{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:45:19Z","timestamp":1792691119791,"version":"4.5.0"},"reference-count":55,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T00:00:00Z","timestamp":1792627200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005058","name":"NED University of Engineering and Technology","doi-asserted-by":"publisher","award":["Acad\/50(48)\/6879"],"award-info":[{"award-number":["Acad\/50(48)\/6879"]}],"id":[{"id":"10.13039\/501100005058","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Detecting small faces remains challenging due to scale variation and limited discriminative cues at low resolutions. We address this with a two-pronged approach. First, we modify YOLOv5 by adding extra convolutional layers and small-object\u2013focused detection heads that operate on larger, higher-resolution backbone feature maps, improving sensitivity to tiny targets. Second, we introduce a dynamic, image adaptive patching strategy for scale selection. We compute Cr channel color probability maps and measure the number and density of pixel clusters; a Fuzzy Inference System (FIS) uses these cues to select the most suitable patch size for near and far faces. On the WIDER FACE benchmark, our method attains 93.07% mAP@50 (Easy), 91.25% mAP@50 (Medium), and 84.45% mAP@50 (Hard). On our proposed local dataset, the proposed model achieves 49.36% mAP@50 for different size faces. Beyond faces, the approach generalizes to small object detection on VisDrone-DET2019, reaching 46.76 mAP@50. These results demonstrate that coupling small-object-aware architecture design with color-guided, fuzzy patch selection yields competitive mAP@50 for small and distant targets.<\/jats:p>","DOI":"10.1371\/journal.pone.0360794","type":"journal-article","created":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:36:51Z","timestamp":1792690611000},"page":"e0360794","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["YOLO-SOD: Color probability map-based fuzzy framework using deep models for face detection"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8915-0596","authenticated-orcid":true,"given":"Aniqa","family":"Saba","sequence":"first","affiliation":[{"name":"NED University of Engineering & Technology","place":["Karachi, Pakistan"],"department":["Department of Electronic Engineering, Faculty of Electrical and Computer Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4488-8860","authenticated-orcid":true,"given":"Muhammad Faizan","family":"Shirazi","sequence":"additional","affiliation":[{"name":"NED University of Engineering & Technology","place":["Karachi, Pakistan"],"department":["Department of Electronic Engineering, Faculty of Electrical and Computer Engineering"]},{"name":"NED University of Engineering & Technology","place":["Karachi, Pakistan"],"department":["Department of Computer Science & Information Technology, Faculty of Electrical and Computer Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yawar","family":"Rehman","sequence":"additional","affiliation":[{"name":"NED University of Engineering & Technology","place":["Karachi, Pakistan"],"department":["Department of Electronic Engineering, Faculty of Electrical and Computer Engineering"]},{"name":"Institute for Advanced Technology Convergence (Mobility), Kyungpook National University","place":["Daegu, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0011-9525","authenticated-orcid":true,"given":"Muhammad Mubashir","family":"Khan","sequence":"additional","affiliation":[{"name":"NED University of Engineering & Technology","place":["Karachi, Pakistan"],"department":["Department of Computer Science & Information Technology, Faculty of Electrical and Computer Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,22]]},"reference":[{"key":"pone.0360794.ref001","doi-asserted-by":"crossref","first-page":"100301","DOI":"10.1016\/j.cosrev.2020.100301","article-title":"A comprehensive and systematic look up into deep learning based object detection techniques: A review","volume":"38","author":"VK Sharma","year":"2020","journal-title":"Comput Sci Rev"},{"key":"pone.0360794.ref002","doi-asserted-by":"crossref","unstructured":"Yang S, Luo P, Loy CC, Tang X. WIDER FACE: A face detection benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. p. 5525\u201333.","DOI":"10.1109\/CVPR.2016.596"},{"issue":"19","key":"pone.0360794.ref003","doi-asserted-by":"crossref","first-page":"2354","DOI":"10.3390\/electronics10192354","article-title":"Human Face Detection Techniques: A Comprehensive Review and Future Research Directions","volume":"10","author":"MK Hasan","year":"2021","journal-title":"Electronics"},{"key":"pone.0360794.ref004","doi-asserted-by":"crossref","unstructured":"Deng J, Guo J, Ververas E, Kotsia I, Zafeiriou S. RetinaFace: Single-shot multi-level face localisation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020. p. 5203\u201312.","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"pone.0360794.ref005","doi-asserted-by":"crossref","unstructured":"Li J, Wang Y, Wang C, Tai Y, Qian J, Yang J, et al. DSFD: Dual shot face detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019. p. 5060\u20139.","DOI":"10.1109\/CVPR.2019.00520"},{"key":"pone.0360794.ref006","doi-asserted-by":"crossref","unstructured":"Liu Y, Wang F, Deng J, Zhou Z, Sun B, Li H. MogFace: Towards a deeper appreciation on face detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022. p. 4093\u2013102.","DOI":"10.1109\/CVPR52688.2022.00406"},{"key":"pone.0360794.ref007","unstructured":"Li Z, Tang X, Han J, Liu J, He R. PyramidBox++: High performance detector for finding tiny face. 2019;arXiv:1904.00386. Available from: https:\/\/arxiv.org\/abs\/1904.00386"},{"key":"pone.0360794.ref008","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A. You Only Look Once: Unified, Real-Time Object Detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. p. 779\u201388.","DOI":"10.1109\/CVPR.2016.91"},{"issue":"19","key":"pone.0360794.ref009","doi-asserted-by":"crossref","first-page":"6209","DOI":"10.3390\/s24196209","article-title":"SOD-YOLOv8-Enhancing YOLOv8 for Small Object Detection in Aerial Imagery and Traffic Scenes","volume":"24","author":"B Khalili","year":"2024","journal-title":"Sensors (Basel)"},{"issue":"17","key":"pone.0360794.ref010","doi-asserted-by":"crossref","first-page":"7665","DOI":"10.3390\/app14177665","article-title":"Dense Small Object Detection Based on an Improved YOLOv7 Model","volume":"14","author":"X Chen","year":"2024","journal-title":"Appl Sci"},{"issue":"4","key":"pone.0360794.ref011","doi-asserted-by":"crossref","first-page":"5807","DOI":"10.3233\/JIFS-224530","article-title":"An advanced YOLOv3 method for small object detection","volume":"45","author":"B Liu","year":"2023","journal-title":"IFS"},{"key":"pone.0360794.ref012","doi-asserted-by":"crossref","unstructured":"Jiang H, Learned-Miller E. Face Detection with the Faster R-CNN. In: 2017 12th IEEE International Conference on Automatic Face and Gesture Recognition. 2017. p. 650\u20137.","DOI":"10.1109\/FG.2017.82"},{"issue":"10","key":"pone.0360794.ref013","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","article-title":"Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks","volume":"23","author":"K Zhang","year":"2016","journal-title":"IEEE Signal Process Lett"},{"key":"pone.0360794.ref014","doi-asserted-by":"crossref","unstructured":"Li H, Lin Z, Shen X, Brandt J, Hua G. A convolutional neural network cascade for face detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015. p. 5325\u201334.","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"pone.0360794.ref015","doi-asserted-by":"crossref","unstructured":"Yu J, Jiang Y, Wang Z, Cao Z, Huang T. UnitBox: An Advanced Object Detection Network. In: Proceedings of the 24th ACM International Conference on Multimedia. 2016. p. 516\u201320.","DOI":"10.1145\/2964284.2967274"},{"key":"pone.0360794.ref016","doi-asserted-by":"crossref","unstructured":"Zhang S, Zhu X, Lei Z, Shi H, Wang X, Li SZ. S3FD: Single shot scale-invariant face detector. In: Proceedings of the IEEE International Conference on Computer Vision. 2017. p. 192\u2013201.","DOI":"10.1109\/ICCV.2017.30"},{"key":"pone.0360794.ref017","doi-asserted-by":"crossref","unstructured":"Najibi M, Samangouei P, Chellappa R, Davis LS. SSH: Single stage headless face detector. In: Proceedings of the IEEE International Conference on Computer Vision. 2017. p. 4885\u201394.","DOI":"10.1109\/ICCV.2017.522"},{"issue":"8","key":"pone.0360794.ref018","doi-asserted-by":"crossref","first-page":"1845","DOI":"10.1109\/TPAMI.2017.2738644","article-title":"Faceness-Net: Face Detection through Deep Facial Part Responses","volume":"40","author":"S Yang","year":"2018","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"pone.0360794.ref019","first-page":"989","article-title":"Finding tiny faces","volume":"41","author":"P Hu","year":"2019","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"pone.0360794.ref020","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1109\/TPAMI.2017.2781233","article-title":"HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition","volume":"41","author":"R Ranjan","year":"2019","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0360794.ref021","doi-asserted-by":"crossref","unstructured":"Zhu C, Tao R, Luu K, Savvides M. Seeing Small Faces from Robust Anchor\u2019s Perspective. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. p. 5127\u201336.","DOI":"10.1109\/CVPR.2018.00538"},{"key":"pone.0360794.ref022","unstructured":"Zhu Y, Cai H, Zhang S, Wang C, Xiong Y. TinaFace: Strong but Simple Baseline for Face Detection. 2020;arXiv:2011.13183. Available from: https:\/\/arxiv.org\/abs\/2011.13183"},{"issue":"01","key":"pone.0360794.ref023","doi-asserted-by":"crossref","first-page":"8231","DOI":"10.1609\/aaai.v33i01.33018231","article-title":"Selective Refinement Network for High Performance Face Detection","volume":"33","author":"C Chi","year":"2019","journal-title":"AAAI"},{"key":"pone.0360794.ref024","unstructured":"Wang H, Li Z, Ji X, Wang Y. Face R-CNN. 2017;arXiv:1706.01061. Available from: https:\/\/arxiv.org\/abs\/1706.01061"},{"key":"pone.0360794.ref025","unstructured":"Yoo Y, Han D, Yun S. EXTD: Extremely tiny face detector via iterative filter reuse. 2019;arXiv:1906.06579. Available from: https:\/\/arxiv.org\/abs\/1906.06579"},{"key":"pone.0360794.ref026","doi-asserted-by":"crossref","unstructured":"Najibi M, Singh B, Davis LS. FA-RPN: Floating Region Proposals for Face Detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019. p. 7723\u201332.","DOI":"10.1109\/CVPR.2019.00791"},{"issue":"5","key":"pone.0360794.ref027","doi-asserted-by":"crossref","first-page":"290","DOI":"10.3390\/info15050290","article-title":"A Lightweight Face Detector via Bi-Stream Convolutional Neural Network and Vision Transformer","volume":"15","author":"Z Zhang","year":"2024","journal-title":"Information"},{"key":"pone.0360794.ref028","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S. End-to-end object detection with transformers. In: Computer Vision \u2013 ECCV 2020. 2020. p. 213\u201329.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"pone.0360794.ref029","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et al. Swin Transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021. p. 10012\u201322. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"pone.0360794.ref030","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J. Deformable DETR: Deformable transformers for end-to-end object detection. In: International Conference on Learning Representations. 2021. Available from: https:\/\/arxiv.org\/abs\/2010.04159"},{"key":"pone.0360794.ref031","unstructured":"Zhang H, Li F, Liu S, Zhang L, Su H, Zhu J, et al. DINO: DETR with improved denoising anchor boxes for end-to-end object detection. In: International Conference on Learning Representations. 2023. Available from: https:\/\/arxiv.org\/abs\/2203.03605"},{"key":"pone.0360794.ref032","unstructured":"Liu Z, Gao G, Sun L, Fang Z. HRDNet: High-resolution detection network for small objects. 2020;arXiv:2006.07607. Available from: https:\/\/arxiv.org\/abs\/2006.07607"},{"key":"pone.0360794.ref033","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV. EfficientDet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020. p. 10781\u201390.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"pone.0360794.ref034","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, et al. Microsoft COCO: Common objects in context. Computer Vision \u2013 ECCV 2014. 2014. p. 740\u201355.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"pone.0360794.ref035","first-page":"1","article-title":"CenterFace: Joint Face Detection and Alignment Using Face as Point","volume":"2020","author":"Y Xu","year":"2020","journal-title":"Sci Programm"},{"key":"pone.0360794.ref036","doi-asserted-by":"crossref","unstructured":"Zhang S, Zhu X, Lei Z, Shi H, Wang X, Li SZ. FaceBoxes: A CPU real-time face detector with high accuracy. In: 2017 IEEE International Joint Conference on Biometrics. 2017. p. 1\u20139.","DOI":"10.1109\/BTAS.2017.8272675"},{"key":"pone.0360794.ref037","author":"V Jain","year":"2010"},{"key":"pone.0360794.ref038","doi-asserted-by":"crossref","unstructured":"Tang X, Du DK, He Z, Liu J. PyramidBox: A context-assisted single shot face detector. In: Computer Vision \u2013 ECCV 2018. 2018. p. 812\u201328.","DOI":"10.1007\/978-3-030-01240-3_49"},{"key":"pone.0360794.ref039","doi-asserted-by":"crossref","unstructured":"Wang W, Yang W, Liu J. HLA-Face: Joint High-Low Adaptation for Low Light Face Detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2021. p. 16195\u2013204.","DOI":"10.1109\/CVPR46437.2021.01593"},{"issue":"11","key":"pone.0360794.ref040","doi-asserted-by":"crossref","first-page":"4008","DOI":"10.1109\/TPAMI.2020.2997456","article-title":"RefineFace: Refinement Neural Network for High Performance Face Detection","volume":"43","author":"S Zhang","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0360794.ref041","doi-asserted-by":"crossref","unstructured":"Zolfi A, Amit G, Baras A, Koda S, Morikawa I, Elovici Y, et al. YolOOD: Utilizing object detection concepts for multi-label out-of-distribution detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2024. p. 5788\u201397.","DOI":"10.1109\/CVPR52733.2024.00553"},{"key":"pone.0360794.ref042","doi-asserted-by":"crossref","first-page":"121366","DOI":"10.1016\/j.ins.2024.121366","article-title":"LUD-YOLO: A novel lightweight object detection network for unmanned aerial vehicle","volume":"686","author":"Q Fan","year":"2025","journal-title":"Inform Sci"},{"key":"pone.0360794.ref043","doi-asserted-by":"crossref","unstructured":"Kirillov A, Mintun E, Ravi N, Mao H, Rolland C, Gustafson L, et al. Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023. p. 4015\u201326.","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"3","key":"pone.0360794.ref044","first-page":"1321","article-title":"Enhancing real time object detection for autonomous driving using YOLO-NAS algorithm with CLEO optimizer","volume":"17","author":"Mamta","year":"2024","journal-title":"Int J Inf Tecnol"},{"issue":"4","key":"pone.0360794.ref045","doi-asserted-by":"crossref","first-page":"70","DOI":"10.3390\/ai6040070","article-title":"Discriminative Deformable Part Model for Pedestrian Detection with Occlusion Handling","volume":"6","author":"S Siddiqi","year":"2025","journal-title":"AI"},{"issue":"23","key":"pone.0360794.ref046","doi-asserted-by":"crossref","first-page":"11555","DOI":"10.3390\/app112311555","article-title":"Detection of Small Size Traffic Signs Using Regressive Anchor Box Selection and DBL Layer Tweaking in YOLOv3","volume":"11","author":"Y Rehman","year":"2021","journal-title":"Appl Sci"},{"key":"pone.0360794.ref047","doi-asserted-by":"crossref","first-page":"18667","DOI":"10.1109\/ACCESS.2022.3150882","article-title":"Small Traffic Sign Detection in Big Images: Searching Needle in a Hay","volume":"10","author":"Y Rehman","year":"2022","journal-title":"IEEE Access"},{"key":"pone.0360794.ref048","unstructured":"Jocher G, Chaurasia A, Qiu J. Ultralytics YOLOv5. Software. 2022. Available from: https:\/\/github.com\/ultralytics\/yolov5"},{"key":"pone.0360794.ref049","doi-asserted-by":"crossref","unstructured":"Wang CY, Liao HYM, Wu YH, Chen PY, Hsieh JW, Yeh IH. CSPNet: A New Backbone That Can Enhance Learning Capability of CNN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2020. p. 390\u20131. Available from: https:\/\/openaccess.thecvf.com\/content_CVPRW_2020\/html\/w28\/Wang_CSPNet_A_New_Backbone_That_Can_Enhance_Learning_Capability_of_CVPRW_2020_paper.html","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"pone.0360794.ref050","doi-asserted-by":"crossref","unstructured":"Lin TY, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S. Feature Pyramid Networks for Object Detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017. p. 2117\u201325.","DOI":"10.1109\/CVPR.2017.106"},{"key":"pone.0360794.ref051","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J. Path Aggregation Network for Instance Segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. p. 8759\u201368.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"pone.0360794.ref052","unstructured":"Du D, Zhu P, Wen L, Bian X, Lin H, Hu Q, et al. VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops. 2019. Available from: https:\/\/openaccess.thecvf.com\/content_ICCVW_2019\/html\/VISDrone\/Du_VisDrone-DET2019_The_Vision_Meets_Drone_Object_Detection_in_Image_Challenge_ICCVW_2019_paper.html"},{"key":"pone.0360794.ref053","doi-asserted-by":"crossref","unstructured":"Tang S, Zhang S, Fang Y. HIC-YOLOv5: Improved YOLOv5 for Small Object Detection. 2023;arXiv:2309.16393. Available from: https:\/\/arxiv.org\/abs\/2309.16393","DOI":"10.1109\/ICRA57147.2024.10610273"},{"issue":"1","key":"pone.0360794.ref054","doi-asserted-by":"crossref","first-page":"9577","DOI":"10.1038\/s41598-023-36781-2","article-title":"Improved GBS-YOLOv5 algorithm based on YOLOv5 applied to UAV intelligent traffic","volume":"13","author":"H Liu","year":"2023","journal-title":"Sci Rep"},{"key":"pone.0360794.ref055","doi-asserted-by":"crossref","unstructured":"Akyon FC, Altinuc SO, Temizel A. Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection. In: 2022 IEEE International Conference on Image Processing. 2022. p. 966\u201370. https:\/\/doi.org\/10.1109\/ICIP46576.2022.9897990","DOI":"10.1109\/ICIP46576.2022.9897990"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0360794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:37:06Z","timestamp":1792690626000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0360794"}},"subtitle":[],"editor":[{"given":"Usman","family":"Ghafoor","sequence":"first","affiliation":[{"name":"National University of Sciences and Technology","place":["PAKISTAN"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,22]]},"references-count":55,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0360794","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,22]]}}}