{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T23:57:26Z","timestamp":1767916646470,"version":"3.49.0"},"reference-count":49,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T00:00:00Z","timestamp":1767830400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"General Project of Science and Technology Programme of Beijing Municipal Commission of Education","award":["KM202410015003"],"award-info":[{"award-number":["KM202410015003"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Driven by the knowledge economy and digitalization, the scale of book logistics continues to expand. However, the quality inspection process in this field currently uses generic target detection models and rarely considers defect characteristics. Therefore, this paper proposes the Merge-YOLO model to address the three prominent characteristics of book packaging defects: low contrast, small-sized defects, and irregular shapes. Three improvements are made to enhance detection performance: the WT-C3k2 module is designed to separate high- and low-frequency features using wavelet transforms, combined with multi-level convolutions and a bottleneck structure to enhance feature extraction capabilities for small objects and complex lighting conditions, while expanding the receptive field and reducing semantic detail loss; introducing the QA Transformer, which uses a learnable transformation matrix to generate adaptive quadrilateral windows, breaking through the limitations of traditional fixed windows and improving the ability to capture features of irregular defects; and adopting the DySample dynamic upscaler, which replaces nearest-neighbor interpolation by dynamically adjusting the scaling ratio through an adaptive scope factor, reducing computational overhead while preserving pixel-level details. Experiments show that the model achieves 95.8% precision, 93.6% recall, and 94.1%mAP@0.5 on the book packaging defect dataset, outperforming the baseline model YOLOv11 and traditional algorithms in all metrics. This provides an efficient and accurate detection model for quality control in book supply chain packaging.<\/jats:p>","DOI":"10.1371\/journal.pone.0340205","type":"journal-article","created":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T18:30:03Z","timestamp":1767897003000},"page":"e0340205","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Merge-YOLO: An accurate detection model for book packaging defects in intelligent logistics scenarios"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8425-606X","authenticated-orcid":true,"given":"Zhaohua","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yirong","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanping","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawen","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,1,8]]},"reference":[{"issue":"2","key":"pone.0340205.ref001","doi-asserted-by":"crossref","first-page":"1293","DOI":"10.1007\/s12596-023-01284-w","article-title":"Automated visual inspection of solar cell images using adapted morphological and edge detection algorithms","volume":"53","author":"M Cao","year":"2023","journal-title":"J Opt"},{"key":"pone.0340205.ref002","doi-asserted-by":"crossref","first-page":"121013","DOI":"10.1016\/j.apenergy.2023.121013","article-title":"Detection and classification of DC and feeder faults in DC microgrid using new morphological operators with multi class AdaBoost algorithm","volume":"340","author":"PK Dash","year":"2023","journal-title":"Applied Energy"},{"key":"pone.0340205.ref003","doi-asserted-by":"crossref","first-page":"64002","DOI":"10.1109\/ACCESS.2020.2984539","article-title":"Detecting defects with support vector machine in logistics packaging boxes for edge computing","volume":"8","author":"X Yang","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0340205.ref004","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2025.3583364","article-title":"VLCIM: a vision-language cyclic interaction model for industrial defect detection","volume":"74","author":"X Shen","year":"2025","journal-title":"IEEE Trans Instrum Meas"},{"key":"pone.0340205.ref005","doi-asserted-by":"crossref","first-page":"113117","DOI":"10.1016\/j.ymssp.2025.113117","article-title":"A multi-expert diffusion model for surface defect detection of valve cores in special control valve equipment systems","volume":"237","author":"X Shen","year":"2025","journal-title":"Mechanical Systems and Signal Processing"},{"key":"pone.0340205.ref006","doi-asserted-by":"crossref","first-page":"100504","DOI":"10.1016\/j.etran.2025.100504","article-title":"Insights into the failure mechanisms of leaky lithium-ion batteries for electric vehicles by a systematic multiscale analytical framework","volume":"26","author":"J Hu","year":"2025","journal-title":"eTransportation"},{"key":"pone.0340205.ref007","doi-asserted-by":"crossref","first-page":"113661","DOI":"10.1016\/j.asoc.2025.113661","article-title":"Robust weakly supervised product surface defect segmentation based on guided cropping and inpainting extension","volume":"184","author":"R Yan","year":"2025","journal-title":"Applied Soft Computing"},{"key":"pone.0340205.ref008","first-page":"100974","article-title":"Cognitive Digital Twin for industrial maintenance: operational framework for fault detection and diagnosis","volume":"48","author":"S Zappa","year":"2025","journal-title":"J Industrial Information Integration"},{"key":"pone.0340205.ref009","doi-asserted-by":"crossref","first-page":"103334","DOI":"10.1016\/j.infrared.2020.103334","article-title":"Detection of surface defects on solar cells by fusing Multi-channel convolution neural networks","volume":"108","author":"X Zhang","year":"2020","journal-title":"Infrared Physics Technol"},{"key":"pone.0340205.ref010","doi-asserted-by":"crossref","first-page":"113374","DOI":"10.1016\/j.measurement.2023.113374","article-title":"A novel multi-model cascade framework for pipeline defects detection based on machine vision","volume":"220","author":"B Gao","year":"2023","journal-title":"Measurement"},{"issue":"4","key":"pone.0340205.ref011","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1002\/pip.3395","article-title":"Deep learning\u2010based automatic detection of multitype defects in photovoltaic modules and application in real production line","volume":"29","author":"Y Zhao","year":"2021","journal-title":"Progress in Photovoltaics"},{"key":"pone.0340205.ref012","doi-asserted-by":"crossref","first-page":"105429","DOI":"10.1016\/j.engappai.2022.105429","article-title":"Geometric characteristic learning R-CNN for shockproof hammer defect detection","volume":"116","author":"Y Zhai","year":"2022","journal-title":"Eng Applications Artificial Intelligence"},{"key":"pone.0340205.ref013","doi-asserted-by":"crossref","first-page":"104146","DOI":"10.1016\/j.compind.2024.104146","article-title":"Intelligent cotter pins defect detection for electrified railway based on improved faster R-CNN and dilated convolution","volume":"162","author":"X Wu","year":"2024","journal-title":"Computers in Industry"},{"issue":"7","key":"pone.0340205.ref014","doi-asserted-by":"crossref","first-page":"1833","DOI":"10.1007\/s10845-020-01670-2","article-title":"A steel surface defect inspection approach towards smart industrial monitoring","volume":"32","author":"R Hao","year":"2020","journal-title":"J Intell Manuf"},{"issue":"10","key":"pone.0340205.ref015","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1016\/j.cja.2022.05.002","article-title":"Visual inspection of aircraft skin: Automated pixel-level defect detection by instance segmentation","volume":"35","author":"M DING","year":"2022","journal-title":"Chinese Journal of Aeronautics"},{"issue":"1","key":"pone.0340205.ref016","doi-asserted-by":"crossref","DOI":"10.1186\/s40494-024-01441-9","article-title":"Automatic defect detection in infrared thermal images of ancient polyptychs based on numerical simulation and a new efficient channel attention mechanism aided Faster R-CNN model","volume":"12","author":"X Wang","year":"2024","journal-title":"Herit Sci"},{"key":"pone.0340205.ref017","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2020.3040485","article-title":"RetinaNet with difference channel attention and adaptively spatial feature fusion for steel surface defect detection","volume":"70","author":"X Cheng","year":"2021","journal-title":"IEEE Trans Instrum Meas"},{"key":"pone.0340205.ref018","doi-asserted-by":"crossref","first-page":"102847","DOI":"10.1016\/j.displa.2024.102847","article-title":"Novel intelligent defects detection of boiler water walls in thermal power plants based on OFM_SSD","volume":"85","author":"Y Han","year":"2024","journal-title":"Displays"},{"issue":"3","key":"pone.0340205.ref019","doi-asserted-by":"crossref","first-page":"1267","DOI":"10.1007\/s10845-023-02105-4","article-title":"A texture-aware one-stage fabric defect detection network with adaptive feature fusion and multi-task training","volume":"35","author":"B Lu","year":"2023","journal-title":"J Intell Manuf"},{"issue":"5","key":"pone.0340205.ref020","doi-asserted-by":"crossref","first-page":"1218","DOI":"10.3390\/rs15051218","article-title":"Leveraging saliency in single-stage multi-label concrete defect detection using unmanned aerial vehicle imagery","volume":"15","author":"L Hebbache","year":"2023","journal-title":"Remote Sensing"},{"key":"pone.0340205.ref021","doi-asserted-by":"crossref","first-page":"127447","DOI":"10.1016\/j.eswa.2025.127447","article-title":"SO-YOLOv8: A novel deep learning-based approach for small object detection with YOLO beyond COCO","volume":"280","author":"Iqra","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"24","key":"pone.0340205.ref022","doi-asserted-by":"crossref","first-page":"11903","DOI":"10.3390\/app142411903","article-title":"Correlation data augmentation-based yolo-integrated object detection of thermal-equalization video using line scanning inductive thermography","volume":"14","author":"S-J Lee","year":"2024","journal-title":"Appl Sci"},{"key":"pone.0340205.ref023","doi-asserted-by":"crossref","first-page":"125737","DOI":"10.1016\/j.eswa.2024.125737","article-title":"Mixed data augmentation and osprey search strategy for enhancing YOLO in tomato disease, pest, and weed detection","volume":"264","author":"J Lin","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"pone.0340205.ref024","doi-asserted-by":"crossref","first-page":"105830","DOI":"10.1016\/j.autcon.2024.105830","article-title":"Real-time lightweight YOLO model for grouting defect detection in external post-tensioned ducts via infrared thermography","volume":"168","author":"S Li","year":"2024","journal-title":"Automation in Construction"},{"key":"pone.0340205.ref025","doi-asserted-by":"crossref","first-page":"127796","DOI":"10.1016\/j.eswa.2025.127796","article-title":"Adaptive YOLOv6 with spatial Transformer Networks for accurate object detection and Multi-Angle classification in remote sensing images","volume":"282","author":"GB Rajendran","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"pone.0340205.ref026","doi-asserted-by":"crossref","first-page":"16214","DOI":"10.1038\/s41598-025-00239-4","article-title":"An object detection model AAPW-YOLO for UAV remote sensing images based on adaptive convolution and reconstructed feature fusion","volume":"15","author":"Y Wu","year":"2025","journal-title":"Sci Rep"},{"key":"pone.0340205.ref027","doi-asserted-by":"crossref","first-page":"141307","DOI":"10.1016\/j.conbuildmat.2025.141307","article-title":"Rapid estimation method of the residual mortar of recycled aggregates by object detection models","volume":"476","author":"Y Yang","year":"2025","journal-title":"Construction and Building Materials"},{"issue":"1","key":"pone.0340205.ref028","article-title":"YOLO-WP: A Lightweight and Efficient Algorithm for Small-Target Detection in Weld Seams of Small-Diameter Stainless Steel Pipes","volume":"16","author":"H Hou","year":"2025","journal-title":"ijacsa"},{"key":"pone.0340205.ref029","doi-asserted-by":"crossref","first-page":"130287","DOI":"10.1016\/j.neucom.2025.130287","article-title":"Improving generalization capability of object detectors via efficient global attention","volume":"639","author":"J Chen","year":"2025","journal-title":"Neurocomputing"},{"issue":"16","key":"pone.0340205.ref030","doi-asserted-by":"crossref","first-page":"2885","DOI":"10.3390\/rs16162885","article-title":"Enhancing remote sensing object detection with K-CBST YOLO: integrating CBAM and swin-transformer","volume":"16","author":"A Cheng","year":"2024","journal-title":"Remote Sensing"},{"key":"pone.0340205.ref031","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1016\/j.aej.2023.10.014","article-title":"Marine target detection for PPI images based on YOLO-SWFormer","volume":"82","author":"Q Zhang","year":"2023","journal-title":"Alexandria Engineering Journal"},{"key":"pone.0340205.ref032","doi-asserted-by":"crossref","first-page":"107169","DOI":"10.1016\/j.cropro.2025.107169","article-title":"YOLO-CWD: a novel model for crop and weed detection based on improved YOLOv8","volume":"192","author":"C Ma","year":"2025","journal-title":"Crop Protection"},{"key":"pone.0340205.ref033","doi-asserted-by":"crossref","first-page":"106068","DOI":"10.1016\/j.autcon.2025.106068","article-title":"Real-time defect detection in underground sewage pipelines using an improved YOLOv5 model","volume":"173","author":"J Lu","year":"2025","journal-title":"Automation in Construction"},{"key":"pone.0340205.ref034","doi-asserted-by":"crossref","first-page":"111294","DOI":"10.1016\/j.patcog.2024.111294","article-title":"Circle-YOLO: an anchor-free lung nodule detection algorithm using bounding circle representation","volume":"161","author":"C Tang","year":"2025","journal-title":"Pattern Recognition"},{"key":"pone.0340205.ref035","doi-asserted-by":"crossref","first-page":"112769","DOI":"10.1016\/j.ecolind.2024.112769","article-title":"Machine vision approach for monitoring and quantifying fish school migration","volume":"169","author":"F Lin","year":"2024","journal-title":"Ecological Indicators"},{"issue":"9","key":"pone.0340205.ref036","doi-asserted-by":"crossref","first-page":"3467","DOI":"10.3390\/s22093467","article-title":"MSFT-YOLO: improved YOLOv5 based on transformer for detecting defects of steel surface","volume":"22","author":"Z Guo","year":"2022","journal-title":"Sensors (Basel)"},{"issue":"4","key":"pone.0340205.ref037","doi-asserted-by":"crossref","first-page":"368504241280765","DOI":"10.1177\/00368504241280765","article-title":"YOLO-Faster: An efficient remote sensing object detection method based on AMFFN","volume":"107","author":"Y Tong","year":"2024","journal-title":"Sci Prog"},{"key":"pone.0340205.ref038","doi-asserted-by":"crossref","first-page":"109049","DOI":"10.1016\/j.engappai.2024.109049","article-title":"A synthetic aperture radar small ship detector based on transformers and multi-dimensional parallel feature extraction","volume":"137","author":"X Fu","year":"2024","journal-title":"Eng Applications Artificial Intelligence"},{"key":"pone.0340205.ref039","doi-asserted-by":"crossref","first-page":"126384","DOI":"10.1016\/j.neucom.2023.126384","article-title":"PETNet: A YOLO-based prior enhanced transformer network for aerial image detection","volume":"547","author":"T Wang","year":"2023","journal-title":"Neurocomputing"},{"key":"pone.0340205.ref040","doi-asserted-by":"crossref","unstructured":"Zhang K, Zuo W, Zhang L. Learning a Single Convolutional Super-Resolution Network for Multiple Degradations. 2018 IEEE\/CVF Conference on Computer Visison and Pattern Recognition. 2018.","DOI":"10.1109\/CVPR.2018.00344"},{"key":"pone.0340205.ref041","unstructured":"Nelson JS. YOLOv5 is Here: State-of-the-Art Object Detection at 140 FPS. https:\/\/blog.roboflow.com\/yolov5-is-here\/"},{"key":"pone.0340205.ref042","author":"C Li","year":"2022"},{"key":"pone.0340205.ref043","author":"CY Wang","year":"2022"},{"key":"pone.0340205.ref044","unstructured":"Qiu GJACAJ. Ultralytics YOLOv8 2023. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"pone.0340205.ref045","doi-asserted-by":"crossref","unstructured":"Wang CY, Yeh IH, Liao HY. YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. European Conference on Computer Vision. 2025.","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"pone.0340205.ref046","doi-asserted-by":"crossref","unstructured":"Wang A, Chen H, Liu L, Chen K, Lin Z, Han J. YOLOv10: Real-Time End-to-End Object Detection. 2024.","DOI":"10.52202\/079017-3429"},{"key":"pone.0340205.ref047","unstructured":"Khanam R, Hussain M. YOLOv11: An Overview of the Key Architectural Enhancements. 2024."},{"key":"pone.0340205.ref048","volume-title":"SSD: Single Shot MultiBox Detector","author":"L Wei","year":"2016"},{"issue":"6","key":"pone.0340205.ref049","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"S Ren","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T18:30:11Z","timestamp":1767897011000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340205"}},"subtitle":[],"editor":[{"given":"Gengpei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,1,8]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0340205","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,8]]}}}