{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T05:22:17Z","timestamp":1788153737858,"version":"build-2803163510"},"reference-count":25,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T00:00:00Z","timestamp":1787961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Jinan Fan Factory Co., Ltd.","award":["2025TSGCCZZB0047"],"award-info":[{"award-number":["2025TSGCCZZB0047"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Foods"],"abstract":"<jats:p>To enable rapid, non-destructive identification of damage to Yali pears, this study proposes a detection method that integrates short-wave infrared hyperspectral imaging (1000\u20132500 nm), regularised linear discriminant analysis (R-LDA) and a lightweight convolutional neural network (CNN). The experiments utilised 180 Yali pears (60 each of healthy, with Mechanical scratch and Compression damage specimens) as training samples, whilst a further 300 independent fruits (150 healthy and 150 damaged) were used for fruit-level sorting validation. Following pre-processing using Principal Component Analysis (PCA) to eliminate multicollinearity, the classification performance of three feature extraction strategies\u2014PCA, Independent Component Analysis (ICA) and R-LDA\u2014was compared when combined with the same lightweight CNN. The results indicate that R-LDA\u2019s Fisher discrimination criterion (5.0275) and separation index (2.3543) were both superior to those of PCA and ICA, and its dimension-reduced features exhibited stronger inter-class separability. In pixel-level testing, the R-LDA + lightweight CNN achieved recognition accuracies of 98.60 per cent and 99.32 per cent for Compression damage and background, respectively, and 93.54 per cent and 96.33 per cent for Mechanical scratch and intact tissue, respectively. In a validation study involving the sorting of 300 independent fruits, this method achieved a recall rate of 100.00% for damaged fruits (zero false negatives), with precision and F1 scores of 97.00% and 97.09% respectively, both of which outperformed PCA combined with a lightweight CNN and ICA combined with a lightweight CNN. The above results indicate that the combination of R-LDA discriminant dimensionality reduction and a lightweight CNN can effectively reduce redundancy in hyperspectral data whilst maintaining a high damage detection rate, thereby providing a viable solution for the rapid, non-destructive detection of post-harvest damage in Yali pears.<\/jats:p>","DOI":"10.3390\/foods15173068","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T04:24:03Z","timestamp":1788150243000},"page":"3068","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Study on Hyperspectral Non-Destructive Testing of Mechanical Damage in Yali Pears Using Linear Dimension Reduction and a Lightweight CNN"],"prefix":"10.3390","volume":"15","author":[{"given":"Chao","family":"Ma","sequence":"first","affiliation":[{"name":"School of Mechanical and Automotive Engineering (School of Precision Manufacturing), Liaocheng University, Liaocheng 252059, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4140-9876","authenticated-orcid":false,"given":"Ling","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Mechanical and Automotive Engineering (School of Precision Manufacturing), Liaocheng University, Liaocheng 252059, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaning","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Automotive Engineering (School of Precision Manufacturing), Liaocheng University, Liaocheng 252059, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Mechanical and Automotive Engineering (School of Precision Manufacturing), Liaocheng University, Liaocheng 252059, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fenglei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Automotive Engineering (School of Precision Manufacturing), Liaocheng University, Liaocheng 252059, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Mechanical and Automotive Engineering (School of Precision Manufacturing), Liaocheng University, Liaocheng 252059, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9533-1504","authenticated-orcid":false,"given":"Huimin","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.hpj.2019.07.006","article-title":"Harvest and Postharvest Factors Affecting Bruise Damage of Fresh Fruits","volume":"6","author":"Hussein","year":"2020","journal-title":"Hortic. Plant J."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"113157","DOI":"10.1016\/j.postharvbio.2024.113157","article-title":"A Defect Detection Method for Akidzuki Pears Based on Computer Vision and Deep Learning","volume":"218","author":"Wang","year":"2024","journal-title":"Postharvest Biol. Technol."},{"key":"ref_3","unstructured":"Galanakis, C.M. (2021). Emerging Nondestructive Technologies for Quality Assessment of Fruits, Vegetables, and Cereals. Food Losses, Sustainable Postharvest and Food Technologies, Academic Press."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yu, K., Zhong, M., Zhu, W., Rashid, A., Han, R., Virk, M.S., Duan, K., Zhao, Y., and Ren, X. (2025). Ad-vances in Computer Vision and Spectroscopy Techniques for Non-Destructive Quality Assessment of Citrus Fruits: A Comprehensive Review. Foods, 14.","DOI":"10.3390\/foods14030386"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Yoon, J.Y., and Yu, C. (2024). Machine Learning\u2013Assisted Multispectral and Hyperspectral Imaging. Machine Learning and Artificial Intelligence in Chemical and Biological Sensing, Elsevier Science.","DOI":"10.1016\/B978-0-443-22001-2.00009-3"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.tifs.2019.12.027","article-title":"Applications of Imaging and Spectroscopy Techniques for Non-Destructive Quality Evaluation of Potatoes and Sweet Potatoes: A Review","volume":"96","author":"Sanchez","year":"2020","journal-title":"Trends Food Sci. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Ekramirad, N., Khaled, A.Y., Doyle, L.E., Loeb, J.R., Donohue, K.D., Villanueva, R.T., and Adedeji, A.A. (2022). Nondestructive Detection of Codling Moth Infestation in Apples Using Pixel-Based NIR Hyperspectral Imaging with Machine Learning and Feature Selection. Foods, 11.","DOI":"10.3390\/foods11010008"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"110078","DOI":"10.1016\/j.microc.2024.110078","article-title":"Quantification of Early Bruises on Blueberries Using Hyperspectral Reflectance Imaging Coupled with Band Ratio and Improved Multi-Threshold Coati Optimization Algorithm Method","volume":"199","author":"Sun","year":"2024","journal-title":"Microchem. J."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"106378","DOI":"10.1016\/j.jfca.2024.106378","article-title":"Detection of Dried Jujube from Fresh Jujube with Different Variety and Maturity after Hot Air Drying Based on Hyperspectral Imaging Technology","volume":"133","author":"Liu","year":"2024","journal-title":"J. Food Compos. Anal."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"108681","DOI":"10.1016\/j.jfca.2025.108681","article-title":"Fusion of Spectral and Image Information for Generalized Detection of SSC in Multi-Variety Peaches","volume":"149","author":"Wang","year":"2026","journal-title":"J. Food Compos. Anal."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e70769","DOI":"10.1111\/1750-3841.70769","article-title":"Prediction of Apple Quality Indicators Under Different Bagging Treatments Using Hyperspectral Imaging Integrated with a Stacking SDAE-PLSR-RR Deep Learning Model","volume":"90","author":"Zhu","year":"2025","journal-title":"J. Food Sci."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Qiu, D., Guo, T., Yu, S., Liu, W., Li, L., Sun, Z., Peng, H., and Hu, D. (2024). Classification of Apple Color and Deformity Using Machine Vision Combined with CNN. Agriculture, 14.","DOI":"10.3390\/agriculture14070978"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"100584","DOI":"10.1016\/j.cosrev.2023.100584","article-title":"Integration of Hyperspectral Imaging and Autoencoders: Benefits, Applications, Hyperparameter Tunning and Challenges","volume":"50","author":"Jaiswal","year":"2023","journal-title":"Comput. Sci. Rev."},{"key":"ref_14","first-page":"219","article-title":"Advances in Hyperspectral Image Classification Based on Convolutional Neural Networks: A Review","volume":"133","author":"Bera","year":"2022","journal-title":"CMES-Comput. Model. Eng. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"108422","DOI":"10.1016\/j.jfca.2025.108422","article-title":"Machine learning in VIS\/NIR spectroscopy and hyperspectral imaging for rapid detection of staple foods quality and safety: A review","volume":"148","author":"Miao","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, J., Sun, J., Wang, Y., Liu, X., Zhang, Y., and Fu, H. (2025). Non-Destructive Detection of Fruit Qual-ity: Technologies, Applications and Prospects. Foods, 14.","DOI":"10.3390\/foods14122137"},{"key":"ref_17","first-page":"101068","article-title":"A comprehensive review of external quality measurements of fruits and vegetables using nondestructive sensing technologies","volume":"15","author":"Akter","year":"2024","journal-title":"J. Agric. Food Res."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e14137","DOI":"10.1111\/jfpe.14137","article-title":"Identification of red jujube varieties based on hyperspectral imaging technology combined with CARS-IRIV and SSA-SVM","volume":"45","author":"Wang","year":"2022","journal-title":"J. Food Process Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/0169-7439(87)80084-9","article-title":"Principal Component Analysis","volume":"2","author":"Wold","year":"1987","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_20","unstructured":"Pandey, R., Khatri, S.K., Singh, N.K., and Verma, P. (2022). Unsupervised Learning. Artificial Intelligence and Machine Learning for EDGE Computing, Academic Press."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1016\/S0893-6080(00)00026-5","article-title":"Independent Component Analysis: Algorithms and Applications","volume":"13","author":"Oja","year":"2000","journal-title":"Neural Netw."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1016\/S0031-3203(00)00162-X","article-title":"A Direct LDA Algorithm for High-Dimensional Data\u2014With Application to Face Recognition","volume":"34","author":"Yu","year":"2001","journal-title":"Pattern Recognit."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"103327","DOI":"10.1016\/j.jfca.2019.103327","article-title":"Discriminating Geographic Origin of Sesame Oils and Determining Lignans by Near-Infrared Spectroscopy Combined with Chemometric Methods","volume":"84","author":"Liu","year":"2019","journal-title":"J. Food Compos. Anal."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Xiong, J., Lin, R., Bu, R., Liu, Z., Yang, Z., and Yu, L. (2018). A Micro-Damage Detection Method of Litchi Fruit Using Hyperspectral Imaging Technology. Sensors, 18.","DOI":"10.3390\/s18030700"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e70130","DOI":"10.1111\/jfpe.70130","article-title":"Detection of Early Damage in Kiwifruit Based on Near-Infrared Technology","volume":"48","author":"Ma","year":"2025","journal-title":"J. Food Process Eng."}],"container-title":["Foods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2304-8158\/15\/17\/3068\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T05:06:40Z","timestamp":1788152800000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2304-8158\/15\/17\/3068"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,29]]},"references-count":25,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["foods15173068"],"URL":"https:\/\/doi.org\/10.3390\/foods15173068","relation":{},"ISSN":["2304-8158"],"issn-type":[{"value":"2304-8158","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,29]]}}}