{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T16:41:53Z","timestamp":1772815313406,"version":"3.50.1"},"reference-count":57,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T00:00:00Z","timestamp":1713312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Apple cultivar classification is challenging due to the inter-class similarity and high intra-class variations. Human experts do not rely on single-view features but rather study each viewpoint of the apple to identify a cultivar, paying close attention to various details. Following our previous work, we try to establish a similar multiview approach for machine-learning (ML)-based apple classification in this paper. In our previous work, we studied apple classification using one single view. While these results were promising, it also became clear that one view alone might not contain enough information in the case of many classes or cultivars. Therefore, exploring multiview classification for this task is the next logical step. Multiview classification is nothing new, and we use state-of-the-art approaches as a base. Our goal is to find the best approach for the specific apple classification task and study what is achievable with the given methods towards our future goal of applying this on a mobile device without the need for internet connectivity. In this study, we compare an ensemble model with two cases where we use single networks: one without view specialization trained on all available images without view assignment and one where we combine the separate views into a single image of one specific instance. The two latter options reflect dataset organization and preprocessing to allow the use of smaller models in terms of stored weights and number of operations than an ensemble model. We compare the different approaches based on our custom apple cultivar dataset. The results show that the state-of-the-art ensemble provides the best result. However, using images with combined views shows a decrease in accuracy by 3% while requiring only 60% of the memory for weights. Thus, simpler approaches with enhanced preprocessing can open a trade-off for classification tasks on mobile devices.<\/jats:p>","DOI":"10.3390\/jimaging10040094","type":"journal-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T09:15:20Z","timestamp":1713345320000},"page":"94","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Apple Cultivar Classification Using Multiview Images"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0282-5471","authenticated-orcid":false,"given":"Silvia","family":"Krug","sequence":"first","affiliation":[{"name":"Department of Computer and Electrical Engineering, Mid Sweden University, Holmgatan 10, 851 70 Sundsvall, Sweden"},{"name":"System Design Department, IMMS Institut f\u00fcr Mikroelektronik- und Mechatronik-Systeme Gemeinn\u00fctzige GmbH (IMMS GmbH), Ehrenbergstra\u00dfe 27, 98693 Ilmenau, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tino","family":"Hutschenreuther","sequence":"additional","affiliation":[{"name":"System Design Department, IMMS Institut f\u00fcr Mikroelektronik- und Mechatronik-Systeme Gemeinn\u00fctzige GmbH (IMMS GmbH), Ehrenbergstra\u00dfe 27, 98693 Ilmenau, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,4,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Zerbe, S. (2022). Restoration of Multifunctional Cultural Landscapes: Merging Tradition and Innovation for a Sustainable Future, Springer.","DOI":"10.1007\/978-3-030-95572-4"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zerbe, S. (2023). Restoration of Ecosystems\u2013Bridging Nature and Humans: A Transdisciplinary Approach, Springer.","DOI":"10.1007\/978-3-662-65658-7"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1007\/s00468-011-0660-9","article-title":"European pome fruit genetic resources evaluated for disease resistance","volume":"26","author":"Kellerhals","year":"2012","journal-title":"Trees"},{"key":"ref_4","first-page":"9","article-title":"Die Deutsche Genbank Obst, ein dezentrales Netzwerk zur nachhaltigen Erhaltung genetischer Ressourcen bei Obst","volume":"62","author":"Flachowsky","year":"2010","journal-title":"J. Fur-Kult.-J. Cultiv. Plants"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Reim, S., Schiffler, J., Braun-L\u00fcllemann, A., Schuster, M., Flachowsky, H., and H\u00f6fer, M. (2023). Genetic and Pomological Determination of the Trueness-to-Type of Sweet Cherry Cultivars in the German National Fruit Genebank. Plants, 12.","DOI":"10.3390\/plants12010205"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1007\/s10722-014-0088-3","article-title":"Phenotypic evaluation and characterization of a collection of Malus species","volume":"61","author":"Sellmann","year":"2014","journal-title":"Genet. Resour. Crop. Evol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"814","DOI":"10.3390\/agriengineering5020050","article-title":"A Case Study toward Apple Cultivar Classification Using Deep Learning","volume":"5","author":"Krug","year":"2023","journal-title":"AgriEngineering"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/s10846-022-01626-z","article-title":"Exploring Multi-Loss Learning for Multi-View Fine-Grained Vehicle Classification","volume":"105","author":"Silva","year":"2022","journal-title":"J. Intell. Robot. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Seeland, M., and M\u00e4der, P. (2021). Multi-view classification with convolutional neural networks. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0245230"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e0211","DOI":"10.5424\/sjar\/2021194-18056","article-title":"Classification of hazelnut varieties by using artificial neural network and discriminant analysis","volume":"19","author":"Keles","year":"2021","journal-title":"Span. J. Agric. Res."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Taner, A., \u00d6ztekin, Y.B., and Duran, H. (2021). Performance analysis of deep learning CNN models for variety classification in hazelnut. Sustainability, 13.","DOI":"10.3390\/su13126527"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1007\/s00217-021-03920-w","article-title":"Discrimination of tomato seeds belonging to different cultivars using machine learning","volume":"248","author":"Ropelewska","year":"2022","journal-title":"Eur. Food Res. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ropelewska, E., Sabanci, K., and Aslan, M.F. (2021). Discriminative power of geometric parameters of different cultivars of sour cherry pits determined using machine learning. Agriculture, 11.","DOI":"10.3390\/agriculture11121212"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Pandey, R., Uziel, S., Hutschenreuther, T., and Krug, S. (2023). Towards Deploying DNN Models on Edge for Predictive Maintenance Applications. Electronics, 12.","DOI":"10.3390\/electronics12030639"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Pandey, R., Uziel, S., Hutschenreuther, T., and Krug, S. (2023, January 7\u20139). Weighted Pruning with Filter Search to Deploy DNN Models on Microcontrollers. Proceedings of the IEEE 12th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), Dortmund, Germany.","DOI":"10.1109\/IDAACS58523.2023.10348867"},{"key":"ref_16","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1093\/botlinnean\/boaa055","article-title":"The Cinderella discipline: Morphometrics and their use in botanical classification","volume":"194","author":"Christodoulou","year":"2020","journal-title":"Bot. J. Linn. Soc."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"805738","DOI":"10.3389\/fpls.2022.805738","article-title":"Deep learning in plant phenological research: A systematic literature review","volume":"13","author":"Katal","year":"2022","journal-title":"Front. Plant Sci."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"W\u00e4ldchen, J., Rzanny, M., Seeland, M., and M\u00e4der, P. (2018). Automated plant species identification\u2014Trends and future directions. PLoS Comput. Biol., 14.","DOI":"10.1371\/journal.pcbi.1005993"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2216","DOI":"10.1111\/2041-210X.13075","article-title":"Machine learning for image based species identification","volume":"9","year":"2018","journal-title":"Methods Ecol. Evol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1335","DOI":"10.1111\/2041-210X.13611","article-title":"The Flora Incognita app\u2013interactive plant species identification","volume":"12","author":"Boho","year":"2021","journal-title":"Methods Ecol. Evol."},{"key":"ref_22","unstructured":"Kahl, S., Wilhelm-Stein, T., Klinck, H., Kowerko, D., and Eibl, M. (2018). Recognizing birds from sound-the 2018 BirdCLEF baseline system. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"101236","DOI":"10.1016\/j.ecoinf.2021.101236","article-title":"BirdNET: A deep learning solution for avian diversity monitoring","volume":"61","author":"Kahl","year":"2021","journal-title":"Ecol. Inform."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Mena, F., Arenas, D., Nuske, M., and Dengel, A. (2024). Common practices and taxonomy in deep multi-view fusion for remote sensing applications. arXiv.","DOI":"10.1109\/JSTARS.2024.3361556"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.neucom.2021.03.090","article-title":"Deep multi-view learning methods: A review","volume":"448","author":"Yan","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., and Learned-Miller, E. (2015, January 7\u201313). Multi-view convolutional neural networks for 3d shape recognition. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref_27","first-page":"9","article-title":"Classification of apple varieties: Comparison of ensemble learning and naive bayes algorithms in H2O framework","volume":"37","author":"Gerdan","year":"2020","journal-title":"J. Agric. Fac. Gaziosmanpa"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"39525","DOI":"10.1007\/s11042-021-11616-2","article-title":"Deep grading of mangoes using Convolutional Neural Network and Computer Vision","volume":"82","author":"Gururaj","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Tapia-Mendez, E., Cruz-Albarran, I.A., Tovar-Arriaga, S., and Morales-Hernandez, L.A. (2023). Deep Learning-Based Method for Classification and Ripeness Assessment of Fruits and Vegetables. Appl. Sci., 13.","DOI":"10.3390\/app132212504"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, L., Hao, Q., and Cao, J. (2023). Attention-Based Fine-Grained Lightweight Architecture for Fuji Apple Maturity Classification in an Open-World Orchard Environment. Agriculture, 13.","DOI":"10.3390\/agriculture13020228"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"804140","DOI":"10.3389\/fpls.2021.804140","article-title":"Image-based automated recognition of 31 poaceae species: The most relevant perspectives","volume":"12","author":"Rzanny","year":"2022","journal-title":"Front. Plant Sci."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Peng, Y., Zhao, S., and Liu, J. (2021). Fused deep features-based grape varieties identification using support vector machine. Agriculture, 11.","DOI":"10.3390\/agriculture11090869"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"12547","DOI":"10.1109\/ACCESS.2022.3231617","article-title":"Facing the void: Overcoming missing data in multi-view imagery","volume":"11","author":"Machado","year":"2022","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.1109\/TSMC.2022.3192635","article-title":"A survey on incomplete multiview clustering","volume":"53","author":"Wen","year":"2022","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"126562","DOI":"10.1016\/j.neucom.2023.126562","article-title":"Multi-view cost-sensitive kernel learning for imbalanced classification problem","volume":"552","author":"Tang","year":"2023","journal-title":"Neurocomputing"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1016\/j.procs.2020.09.117","article-title":"Deep learning for grape variety recognition","volume":"176","author":"Franczyk","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"107944","DOI":"10.1016\/j.compag.2023.107944","article-title":"Comparison of deep learning methods for grapevine growth stage recognition","volume":"211","author":"Schieck","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_38","first-page":"8878","article-title":"Apples grading based on SVM classifier","volume":"975","author":"Suresha","year":"2012","journal-title":"Int. J. Comput. Appl."},{"key":"ref_39","unstructured":"Miriti, E. (2016). Classification of Selected Apple Fruit Varieties Using Naive Bayes. [Ph.D. Thesis, University of Nairobi]."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"166","DOI":"10.18201\/ijisae.2016SpecialIssue-146967","article-title":"Different apple varieties classification using kNN and MLP algorithms","volume":"4","year":"2016","journal-title":"Int. J. Intell. Syst. Appl. Eng."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/j.compag.2019.04.027","article-title":"Potential use of seed morpho-colourimetric analysis for Sardinian apple cultivar characterisation","volume":"162","author":"Sau","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Liu, C., Han, J., Chen, B., Mao, J., Xue, Z., and Li, S. (2020). A novel identification method for apple (Malus domestica Borkh.) cultivars based on a deep convolutional neural network with leaf image input. Symmetry, 12.","DOI":"10.3390\/sym12020217"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1319","DOI":"10.1007\/s00217-021-03711-3","article-title":"The application of image processing for cultivar discrimination of apples based on texture features of the skin, longitudinal section and cross-section","volume":"247","author":"Ropelewska","year":"2021","journal-title":"Eur. Food Res. Technol."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1359","DOI":"10.1007\/s12161-021-01970-0","article-title":"Classification and grading of multiple varieties of apple fruit","volume":"14","author":"Bhargava","year":"2021","journal-title":"Food Anal. Methods"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Shruthi, U., Narmadha, K.S., Meghana, E., Meghana, D., Lakana, K., and Bhuvan, M. (2022, January 21\u201323). Apple Varieties Classification using Light Weight CNN Model. Proceedings of the 4th International Conference on Circuits, Control, Communication and Computing, Bangalore, India.","DOI":"10.1109\/I4C57141.2022.10057703"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Chen, J., Han, J., Liu, C., Wang, Y., Shen, H., and Li, L. (2022). A Deep-Learning Method for the Classification of Apple Varieties via Leaf Images from Different Growth Periods in Natural Environment. Symmetry, 14.","DOI":"10.3390\/sym14081671"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Garc\u00eda Cort\u00e9s, S., Men\u00e9ndez D\u00edaz, A., Oliveira Prendes, J.A., and Bello Garc\u00eda, A. (2022). Transfer Learning with Convolutional Neural Networks for Cider Apple Varieties Classification. Agronomy, 12.","DOI":"10.3390\/agronomy12112856"},{"key":"ref_48","first-page":"15","article-title":"Classification of apple types using principal component analysis and K-nearest neighbor","volume":"1","author":"Hasan","year":"2023","journal-title":"Int. J. Inf. Syst. Technol. Data Sci."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Taner, A., Mengstu, M.T., Selvi, K.\u00c7., Duran, H., Kaba\u015f, \u00d6., G\u00fcr, \u0130., Karak\u00f6se, T., and Gheorghi\u021b\u0103, N.E. (2023). Multiclass apple varieties classification using machine learning with histogram of oriented gradient and color moments. Appl. Sci., 13.","DOI":"10.3390\/app13137682"},{"key":"ref_50","first-page":"895","article-title":"Identification of apple varieties using hybrid transfer learning and multi-level feature extraction","volume":"250","year":"2023","journal-title":"Eur. Food Res. Technol."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Yu, F., Lu, T., and Xue, C. (2023). Deep Learning-Based Intelligent Apple Variety Classification System and Model Interpretability Analysis. Foods, 12.","DOI":"10.3390\/foods12040885"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Taner, A., Mengstu, M.T., Selvi, K.\u00c7., Duran, H., G\u00fcr, \u0130., and Ungureanu, N. (2024). Apple Varieties Classification Using Deep Features and Machine Learning. Agriculture, 14.","DOI":"10.3390\/agriculture14020252"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3527457","article-title":"Memory-Throughput Trade-off for CNN-based Applications at the Edge","volume":"28","author":"Minakova","year":"2022","journal-title":"ACM Trans. Des. Autom. Electron. Syst."},{"key":"ref_54","first-page":"1","article-title":"A comparative study of optimization algorithms for feature selection on ML-based classification of agricultural data","volume":"1","author":"Garip","year":"2023","journal-title":"Clust. Comput."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_56","unstructured":"Chollet, F. (2024, February 26). Keras. Available online: https:\/\/keras.io."},{"key":"ref_57","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2024, February 26). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Available online: https:\/\/www.tensorflow.org\/."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/10\/4\/94\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:29:09Z","timestamp":1760106549000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/10\/4\/94"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,17]]},"references-count":57,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["jimaging10040094"],"URL":"https:\/\/doi.org\/10.3390\/jimaging10040094","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,17]]}}}