{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T23:19:57Z","timestamp":1794007197393,"version":"4.8.0"},"reference-count":57,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Jiangsu Provincial Science and Technology Plan Special Fund","award":["BE2022317"],"award-info":[{"award-number":["BE2022317"]}]},{"name":"Jiangsu Province Integrated Project for R&D, Manufacturing, Promotion, and Application of Agricultural Machinery","award":["JSYTH16"],"award-info":[{"award-number":["JSYTH16"]}]},{"name":"Agricultural Science and Technology Innovation Program of the Chinese Academy of Agricultural Sciences","award":["31-NIAM-09"],"award-info":[{"award-number":["31-NIAM-09"]}]},{"award":["31-NIAM-09"],"award-info":[{"award-number":["31-NIAM-09"]}],"id":[{"id":"https:\/\/ror.org\/0313jb750","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Foods"],"abstract":"<jats:p>In order to enable accurate and efficient rice quality evaluation through full-surface defect detection of brown rice, a detection system based on convolutional neural network (CNN) was developed. A dataset of images of five categories\u2014unhulled, normal, broken, cracked, and insect-bitten brown rice\u2014was collected. Three CNN models, YOLOv5s, YOLOv7, and Faster R-CNN, were evaluated and compared with traditional algorithms including support vector machine (SVM) and back propagation (BP) neural networks. Experimental results showed that CNN-based methods in the present database significantly outperformed traditional approaches, with the YOLOv5s model achieving the best comprehensive performance: 95.80% detection accuracy, 10.90 ms inference time per image, and 92 frames\/s processing speed. An improved Rice-YOLOv5s algorithm was further proposed and validated through batch detection experiments, achieving an average recognition accuracy of 96.44% and a processing time of 9.2 ms per image, which is equivalent to approximately 108.7 FPS. This study demonstrates the feasibility of CNN-based brown rice defect detection, with future work directed toward lightweight deployment and multimodal fusion for production-line application.<\/jats:p>","DOI":"10.3390\/foods15162910","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T08:10:20Z","timestamp":1787213420000},"page":"2910","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A CNN-Based Image Detection System for Full-Surface Defects in Brown Rice"],"prefix":"10.3390","volume":"15","author":[{"given":"Zhaoyan","family":"You","sequence":"first","affiliation":[{"name":"Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianchun","family":"Yan","sequence":"additional","affiliation":[{"name":"College of Engineering, Nanjing Agricultural University, Nanjing 210031, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hai","family":"Wei","sequence":"additional","affiliation":[{"name":"Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minji","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiannan","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanxiong","family":"Xie","sequence":"additional","affiliation":[{"name":"Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"ref_1","unstructured":"FAO (2026, February 06). Global Supply and Demand Brief, February 2026. Available online: http:\/\/static.facisp.cn\/html\/20260209\/ca12be37-eddf-4c5d-8df8-f4c18fe238b4.html."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"103911","DOI":"10.1016\/j.ifset.2024.103911","article-title":"A method for improving milling quality based on pre-milling in the combined rice milling process","volume":"100","author":"Sun","year":"2025","journal-title":"Innov. Food Sci. Emerg. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"111885","DOI":"10.1016\/j.compag.2026.111885","article-title":"A hybrid machine-learning and process-based regional crop modelling framework to improve rice production strategies under data constraints","volume":"249","author":"Li","year":"2026","journal-title":"Comput. Electron. Agric."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e15480","DOI":"10.1016\/j.heliyon.2023.e15480","article-title":"Modelling climate variabilities and global rice production: A panel regression and time series analysis","volume":"9","author":"Masha","year":"2023","journal-title":"Heliyon"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"108483","DOI":"10.1016\/j.compag.2023.108483","article-title":"Self-Supervised Domain-Adaptive learning for Self-Labeling unknown rice grains during actual rice transportation process","volume":"216","author":"Jirayu","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"104473","DOI":"10.1016\/j.biosystemseng.2026.104473","article-title":"Mechanism of impact breakage in paddy rice: A cohesive zone model-based research on crack evolution and energy dissipation","volume":"267","author":"Li","year":"2026","journal-title":"Biosyst. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"102236","DOI":"10.1016\/j.jspr.2023.102236","article-title":"Rice storage under controlled conditions: Changes in its physicochemical and functional properties","volume":"105","author":"Ma","year":"2024","journal-title":"J. Stored Prod. Res."},{"key":"ref_8","first-page":"137","article-title":"Research on online identification system of rice broken impurities in combine harvester","volume":"42","author":"Chen","year":"2021","journal-title":"J. Chin. Agric. Mech."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"125381","DOI":"10.1016\/j.foodchem.2019.125381","article-title":"Volatile biomarkers for early-stage detection of insect-infested brown rice: Isopentenols and polysulfides","volume":"303","author":"Fukuyo","year":"2020","journal-title":"Food Chem."},{"key":"ref_10","first-page":"428","article-title":"Moldy rice detection method based on near infrared spectroscopy image processing technology","volume":"42","author":"Wen","year":"2022","journal-title":"Spectrosc. Spectr. Anal."},{"key":"ref_11","first-page":"100843","article-title":"Assessing rice (Oryza sativa L.) quality: A comprehensive review of current techniques and future directions","volume":"14","author":"Jawaria","year":"2023","journal-title":"J. Agric. Food Res."},{"key":"ref_12","first-page":"1","article-title":"Research progress of rapid optical detection technology and equipment for grain quality","volume":"53","author":"Nie","year":"2022","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"106230","DOI":"10.1016\/j.compag.2021.106230","article-title":"Real-time recognition system of soybean seed full-surface defects based on deep learning","volume":"187","author":"Zhao","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_14","first-page":"266","article-title":"Development of full-surface online detection and sorting device for external defects of apples","volume":"38","author":"Peng","year":"2023","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"106811","DOI":"10.1016\/j.compag.2022.106811","article-title":"Deep CNN-based damage classification of milled rice grains using a high-magnification image dataset","volume":"195","author":"Bhupendra","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1016\/j.foodcont.2009.08.006","article-title":"Assessing breakage and cracks of parboiled rice kernels by image analysis techniques","volume":"21","author":"Francis","year":"2010","journal-title":"Food Control"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.jcs.2007.08.009","article-title":"Measurement and fissuring of rice kernels during quasi-moisture sorption by image analysis","volume":"48","author":"Shimizu","year":"2008","journal-title":"J. Cereal Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"104489","DOI":"10.1016\/j.chemolab.2021.104489","article-title":"Detection of insect damaged rice grains using visible and near infrared hyperspectral imaging technique","volume":"221","author":"Shubhangi","year":"2022","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"104882","DOI":"10.1016\/j.compag.2019.104882","article-title":"Purity analysis of multi-grain rice seeds with non-destructive visible and near-infrared spectroscopy","volume":"164","author":"Zhang","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref_20","first-page":"159","article-title":"Study on quality analysis device and experiment of rice based on visual recognition technology","volume":"5","author":"Liu","year":"2023","journal-title":"J. Agric. Mech. Res."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1007\/s12161-014-9916-5","article-title":"Use of Hyperspectral imaging to discriminate the variety and quality of rice","volume":"8","author":"Wang","year":"2015","journal-title":"Food Anal. Methods"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"22493","DOI":"10.1109\/ACCESS.2020.2969847","article-title":"Varietal classification of rice seeds using RGB and Hyperspectral images","volume":"8","author":"Samson","year":"2020","journal-title":"IEEE Access"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"117587","DOI":"10.1016\/j.powtec.2022.117587","article-title":"Cracking prediction of germinated brown rice based on intragranular drying kinetics","volume":"406","author":"Liu","year":"2022","journal-title":"Powder Technol."},{"key":"ref_24","first-page":"235","article-title":"Method for single rice grain weight grading based on ECA-FV-CNN","volume":"54","author":"Chen","year":"2023","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_25","first-page":"146","article-title":"Automatic detection of yellow-colored rice using image recognition","volume":"20","author":"Shang","year":"2004","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_26","first-page":"147","article-title":"Head rice automatic detection system based on image recognition","volume":"21","author":"Yu","year":"2006","journal-title":"J. Chin. Cereals Oils Assoc."},{"key":"ref_27","first-page":"27","article-title":"Prediction of grain mildew based on IFA-SVM model","volume":"37","author":"Guo","year":"2022","journal-title":"J. Chin. Cereals Oils Assoc."},{"key":"ref_28","first-page":"100890","article-title":"A comparative study of state-of-the-art deep learning architectures for rice grain classification","volume":"15","author":"Farshad","year":"2024","journal-title":"J. Agric. Food Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"113396","DOI":"10.1016\/j.postharvbio.2025.113396","article-title":"AI-driven deep learning framework for shelf life prediction of edible mushrooms","volume":"222","author":"Javanmardi","year":"2025","journal-title":"Postharvest Biol. Technol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"147600","DOI":"10.1016\/j.conbuildmat.2026.147600","article-title":"Intelligent identification of crack modes and damage evolution in SCA-modified metakaolin-based geopolymers using AE, DIC, and CNN","volume":"540","author":"Tian","year":"2026","journal-title":"Constr. Build. Mater."},{"key":"ref_31","first-page":"25","article-title":"Plant disease detection based on lightweight VGG","volume":"43","author":"Wang","year":"2022","journal-title":"J. Chin. Agric. Mech."},{"key":"ref_32","first-page":"23","article-title":"Transfer learning for multi-crop leaf disease image classification using convolutional neural network VGG","volume":"6","author":"Ananda","year":"2022","journal-title":"Artif. Intell. Agric."},{"key":"ref_33","first-page":"89","article-title":"Sorting model of camellia fruit shells and tea seeds based on SE-ResNet network","volume":"44","author":"Duan","year":"2023","journal-title":"J. Chin. Agric. Mech."},{"key":"ref_34","first-page":"105","article-title":"Automatic detecting and grading method of apples based on improved LeNet-5","volume":"41","author":"Wang","year":"2020","journal-title":"J. Chin. Agric. Mech."},{"key":"ref_35","first-page":"124","article-title":"Research on embedded face detection based on MobileNet-YOLO","volume":"43","author":"Xiang","year":"2022","journal-title":"J. Chin. Agric. Mech."},{"key":"ref_36","first-page":"145","article-title":"Research on segmentation method of rice stem impurities based on improved Mask R-CNN","volume":"42","author":"Ma","year":"2021","journal-title":"J. Chin. Agric. Mech."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"107757","DOI":"10.1016\/j.compag.2023.107757","article-title":"Detection of tomato plant phenotyping traits using YOLOv5-based single stage detectors","volume":"207","author":"Angelo","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_38","first-page":"255","article-title":"Online real-time detection system for cracked eggs using improved YOLOv7","volume":"39","author":"Zhao","year":"2023","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.procs.2023.10.641","article-title":"Real-time pineapple detection for agricultural robot via lightweight YOLOv7-tiny model","volume":"226","author":"Li","year":"2023","journal-title":"Procedia Comput. Sci."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"100300","DOI":"10.1016\/j.atech.2023.100300","article-title":"Improving the network architecture of YOLOv7 to achieve real-time grading of canola based on kernel health","volume":"5","author":"Angshuman","year":"2023","journal-title":"Smart Agric. Technol."},{"key":"ref_41","first-page":"212","article-title":"Detection method of rice leaf disease based on improved Yolov5s","volume":"45","author":"Xiang","year":"2024","journal-title":"J. Chin. Agric. Mech."},{"key":"ref_42","first-page":"195","article-title":"Dynamic maize seed detection and counting method based on improved YOLOv10n","volume":"42","author":"Xu","year":"2026","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_43","first-page":"223","article-title":"Apple location and classification based on improved SSD convolutional neural network","volume":"54","author":"Zhang","year":"2023","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"2755","DOI":"10.1007\/s00521-022-07743-y","article-title":"Convolutional neural network-based tea leaf disease prediction system on smart phone using paas cloud","volume":"35","author":"Madhusudan","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/j.compag.2018.01.009","article-title":"Deep learning models for plant disease detection and diagnosis","volume":"145","author":"Konstantinos","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref_46","first-page":"36","article-title":"Wheat grain integrity image detection system based on CNN","volume":"51","author":"Zhu","year":"2020","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_47","first-page":"309","article-title":"Image detection system of corn seed internal crack based on CNN","volume":"53","author":"Zhang","year":"2022","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_48","first-page":"174","article-title":"Segmentation of impurity rice grain images based on U-Net model","volume":"36","author":"Chen","year":"2020","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_49","first-page":"383","article-title":"Detection method for implicit apple damages based on SIRI and CNN","volume":"55","author":"Wang","year":"2024","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_50","first-page":"151","article-title":"Detection system for grape leaf diseases based on transfer learning and updated CNN","volume":"37","author":"Fan","year":"2021","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_51","first-page":"134","article-title":"Study of garlic scale bud orientation recognition based on CNN and SVM classification optimization","volume":"43","author":"Cao","year":"2022","journal-title":"J. Chin. Agric. Mech."},{"key":"ref_52","first-page":"151","article-title":"Forecasting winter wheat yield at county level using CNN and BP neural networks","volume":"38","author":"Sun","year":"2022","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_53","first-page":"1322","article-title":"Simulation of rice disease recognition based on improved attention mechanism embedded in PR-Net model","volume":"36","author":"Lu","year":"2024","journal-title":"J. Syst. Simul."},{"key":"ref_54","first-page":"185","article-title":"Method for identifying tea diseases in natural environment using improved YOLOv5s","volume":"39","author":"Chen","year":"2023","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_55","first-page":"150","article-title":"Method for identifying tea buds based on improved YOLOv5s model","volume":"39","author":"Wang","year":"2023","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_56","first-page":"792","article-title":"Research on internal crack recognition method of brown rice based on YOLOv5-RF","volume":"47","author":"Zhang","year":"2024","journal-title":"J. Nanjing Agric. Univ."},{"key":"ref_57","first-page":"268","article-title":"Real-time detection of imperfect wheat grains on wheat pile surface based on IDS-YOLO","volume":"45","author":"Fan","year":"2024","journal-title":"Food Sci."}],"container-title":["Foods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2304-8158\/15\/16\/2910\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T08:53:57Z","timestamp":1787216037000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2304-8158\/15\/16\/2910"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":57,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["foods15162910"],"URL":"https:\/\/doi.org\/10.3390\/foods15162910","relation":{},"ISSN":["2304-8158"],"issn-type":[{"value":"2304-8158","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]}}}