[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-437737-105":59,"doc-detail-437737-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","a-lightweight-intelligent-grading-method-for-lychee-anthracnose-based-on-improved-yolov12","A lightweight intelligent grading method for lychee anthracnose based on improved YOLOv12","","A lightweight improved detection model is proposed for rapid, non-destructive lychee anthracnose grading, targeting the trade-off between high accuracy and lightweight deployment. The study introduces LycheeGuard-Lite built on YOLOv12, using a C3k2_Light module with depthwise separable convolutions, a dual-path C2PSA attention mechanism, and a weighted convolution strategy to strengthen lesion feature extraction. Experiments on a self-built dataset of 14,576 images from two cultivars labeled with Mild/Moderate/Severe show 99.4% mAP50 with only 2.19M parameters and 4.1 GFLOPs, enabling practical postharvest sorting and quality management.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/a-lightweight-intelligent-grading-method-for-lychee-anthracnose-based-on-improved-yolov12/437737/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/a-lightweight-intelligent-grading-method-for-lychee-anthracnose-based-on-improved-yolov12/437737.png","ImageObject",300,407,{"name":92,"@type":93},"Ben ","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-30","2026-09-29",true,{"@type":102,"interactionType":103,"userInteractionCount":14},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the study address in lychee anthracnose grading?","Question",{"text":112,"@type":113},"Traditional manual grading is slow and subjective, and existing vision methods are limited by heavy models, weak small-spot sensitivity, and instability in complex postharvest environments.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What model is proposed and on which framework is it based?",{"text":117,"@type":113},"The study proposes LycheeGuard-Lite, a lightweight model built on an improved YOLOv12 framework.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the proposed approach improve efficiency and maintain accuracy?",{"text":121,"@type":113},"It uses a depthwise separable convolution-based C3k2_Light module, a dual-path C2PSA attention mechanism, and a weighted convolution strategy to enhance lesion feature extraction while reducing parameters and computational cost.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},437737,1790769726,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":14,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},2336478951081,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","TYPE Original Research PUBLISHED 22 December 2025 DOI 10.3389/fpls.2025.1688675  \nOPEN ACCESS  \nEDITED BY  \nNeil Vaughan,  \nUniversity of Exeter, United Kingdom  \nREVIEWED BY  \nYasin Kaya,  \nAdana Alparslan Turkes Science and Technology University, Türkiye Mingyue Zhang,  \nSouth China Agricultural University, China  \n*CORRESPONDENCE  \nXianjun Wu  \n [wuxianjun@gdupt.edu.cn](wuxianjun@gdupt.edu.cn)  \nRECEIVED 19 August 2025  \nREVISED 18 September 2025  \nACCEPTED 25 November 2025  \nPUBLISHED 22 December 2025  \nCITATION  \nXu B, Ma Z, Su X, He X and Wu X (2025)  \nA lightweight intelligent grading method for lychee anthracnose based on improved YOLOv12 .  \nFront. Plant Sci. 16:1688675 .  \ndoi: 10.3389/fpls.2025.1688675  \nCOPYRIGHT  \n© 2025 Xu, Ma, Su, He and Wu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nA lightweight intelligent grading method for lychee anthracnose based on improved YOLOv12  \nBing Xu, Zejie Ma, Xueping Su, Xiaoru He and Xianjun Wu*  \nSchool of Computer, Guangdong University of Petrochemical Technology, Maoming, Guangdong, China  \nAnthracnose is one of the primary diseases leading to quality deterioration in lychee. Traditional manual grading methods suffer from low efficiency and high subjectivity. To achieve rapid, non-destructive detection and intelligent grading of lychee anthracnose, while addressing the challenge of balancing high accuracy and lightweight design in detection models, this study proposes a lightweight improved model named LycheeGuard-Lite based on the YOLOv12 framework. By introducing the C3k2 _Light module reconstructed with depthwise separable convolutions, a dual-path C2PSA attention mechanism (position-channel dual-path attention), and the wConv2D weighted convolution strategy, the model enhances lesion feature extraction capability while reducing computational complexity. Evaluation was performed on a selfbuilt dataset comprising 14, 576 images of two dominant lychee varieties (‘ Feizixiao’ and ‘ Baitangying ’) collected under multiple lighting conditions and annotated with three severity levels (Mild, Moderate, Severe) . The results demonstrate that the model maintains 99.4% mAP50 detection accuracy while reducing its number of parameters to 2.19M (a 12.8% decrease) and computational cost to 4.1 GFLOPs (a 29.3% reduction).This research provides a lightweight and deployable algorithmic foundation for automated lychee disease recognition and intelligent grading, offering practical engineering value for postharvest fruit sorting and quality management.  \nKEYWORDS  \nlychee anthracnose, disease classification, YOLOv12, lightweight model, attention mechanism  \n1 Introduction  \nLychee is an economically important fruit in tropical and subtropical regions, with China being the world’s largest producer (contributing approximately 65% of the global yield) . Major cultivars such as ‘Feizixiao’ and ‘Baitangying’ are highly susceptible toanthracnose after harvesting, leading to significant economic losses.Anthracnose, primarily caused by the fungus Colletotrichum gloeosporioides, is a destructive postharvest disease that severely impacts fruit quality and market value. Notably, susceptibility to anthracnose varies significantly among different litchi cultivars,  \nFrontiers in Plant Science 01 [frontiersin.org](frontiersin.org)  \nhighlighting the importance of cultivar-specific disease management strategies (Xu et al., 2025) .  \nAt present, lychee anthracnose grading faces serious challenges. The traditional manual detection method relies on the operator’s experience to judge lesion area and color changes,","cbCaivF7ICphkKiL","https://ap.wps.com/l/cbCaivF7ICphkKiL","pdf",9656913,27,"English","# Introduction\n## Background and importance of lychee anthracnose\n## Challenges of traditional manual grading\n## Limitations of existing computer vision methods\n## Aim and contributions of this study","[{\"question\":\"What problem does the study address in lychee anthracnose grading?\",\"answer\":\"Traditional manual grading is slow and subjective, and existing vision methods are limited by heavy models, weak small-spot sensitivity, and instability in complex postharvest environments.\"},{\"question\":\"What model is proposed and on which framework is it based?\",\"answer\":\"The study proposes LycheeGuard-Lite, a lightweight model built on an improved YOLOv12 framework.\"},{\"question\":\"How does the proposed approach improve efficiency and maintain accuracy?\",\"answer\":\"It uses a depthwise separable convolution-based C3k2_Light module, a dual-path C2PSA attention mechanism, and a weighted convolution strategy to enhance lesion feature extraction while reducing parameters and computational cost.\"}]","A lightweight intelligent grading method for lychee anthracnose based on improved YOLOv12 | PDF",1790683069,68]