{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T08:15:57Z","timestamp":1771229757358,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Universit\u00e0 degli Studi di Bari Aldo Moro"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Inf Syst"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The quality assessment of fruits and vegetables is crucial in the agroalimentary supply chain, as it directly affects consumer satisfaction, market value and overall food security. Traditional approaches rely on visual inspections or destructive techniques, which are labor-intensive and time-consuming. On the contrary, non-destructive techniques emerged as promising alternatives, offering solutions that can be adopted in real environments. Previous studies emphasized that the color distribution over images plays a significant role in the quality evaluation of food. In this paper, we propose a solution that leverages an autoencoder architecture to extract groups of relevant colors from the complete histogram of colors. To enhance the analysis of real-world images with complex backgrounds, we employ a pre-trained U2-Net architecture for background removal. Moreover, we propose a novel procedure based on outlier detection to identify and remove parts of the background that are not fully eliminated, especially along the edges of the product. After this preprocessing, we extract a complete color histogram which is fed to an autoencoder architecture, to extract high-level features representing color groups at different levels of granularity. The goal is to make the learned models less sensitive to light and color perturbations. Our experiments, conducted on two real-world datasets related to two different learning tasks, demonstrated the effectiveness of the proposed solution, that outperformed several baseline and state-of-the-art approaches, also based on complex neural network architectures.<\/jats:p>","DOI":"10.1007\/s10844-025-00984-y","type":"journal-article","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T09:04:54Z","timestamp":1760087094000},"page":"215-238","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Handling complex backgrounds and light perturbations for enhancing learning tasks from images of vegetables"],"prefix":"10.1007","volume":"64","author":[{"given":"Stefano","family":"Polimena","sequence":"first","affiliation":[]},{"given":"Gianvito","family":"Pio","sequence":"additional","affiliation":[]},{"given":"Giovanni","family":"Attolico","sequence":"additional","affiliation":[]},{"given":"Michelangelo","family":"Ceci","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,10]]},"reference":[{"key":"984_CR1","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1016\/j.ins.2022.05.079","volume":"606","author":"EP Barracchia","year":"2022","unstructured":"Barracchia, E. P., Pio, G., Bifet, A., et al. (2022). LP-ROBIN: Link prediction in dynamic networks exploiting incremental node embedding. Information Sciences, 606, 702\u2013721. https:\/\/doi.org\/10.1016\/j.ins.2022.05.079","journal-title":"Information Sciences"},{"key":"984_CR2","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.jfoodeng.2017.11.042","volume":"223","author":"DP Cavallo","year":"2018","unstructured":"Cavallo, D. P., Cefola, M., Pace, B., et al. (2018). Non-destructive automatic quality evaluation of fresh-cut iceberg lettuce through packaging material. Journal of Food Engineering, 223, 46\u201352. https:\/\/doi.org\/10.1016\/j.jfoodeng.2017.11.042","journal-title":"Journal of Food Engineering"},{"key":"984_CR3","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1016\/j.compag.2018.12.019","volume":"156","author":"DP Cavallo","year":"2019","unstructured":"Cavallo, D. P., Cefola, M., Pace, B., et al. (2019). Non-destructive and contactless quality evaluation of table grapes by a computer vision system. Computers and Electronics in Agriculture, 156, 558\u2013564. https:\/\/doi.org\/10.1016\/j.compag.2018.12.019","journal-title":"Computers and Electronics in Agriculture"},{"key":"984_CR4","doi-asserted-by":"publisher","unstructured":"Ciarfuglia, T. A., Motoi, I. M., Saraceni, L., et\u00a0al. (2023). Weakly and semi-supervised detection, segmentation and tracking of table grapes with limited and noisy data. Computers and Electronics in Agriculture,205, Article 107624. https:\/\/doi.org\/10.1016\/j.compag.2023.107624","DOI":"10.1016\/j.compag.2023.107624"},{"key":"984_CR5","doi-asserted-by":"crossref","unstructured":"Corizzo, R., Dauphin, Y., Bellinger, C., et\u00a0al. (2021). Explainable image analysis for decision support in medical healthcare. In: 2021 IEEE International Conference on Big Data (Big Data), pp 4667\u20134674. 10.1109\/BigData52589.2021.9671335","DOI":"10.1109\/BigData52589.2021.9671335"},{"key":"984_CR6","doi-asserted-by":"publisher","unstructured":"Dai, G., Tian, Z., Fan, J., et\u00a0al. (2024). Dfn-psan: Multi-level deep information feature fusion extraction network for interpretable plant disease classification. Computers and Electronics in Agriculture,216, Article 108481. https:\/\/doi.org\/10.1016\/j.compag.2023.108481","DOI":"10.1016\/j.compag.2023.108481"},{"key":"984_CR7","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale.\u00a0arXiv preprint arXiv:2010.11929. https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"issue":"1","key":"984_CR8","doi-asserted-by":"publisher","first-page":"7347","DOI":"10.1038\/s41598-023-34527-8","volume":"13","author":"J Dutta","year":"2023","unstructured":"Dutta, J., Patwardhan, M., Deshpande, P., et al. (2023). Zero-shot transfer learned generic AI models for prediction of optimally ripe climacteric fruits. Scientific Reports, 13(1), 7347. https:\/\/doi.org\/10.1038\/s41598-023-34527-8","journal-title":"Scientific Reports"},{"key":"984_CR9","unstructured":"Garcin, C., Joly, A., Bonnet, P., et\u00a0al. (2021). Pl@ntNet-300K: a plant image dataset with high label ambiguity and a long-tailed distribution. In: NeurIPS Datasets and Benchmarks 2021. 10.5281\/zenodo.5645731"},{"key":"984_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108474","volume":"216","author":"Y Ge","year":"2024","unstructured":"Ge, Y., From, P. J., & Xiong, Y. (2024). Multi-view gripper internal sensing for the regression of strawberry ripeness using a mini-convolutional neural network for robotic harvesting. Computers and Electronics in Agriculture, 216, Article 108474. https:\/\/doi.org\/10.1016\/j.compag.2023.108474","journal-title":"Computers and Electronics in Agriculture"},{"key":"984_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/s11119-023-10022-y","author":"Y Han","year":"2023","unstructured":"Han, Y., Bai, S. H., Trueman, S. J., et al. (2023). Predicting the ripening time of \u2018hass\u2019 and \u2018shepard\u2019avocado fruit by hyperspectral imaging. Precision Agriculture. https:\/\/doi.org\/10.1007\/s11119-023-10022-y","journal-title":"Precision Agriculture"},{"key":"984_CR12","doi-asserted-by":"crossref","unstructured":"He. K., Zhang, X., Ren, S., et\u00a0al. (2016). Deep residual learning for image recognition. In: 2016 IEEE Conference on CVPR, pp 770\u2013778. 10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"984_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2021.106040","volume":"182","author":"N Hussain","year":"2021","unstructured":"Hussain, N., Farooque, A. A., Schumann, A. W., et al. (2021). Application of deep learning to detect lamb\u2019s quarters (chenopodium album L.) in potato fields of Atlantic Canada. Computers and Electronics in Agriculture, 182, Article 106040. https:\/\/doi.org\/10.1016\/j.compag.2021.106040","journal-title":"Computers and Electronics in Agriculture"},{"key":"984_CR14","unstructured":"Jocher, G. (2020). YOLOv5 by Ultralytics. 10.5281\/zenodo.3908559"},{"key":"984_CR15","doi-asserted-by":"publisher","unstructured":"Kim, S. Y., Hong, S. J., Kim, E., et\u00a0al. (2023). Application of ensemble neural-network method to integrated sugar content prediction model for citrus fruit using vis\/nir spectroscopy. Journal of Food Engineering,338, Article 111254. https:\/\/doi.org\/10.1016\/j.jfoodeng.2022.111254","DOI":"10.1016\/j.jfoodeng.2022.111254"},{"key":"984_CR16","doi-asserted-by":"crossref","unstructured":"Kunang, Y.N., Nurmaini, S., Stiawan, D., et\u00a0al. (2018). Automatic features extraction using autoencoder in intrusion detection system. In: 2018 International Conference on Electrical Engineering and Computer Science (ICECOS), pp 219\u2013224. 10.1109\/ICECOS.2018.8605181","DOI":"10.1109\/ICECOS.2018.8605181"},{"key":"984_CR17","unstructured":"LEE, Y., Kwon, H., Park, F. (2021). Neighborhood reconstructing autoencoders. In: Ranzato M, Beygelzimer A, Dauphin Y, et\u00a0al (eds) Advances in Neural Information Processing Systems, vol\u00a034. Curran Associates, Inc., pp 536\u2013546"},{"key":"984_CR18","doi-asserted-by":"publisher","unstructured":"Li, P., Pei, Y., & Li, J. (2023). A comprehensive survey on design and application of autoencoder in deep learning. Applied Soft Computing,138, Article 110176. https:\/\/doi.org\/10.1016\/j.asoc.2023.110176","DOI":"10.1016\/j.asoc.2023.110176"},{"key":"984_CR19","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/j.biosystemseng.2021.11.011","volume":"212","author":"H Li","year":"2021","unstructured":"Li, H., Li, C., Li, G., et al. (2021). A real-time table grape detection method based on improved yolov4-tiny network in complex background. Biosystems Engineering, 212, 347\u2013359. https:\/\/doi.org\/10.1016\/j.biosystemseng.2021.11.011","journal-title":"Biosystems Engineering"},{"issue":"7","key":"984_CR20","doi-asserted-by":"publisher","first-page":"3289","DOI":"10.1109\/TNNLS.2017.2712793","volume":"29","author":"W Luo","year":"2018","unstructured":"Luo, W., Li, J., Yang, J., et al. (2018). Convolutional sparse autoencoders for image classification. IEEE Transactions on Neural Networks and Learning Systems, 29(7), 3289\u20133294. https:\/\/doi.org\/10.1109\/TNNLS.2017.2712793","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"984_CR21","doi-asserted-by":"publisher","unstructured":"MacEachern, C. B., Esau, T. J., Schumann, A. W., et\u00a0al. (2023). Detection of fruit maturity stage and yield estimation in wild blueberry using deep learning convolutional neural networks. Smart Agricultural Technology,3, Article 100099. https:\/\/doi.org\/10.1016\/j.atech.2022.100099","DOI":"10.1016\/j.atech.2022.100099"},{"issue":"2","key":"984_CR22","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1109\/34.908974","volume":"23","author":"A Martinez","year":"2001","unstructured":"Martinez, A., & Kak, A. (2001). Pca versus lda. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(2), 228\u2013233. https:\/\/doi.org\/10.1109\/34.908974","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"984_CR23","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1016\/j.tifs.2023.02.005","volume":"133","author":"M Mohd Ali","year":"2023","unstructured":"Mohd Ali, M., Hashim, N., Bejo, S. K., et al. (2023). Innovative non-destructive technologies for quality monitoring of pineapples: Recent advances and applications. Trends in Food Science & Technology, 133, 176\u2013188. https:\/\/doi.org\/10.1016\/j.tifs.2023.02.005","journal-title":"Trends in Food Science & Technology"},{"key":"984_CR24","doi-asserted-by":"publisher","unstructured":"Palumbo, M., Cefola, M., Pace, B., et\u00a0al. (2024). Machine learning for the identification of colour cues to estimate quality parameters of rocket leaves. Journal of Food Engineering,366, Article 111850. https:\/\/doi.org\/10.1016\/j.jfoodeng.2023.111850","DOI":"10.1016\/j.jfoodeng.2023.111850"},{"key":"984_CR25","doi-asserted-by":"publisher","unstructured":"Palumbo, M., Pace, B., Cefola, M., et\u00a0al. (2022). Non-destructive and contactless estimation of chlorophyll and ammonia contents in packaged fresh-cut rocket leaves by a computer vision system. Postharvest Biology and Technology,189, Article 111910. https:\/\/doi.org\/10.1016\/j.postharvbio.2022.111910","DOI":"10.1016\/j.postharvbio.2022.111910"},{"key":"984_CR26","doi-asserted-by":"publisher","first-page":"1426","DOI":"10.1109\/JSTARS.2020.2983000","volume":"13","author":"S Paul","year":"2020","unstructured":"Paul, S., Poliyapram, V., \u0130mamo\u011flu, N., et al. (2020). Canopy averaged chlorophyll content prediction of pear trees using convolutional autoencoder on hyperspectral data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 1426\u20131437. https:\/\/doi.org\/10.1109\/JSTARS.2020.2983000","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"984_CR27","doi-asserted-by":"publisher","unstructured":"Petchhan, J., & Su, S. F. (2024). Self-supervised domain-adaptive learning for self-labeling unknown rice grains during actual rice transportation process. Computers and Electronics in Agriculture,216, Article 108483. https:\/\/doi.org\/10.1016\/j.compag.2023.108483","DOI":"10.1016\/j.compag.2023.108483"},{"key":"984_CR28","doi-asserted-by":"crossref","unstructured":"Polimena, S., Pio, G., Attolico, G., et\u00a0al. (2024). Improving the robustness to color perturbations of classification and regression models in the visual evaluation of fruits and vegetables. In: Appice, A., Azzag, H., Hacid, M.S., et\u00a0al. (eds) Foundations of Intelligent Systems. Springer Nature Switzerland, Cham, pp 3\u201313. 10.1007\/978-3-031-62700-2_1","DOI":"10.1007\/978-3-031-62700-2_1"},{"key":"984_CR29","unstructured":"Pu, Y., Gan, Z., Henao, R., et\u00a0al. (2016). Variational autoencoder for deep learning of images, labels and captions. In D. Lee, M. Sugiyama, U. Luxburg, et\u00a0al. (Eds.), Advances in Neural Information Processing Systems.  (Vol. 29). Curran Associates Inc."},{"key":"984_CR30","doi-asserted-by":"publisher","unstructured":"Qi, H., Shen, C., Chen, G., et\u00a0al. (2023). Rapid and non-destructive determination of soluble solid content of crown pear by visible\/near-infrared spectroscopy with deep learning regression. Journal of Food Composition and Analysis,123, Article 105585. https:\/\/doi.org\/10.1016\/j.jfca.2023.105585","DOI":"10.1016\/j.jfca.2023.105585"},{"key":"984_CR31","doi-asserted-by":"publisher","unstructured":"Qin, X., Zhang, Z., Huang, C., et\u00a0al. (2020). U2-net: Going deeper with nested u-structure for salient object detection. Pattern Recognition,106, Article 107404. https:\/\/doi.org\/10.1016\/j.patcog.2020.107404","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"984_CR32","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., et\u00a0al. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 10.1109\/CVPR.2018.00474","DOI":"10.1109\/CVPR.2018.00474"},{"key":"984_CR33","doi-asserted-by":"publisher","unstructured":"Shinde, R. (2021). Glaucoma detection in retinal fundus images using u-net and supervised machine learning algorithms. Intelligence-Based Medicine,5, Article 100038. https:\/\/doi.org\/10.1016\/j.ibmed.2021.100038","DOI":"10.1016\/j.ibmed.2021.100038"},{"key":"984_CR34","doi-asserted-by":"crossref","unstructured":"Song, F., Guo, Z., Mei, D. (2010). Feature selection using principal component analysis. In: 2010 International Conference on System Science, Engineering Design and Manufacturing Informatization, pp 27\u201330. 10.1109\/ICSEM.2010.14","DOI":"10.1109\/ICSEM.2010.14"},{"key":"984_CR35","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1016\/j.compag.2019.04.019","volume":"162","author":"J Steinbrener","year":"2019","unstructured":"Steinbrener, J., Posch, K., & Leitner, R. (2019). Hyperspectral fruit and vegetable classification using convolutional neural networks. Computers and Electronics in Agriculture, 162, 364\u2013372. https:\/\/doi.org\/10.1016\/j.compag.2019.04.019","journal-title":"Computers and Electronics in Agriculture"},{"key":"984_CR36","doi-asserted-by":"publisher","unstructured":"Wang, X., Kang, H., Zhou, H., et\u00a0al. (2022). Geometry-aware fruit grasping estimation for robotic harvesting in apple orchards. Computers and Electronics in Agriculture,193, Article 106716. https:\/\/doi.org\/10.1016\/j.compag.2022.106716","DOI":"10.1016\/j.compag.2022.106716"},{"issue":"2","key":"984_CR37","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1007\/s10618-014-0356-z","volume":"29","author":"F Wang","year":"2015","unstructured":"Wang, F., & Sun, J. (2015). Survey on distance metric learning and dimensionality reduction in data mining. Data Mining And Knowledge Discovery, 29(2), 534\u2013564. https:\/\/doi.org\/10.1007\/s10618-014-0356-z","journal-title":"Data Mining And Knowledge Discovery"},{"key":"984_CR38","unstructured":"Yang, Z., Hu, Z., Salakhutdinov, R., et\u00a0al. (2017). Improved variational autoencoders for text modeling using dilated convolutions. In: International conference on machine learning, PMLR, pp 3881\u20133890"},{"issue":"1","key":"984_CR39","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1109\/TSMC.2020.2968516","volume":"52","author":"C Yin","year":"2022","unstructured":"Yin, C., Zhang, S., Wang, J., et al. (2022). Anomaly detection based on convolutional recurrent autoencoder for iot time series. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 52(1), 112\u2013122. https:\/\/doi.org\/10.1109\/TSMC.2020.2968516","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"984_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119885","volume":"661","author":"K Zhang","year":"2024","unstructured":"Zhang, K., Hao, W., Yu, X., et al. (2024). An interpretable image classification model combining a fuzzy neural network with a variational autoencoder inspired by the human brain. Information Sciences, 661, Article 119885. https:\/\/doi.org\/10.1016\/j.ins.2023.119885","journal-title":"Information Sciences"},{"key":"984_CR41","doi-asserted-by":"publisher","unstructured":"Zhao, F., Hao, J., Zhang, H., et\u00a0al. (2024). Quality recognition method of oyster based on u-net and random forest. Journal of Food Composition and Analysis,125, Article 105746. https:\/\/doi.org\/10.1016\/j.jfca.2023.105746","DOI":"10.1016\/j.jfca.2023.105746"},{"key":"984_CR42","doi-asserted-by":"publisher","unstructured":"Zhou, X., Sun, J., Tian, Y., et\u00a0al. (2020). Hyperspectral technique combined with deep learning algorithm for detection of compound heavy metals in lettuce. Food Chemistry,321, Article 126503. https:\/\/doi.org\/10.1016\/j.foodchem.2020.126503","DOI":"10.1016\/j.foodchem.2020.126503"}],"container-title":["Journal of Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-025-00984-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10844-025-00984-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-025-00984-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T07:39:44Z","timestamp":1771227584000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10844-025-00984-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,10]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["984"],"URL":"https:\/\/doi.org\/10.1007\/s10844-025-00984-y","relation":{},"ISSN":["0925-9902","1573-7675"],"issn-type":[{"value":"0925-9902","type":"print"},{"value":"1573-7675","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,10]]},"assertion":[{"value":"18 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 October 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to publish"}},{"value":"The authors declare no competing interests.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}