{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,20]],"date-time":"2026-11-20T16:47:04Z","timestamp":1795193224444,"version":"4.10.3"},"reference-count":43,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T00:00:00Z","timestamp":1694649600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Recovery and Resilience Plan (NRRP)","award":["PE00000003"],"award-info":[{"award-number":["PE00000003"]}]},{"name":"National Recovery and Resilience Plan (NRRP)","award":["CUP D93C22000890001"],"award-info":[{"award-number":["CUP D93C22000890001"]}]},{"name":"European Union\u2013NextGenerationEU","award":["PE00000003"],"award-info":[{"award-number":["PE00000003"]}],"id":[{"id":"https:\/\/ror.org\/019w4f821","id-type":"ROR","asserted-by":"crossref"}]},{"name":"European Union\u2013NextGenerationEU","award":["CUP D93C22000890001"],"award-info":[{"award-number":["CUP D93C22000890001"]}],"id":[{"id":"https:\/\/ror.org\/019w4f821","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Italian Ministry of University and Research","award":["PE00000003"],"award-info":[{"award-number":["PE00000003"]}]},{"name":"Italian Ministry of University and Research","award":["CUP D93C22000890001"],"award-info":[{"award-number":["CUP D93C22000890001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Defect segmentation of apples is an important task in the agriculture industry for quality control and food safety. In this paper, we propose a deep learning approach for the automated segmentation of apple defects using convolutional neural networks (CNNs) based on a U-shaped architecture with skip-connections only within the noise reduction block. An ad-hoc data synthesis technique has been designed to increase the number of samples and at the same time to reduce neural network overfitting. We evaluate our model on a dataset of multi-spectral apple images with pixel-wise annotations for several types of defects. In this paper, we show that our proposal outperforms in terms of segmentation accuracy general-purpose deep learning architectures commonly used for segmentation tasks. From the application point of view, we improve the previous methods for apple defect segmentation. A measure of the computational cost shows that our proposal can be employed in real-time (about 100 frame-per-second on GPU) and in quasi-real-time (about 7\/8 frame-per-second on CPU) visual-based apple inspection. To further improve the applicability of the method, we investigate the potential of using only RGB images instead of multi-spectral images as input images. The results prove that the accuracy in this case is almost comparable with the multi-spectral case.<\/jats:p>","DOI":"10.3390\/s23187893","type":"journal-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T04:06:13Z","timestamp":1694750773000},"page":"7893","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Quasi Real-Time Apple Defect Segmentation Using Deep Learning"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0009-8007","authenticated-orcid":false,"given":"Mirko","family":"Agarla","sequence":"first","affiliation":[{"name":"Dipartimento di Informatica, Sistemistica e Comunicazione, Universit\u00e0 Milano-Bicocca, 20126 Milano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9112-0574","authenticated-orcid":false,"given":"Paolo","family":"Napoletano","sequence":"additional","affiliation":[{"name":"Dipartimento di Informatica, Sistemistica e Comunicazione, Universit\u00e0 Milano-Bicocca, 20126 Milano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7461-1451","authenticated-orcid":false,"given":"Raimondo","family":"Schettini","sequence":"additional","affiliation":[{"name":"Dipartimento di Informatica, Sistemistica e Comunicazione, Universit\u00e0 Milano-Bicocca, 20126 Milano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,9,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1186\/s40066-017-0130-8","article-title":"A review on mechanisms and commercial aspects of food preservation and processing","volume":"6","author":"Amit","year":"2017","journal-title":"Agric. Food Secur."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"107789","DOI":"10.1016\/j.compag.2023.107789","article-title":"Evaluation of a new apple in-field sorting system for fruit singulation, rotation and imaging","volume":"208","author":"Zhang","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.biosystemseng.2019.11.011","article-title":"Machine learning applications to non-destructive defect detection in horticultural products","volume":"189","author":"Nturambirwe","year":"2020","journal-title":"Biosyst. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1007\/s12393-022-09307-1","article-title":"Defect Detection in Fruit and Vegetables by Using Machine Vision Systems and Image Processing","volume":"14","author":"Sardari","year":"2022","journal-title":"Food Eng. Rev."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Guin\u00e9, R.P., Floren\u00e7a, S.G., Barroca, M.J., and Anjos, O. (2020). The link between the consumer and the innovations in food product development. Foods, 9.","DOI":"10.3390\/foods9091317"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Carvalho, R., Nascimento, R., D\u2019Angelo, T., Delabrida, S., GC Bianchi, A., Oliveira, R.A., Azp\u00farua, H., and Uzeda Garcia, L.G. (2020). A UAV-based framework for semi-automated thermographic inspection of belt conveyors in the mining industry. Sensors, 20.","DOI":"10.3390\/s20082243"},{"key":"ref_7","unstructured":"Anjali, N., Kannan, R., Andres, F., and Ghinea, G. (2023, September 08). Trend Review Related to Defects Detection from Fruits and Vegetables. Available online: https:\/\/www.preprints.org\/manuscript\/202111.0035\/v1."},{"key":"ref_8","unstructured":"Division, F.S. (2023, September 08). FAOSTAT. Available online: https:\/\/www.fao.org\/faostat\/en\/#data\/QCL."},{"key":"ref_9","first-page":"25","article-title":"A survey on apple fruit diseases detection and classification","volume":"130","author":"Samajpati","year":"2015","journal-title":"Int. J. Comput. Appl."},{"key":"#cr-split#-ref_10.1","unstructured":"European Commission (2004). Commission regulation"},{"key":"#cr-split#-ref_10.2","unstructured":"(EC) no 85\/2004 of 15 January 2004 on marketing standards for apples. Off. J. Eur. Union L, 13, 3-18."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.jfoodeng.2014.09.002","article-title":"Development of a multispectral imaging system for online detection of bruises on apples","volume":"146","author":"Huang","year":"2015","journal-title":"J. Food Eng."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Agarla, M., Bianco, S., Buzzelli, M., Celona, L., and Schettini, R. (2022, January 18\u201324). Fast-N-Squeeze: Towards Real-Time Spectral Reconstruction From RGB Images. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPRW56347.2022.00122"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/S0925-5214(00)00130-7","article-title":"Comparison of reflectance, interactance and transmission modes of visible-near infrared spectroscopy for measuring internal properties of kiwifruit (Actinidia chinensis)","volume":"20","author":"Schaare","year":"2000","journal-title":"Postharvest Biol. Technol."},{"key":"ref_14","unstructured":"Rahi, S., Mobli, H., and Jamshidi, B. (2018, January 4\u20135). Spectroscopy and spectral imaging techniques for non-destructive food microbial assessment. Proceedings of the 5th Iranian International NDT Conference, Tehran, Iran."},{"key":"ref_15","first-page":"380","article-title":"Grading method of soybean mosaic disease based on hyperspectral imaging technology","volume":"8","author":"Gui","year":"2021","journal-title":"Inf. Process. Agric."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/j.jspr.2014.10.001","article-title":"Discriminating and elimination of damaged soybean seeds based on image characteristics","volume":"60","author":"Liu","year":"2015","journal-title":"J. Stored Prod. Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.jfoodeng.2004.07.008","article-title":"Development of a multi-spectral vision system for the detection of defects on apples","volume":"69","author":"Kleynen","year":"2005","journal-title":"J. Food Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.compag.2013.02.009","article-title":"An image segmentation method for apple sorting and grading using support vector machine and Otsu\u2019s method","volume":"94","author":"Mizushima","year":"2013","journal-title":"Comput. Electron. Agric."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.postharvbio.2006.06.010","article-title":"Automatic defect segmentation of \u2018Jonagold\u2019apples on multi-spectral images: A comparative study","volume":"42","author":"Unay","year":"2006","journal-title":"Postharvest Biol. Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1007\/s13244-018-0639-9","article-title":"Convolutional neural networks: An overview and application in radiology","volume":"9","author":"Yamashita","year":"2018","journal-title":"Insights Imaging"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Taye, M.M. (2023). Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions. Computation, 11.","DOI":"10.3390\/computation11030052"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1016\/j.compbiomed.2017.08.022","article-title":"A deep convolutional neural network model to classify heartbeats","volume":"89","author":"Acharya","year":"2017","journal-title":"Comput. Biol. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"16618","DOI":"10.1038\/s41598-021-96103-2","article-title":"Apple quality identification and classification by image processing based on convolutional neural networks","volume":"11","author":"Li","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"110102","DOI":"10.1016\/j.jfoodeng.2020.110102","article-title":"On line detection of defective apples using computer vision system combined with deep learning methods","volume":"286","author":"Fan","year":"2020","journal-title":"J. Food Eng."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1016\/j.neucom.2020.05.070","article-title":"A survey on U-shaped networks in medical image segmentations","volume":"409","author":"Liu","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"38833","DOI":"10.1109\/ACCESS.2020.2974262","article-title":"Detection of apple defects based on the FCM-NPGA and a multivariate image analysis","volume":"8","author":"Zhang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_27","first-page":"33","article-title":"Computer vision-based apple grading for golden delicious apples based on surface features","volume":"4","author":"Moallem","year":"2017","journal-title":"Inf. Process. Agric."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1831","DOI":"10.13031\/trans.12930","article-title":"Detection of surface and subsurface defects of apples using structured-illumination reflectance imaging with machine learning algorithms","volume":"61","author":"Lu","year":"2018","journal-title":"Trans. ASABE"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"7857","DOI":"10.1007\/s11042-019-08564-3","article-title":"Quality evaluation of Mono & bi-Colored Apples with computer vision and multispectral imaging","volume":"79","author":"Bhargava","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"106715","DOI":"10.1016\/j.compag.2022.106715","article-title":"Real-time defects detection for apple sorting using NIR cameras with pruning-based YOLOV4 network","volume":"193","author":"Fan","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.compag.2009.09.014","article-title":"In-line detection of apple defects using three color cameras system","volume":"70","author":"Yanxiao","year":"2010","journal-title":"Comput. Electron. Agric."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/0168-1699(95)00038-0","article-title":"Accurate blemish detection with active contour models","volume":"14","author":"Yang","year":"1996","journal-title":"Comput. Electron. Agric."},{"key":"ref_33","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany. Proceedings, Part III 18."},{"key":"ref_34","unstructured":"Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N., and Liang, J. (2018). Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2017, January 21\u201326). Pyramid scene parsing network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref_36","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv."},{"key":"ref_37","unstructured":"Li, H., Xiong, P., An, J., and Wang, L. (2018). Pyramid attention network for semantic segmentation. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"103911","DOI":"10.1016\/j.compind.2023.103911","article-title":"Deep CNN-based visual defect detection: Survey of current literature","volume":"148","author":"Jha","year":"2023","journal-title":"Comput. Ind."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Agarla, M., Celona, L., and Schettini, R. (2021). An efficient method for no-reference video quality assessment. J. Imaging, 7.","DOI":"10.3390\/jimaging7030055"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Abraham, N., and Khan, N.M. (2019, January 8\u201311). A novel focal tversky loss function with improved attention u-net for lesion segmentation. Proceedings of the 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy.","DOI":"10.1109\/ISBI.2019.8759329"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Jadon, S. (2020, January 27\u201329). A survey of loss functions for semantic segmentation. Proceedings of the 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Vi\u00f1a del Mar, Chile.","DOI":"10.1109\/CIBCB48159.2020.9277638"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1186\/s12880-015-0068-x","article-title":"Metrics for evaluating 3D medical image segmentation: Analysis, selection, and tool","volume":"15","author":"Taha","year":"2015","journal-title":"BMC Med. Imaging"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/18\/7893\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:51:19Z","timestamp":1760129479000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/18\/7893"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,14]]},"references-count":43,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["s23187893"],"URL":"https:\/\/doi.org\/10.3390\/s23187893","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,14]]}}}