{
  "abstract": "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–focused 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.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Electronic Engineering, Faculty of Electrical and Computer Engineering.NED University of Engineering & Technology, Karachi, Pakistan.",
    "Department of Computer Science & Information Technology, Faculty of Electrical and Computer Engineering.NED University of Engineering & Technology, Karachi, Pakistan.",
    "Institute for Advanced Technology Convergence (Mobility), Kyungpook National University, Buk-gu, Daegu, Republic of Korea."
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Aniqa Saba",
      "orcid": "0009-0008-8915-0596"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Muhammad Faizan Shirazi",
      "orcid": "0000-0002-4488-8860"
    },
    {
      "affs": [
        0,
        2
      ],
      "name": "Yawar Rehman",
      "orcid": "0000-0001-9743-729X"
    },
    {
      "affs": [
        1
      ],
      "name": "Muhammad Mubashir Khan",
      "orcid": "0000-0002-0011-9525"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9xcgp4ggm1hf2.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0360794",
  "fulltext_url": "https://europepmc.org/articles/PMC13690218",
  "id": "9xcgp4ggm1hf2",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0360794",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1707|Face recognition and analysis"
    ],
    [
      "plos",
      "/Biology and life sciences/Anatomy/Head"
    ],
    [
      "plos",
      "/Biology and life sciences/Anatomy/Head/Face"
    ],
    [
      "plos",
      "/Biology and life sciences/Anatomy/Neck"
    ],
    [
      "plos",
      "/Computer and information sciences/Computer architecture"
    ],
    [
      "plos",
      "/Computer and information sciences/Computer vision/Target detection"
    ],
    [
      "plos",
      "/Engineering and technology/Equipment/Optical equipment/Cameras"
    ],
    [
      "plos",
      "/Medicine and health sciences/Anatomy/Head"
    ],
    [
      "plos",
      "/Medicine and health sciences/Anatomy/Head/Face"
    ],
    [
      "plos",
      "/Medicine and health sciences/Anatomy/Neck"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Probability theory/Probability density"
    ],
    [
      "plos",
      "/Research and analysis methods/Imaging techniques"
    ]
  ],
  "openalex": "W7223227910",
  "pdf_url": "https://europepmc.org/articles/PMC13690218?pdf=render",
  "pmcid": "PMC13690218",
  "pmid": "42911962",
  "published": "2026-10-22",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/9xcgp4ggm1hf2.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:23Z",
      "native_id": "10.1371/journal.pone.0360794",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0360794"
    },
    {
      "first_seen": "2026-10-30T12:20:10Z",
      "native_id": "MED:42911962",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42911962"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "plos:anatomy",
      "subfield": "physiology"
    }
  ],
  "title": "YOLO-SOD: Color probability map-based fuzzy framework using deep models for face detection",
  "title_text": "YOLO-SOD: Color probability map-based fuzzy framework using deep models for face detection",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:20:10Z",
  "url": "https://research.draconitic.com/paper/9xcgp4ggm1hf2",
  "venue": "PLOS One",
  "versions": []
}