy and efficiency in apple variety identification, benefitting both the agricultural and commercial sectors. The classification of apple types involved feature extraction using three methods: MobileNetV2, EfficientNetV2B0, and a combination of GLCM and Color-Space algorithms from apple images. Machine learning models were then built to classify apple varieties, utilizing various algorithms such as support vector machine (SVM), k-nearest neighbors (Knn), random subspace (RSS), and random forest. In the case of "EfficientNetV2B0 + GLCM + Color-Space" and utilizing the ReliefF feature selection method, the random forest algorithm attains peak performance with an accuracy, precision, recall, and F-score all registering an impressive 98.33%.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00217-023-04436-1/MediaObjects/217_2023_4436_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00217-023-04436-1/MediaObjects/217_2023_4436_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00217-023-04436-1/MediaObjects/217_2023_4436_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00217-023-04436-1/MediaObjects/217_2023_4436_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00217-023-04436-1/MediaObjects/217_2023_4436_Fig5_HTML.png)
Similar content being viewed by others
Data availability
Data can be found in this link (https://github.com/rifatkurban/apple_dataset).
References
Lyu F, Luiz SF, Azeredo DRP, Cruz AG, Ajlouni S, Ranadheera CS (2020) Apple pomace as a functional and healthy ingredient in food products: A review. Processes 8(3):319
Musacchi S, Serra S (2018) Apple fruit quality: overview on pre-harvest factors. Sci Hortic 234:409–430
Gulzar Y (2023) Fruit image classification model based on MobileNetV2 with deep transfer learning technique. Sustainability 15(3):1906
Häni N, Roy P, Isler V (2020) A comparative study of fruit detection and counting methods for yield map** in apple orchards. J Field Robot 37(2):263–282. https://doi.org/10.1002/rob.21902
Khan AI, Quadri SMK, Banday S, Latief Shah J (2022) Deep diagnosis: a real-time apple leaf disease detection system based on deep learning. Comput Electron Agric 198:107093. https://doi.org/10.1016/j.compag.2022.107093
Hasanzadeh B, Abbaspour-Gilandeh Y, Soltani-Nazarloo A, Cruz-Gámez EDL, Hernández-Hernández JL, Martínez-Arroyo M (2022) Non-destructive measurement of quality parameters of apple fruit by using visible/near-ınfrared spectroscopy and multivariate regression analysis. Sustainability 14(22):22. https://doi.org/10.3390/su142214918
Alonso-Salces RM, Herrero C, Barranco A, Berrueta LA, Gallo B, Vicente F (2005) Classification of apple fruits according to their maturity state by the pattern recognition analysis of their polyphenolic compositions. Food Chem 93(1):113–123. https://doi.org/10.1016/j.foodchem.2004.10.013
Wu A, Zhu J, Ren T (2020) Detection of apple defect using laser-induced light backscattering imaging and convolutional neural network. Comput Electr Eng 81:106454. https://doi.org/10.1016/j.compeleceng.2019.106454
Luo W et al (2011) Preliminary study on the application of near infrared spectroscopy and pattern recognition methods to classify different types of apple samples. Food Chem 128(2):555–561. https://doi.org/10.1016/j.foodchem.2011.03.065
Li C, Li L, Wu Y, Lu M, Yang Y, Li L (2018) Apple variety identification using near-infrared spectroscopy. J Spectrosc 2018:e6935197. https://doi.org/10.1155/2018/6935197
Li J et al (2020) A shallow convolutional neural network for apple classification. IEEE Access 8:111683–111692. https://doi.org/10.1109/ACCESS.2020.3002882
Huang Y, Yang Y, Sun Y, Zhou H, Chen K (2020) Identification of apple varieties using a multichannel hyperspectral ımaging system. Sensors 20(18):18. https://doi.org/10.3390/s20185120
Gerdan D, Beyaz A, Vatandaş M (2020) Classification of apple varieties: comparison of ensemble learning and Naive bayes algorithms in H2O framework. J Agric. Fac. Gaziosmanpaşa Univ JAFAG 37(1):1. https://doi.org/10.13002/jafag4646
Bhargava A, Bansal A (2021) Classification and grading of multiple varieties of apple fruit. Food Anal Methods 14(7):1359–1368. https://doi.org/10.1007/s12161-021-01970-0
Taner A et al (2023) Multiclass apple varieties classification using machine learning with histogram of oriented gradient and color moments. Appl Sci 13(13):13. https://doi.org/10.3390/app13137682
Jiang H, Li X, Safara F (2021) IoT-based agriculture: deep learning in detecting apple fruit diseases. Microprocess Microsyst 104321
Kapila G, Vandana B, Khaitan A, Francis Avinash A, Ajay Kumar CH (2022) Apple fruit classification and damage detection using pre-trained deep neural network as feature extractor. İn: Saini HS, Singh RK, Tariq Beg M, Mulaveesala R, and Mahmood MR (Eds) Innovations in electronics and communication engineering vol. 355, in Lecture Notes in Networks and Systems, vol. 355, Singapore: Springer Singapore, pp. 235–243. doi: https://doi.org/10.1007/978-981-16-8512-5_26.
Chu P, Li Z, Lammers K, Lu R, Liu X (2021) Deep learning-based apple detection using a suppression mask R-CNN. Pattern Recognit Lett 147:206–211
Xue G, Liu S, Ma Y (2023) A hybrid deep learning-based fruit classification using attention model and convolution autoencoder. Complex Intell Syst 9(3):2209–2219. https://doi.org/10.1007/s40747-020-00192-x
Hasan MA (2023) Classification of apple types using principal component analysis and K-nearest neighbor. Int J Inf Syst Technol Data Sci 1(1):15–22
Yang H, Wang W, and Mao Z (2023) Research on the improved apple classification method of AlexNet. İn: Third ınternational conference on ımage processing and ıntelligent control (IPIC 2023), SPIE, 2023, pp. 378–385. Accessed: Nov. 20, 2023. [Online]. Available: https://www.spiedigitallibrary.org/conference-proceedings-of-spie/12782/127821I/Research-on-the-improved-apple-classification-method-of-AlexNet/https://doi.org/10.1117/12.3000778.short
Adige S, Kurban R, Durmuş A, Karaköse E (2023) Classification of apple images using support vector machines and deep residual networks. Neural Comput Appl 35(16):12073–12087. https://doi.org/10.1007/s00521-023-08340-3
Mohanaiah P, Sathyanarayana P, GuruKumar L (2013) Image texture feature extraction using GLCM approach. Int J Sci Res Publ 3(5):1–5
Madhura C, Dheeraj D (2013) Feature extraction for image retrieval using Color-Spaces and GLCM. Int J Innov Technol Explor Eng IJITEE 3(2):159–162
Tan M, Le Q Efficientnetv2: smaller models and faster training’, in International conference on machine learning, PMLR, 2021, pp. 10096–10106. Accessed: Sep. 28, 2023. [Online]. Available: http://proceedings.mlr.press/v139/tan21a.html
Howard AG et al. (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications’, Ar**v Prepr. Ar**v170404861
Chollet F (2017) Xception: deep learning with depthwise separable convolutions. İn: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1251–1258.
Szegedy C, Ioffe S, Vanhoucke V, and Alemi A (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. İn: Proceedings of the AAAI conference on artificial intelligence,
Sandler M, Howard A, Zhu M, Zhmoginov A, and Chen L-C (2018) ‘Mobilenetv2: Inverted residuals and linear bottlenecks. İn: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4510–4520.
Nithya B, Ilango V (2019) Evaluation of machine learning based optimized feature selection approaches and classification methods for cervical cancer prediction. SN Appl Sci 1(6):641. https://doi.org/10.1007/s42452-019-0645-7
Bülbül MA (2023) Optimization of artificial neural network structure and hyperparameters in hybrid model by genetic algorithm: iOS–android application for breast cancer diagnosis/prediction. J Supercomput. https://doi.org/10.1007/s11227-023-05635-z
Pacal I (2024) Enhancing crop productivity and sustainability through disease identification in maize leaves: exploiting a large dataset with an advanced vision transformer model. Expert Syst Appl 238:122099
Akbacak E, Toktas A, Erkan U, Gao S (2023) MLMQ-IR: multi-label multi-query image retrieval based on the variance of hamming distance. Knowl-Based Syst 283:111193
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297
Kotsiantis S (2011) Combining bagging, boosting, rotation forest and random subspace methods. Artif Intell Rev 35(3):223–240. https://doi.org/10.1007/s10462-010-9192-8
Guo G, Wang H, Bell D, Bi Y, and Greer K (2003) KNN model-based approach in classification. In: On the move to meaningful ınternet systems 2003: CoopIS, DOA, and ODBASE: OTM confederated ınternational conferences, CoopIS, DOA, and ODBASE 2003, Catania, Sicily, Italy, November 3-7, 2003. Proceedings, Springer, pp. 986–996
Rigatti SJ (2017) Random forest. J Insur Med 47(1):31–39
Funding
The study was not supported by any funding.
Author information
Authors and Affiliations
Contributions
The authors contributed equally to the study.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Compliance with ethics requirements
This article does not contain any studies with animal or human subjects.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kılıçarslan, S., Dönmez, E. & Kılıçarslan, S. Identification of apple varieties using hybrid transfer learning and multi-level feature extraction. Eur Food Res Technol 250, 895–909 (2024). https://doi.org/10.1007/s00217-023-04436-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00217-023-04436-1