ResQ ID: A Reproducible Face and Ear Retrieval Prototype for Disaster Identification Assistance

References

[1] Zhong Y, Deng W, Hu J, Zhao D, Li X, Wen D. SFace: Sigmoid-constrained hypersphere loss for robust face recognition. IEEE Transactions on Image Processing. 2021;30:2587–2598. https://doi.org/10.1109/TIP.2020.3048632

[2] Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2005. Vol. 1, p. 886–893. https://doi.org/10.1109/CVPR.2005.177

[3] Emeršič Ž, Štruc V, Peer P. Ear recognition: More than a survey. Neurocomputing. 2017;255:26–39. https://doi.org/10.1016/j.neucom.2016.08.139

[4] Boodoo NB, Subramanian RK. Robust multi biometric recognition using face and ear images. International Journal of Computer Science and Information Security. 2009;6(2):164–169. https://arxiv.org/abs/0912.0955

[5] Kim M, Jain AK, Liu X. AdaFace: Quality adaptive margin for face recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2022. p. 18750–18759.

[6] scikit-learn contributors. fetch_olivetti_faces: dataset documentation and official loader. Available from: https://scikit-learn.org/stable/modules/generated/sklearn.datasets.fetch_olivetti_faces.html [Accessed 4 October 2026].

[7] Gonzalez E, Alvarez L, Mazorra L. AMI Ear Database. Universidad de Las Palmas de Gran Canaria. Available from: https://ctim.ulpgc.es/research_works/ami_ear_database/ [Accessed 4 October 2026].

[8] OpenCV contributors. OpenCV Zoo: Face detection YuNet and face recognition SFace [model repository]. Available from: https://github.com/opencv/opencv_zoo [Accessed 4 October 2026].

[9] Grother P, Ngan M, Hanaoka K. Face Recognition Vendor Test Part 3: Demographic Effects. NISTIR 8280. National Institute of Standards and Technology; 2019. https://doi.org/10.6028/NIST.IR.8280

[10] Deng J, Guo J, Xue N, Zafeiriou S. ArcFace: Additive angular margin loss for deep face recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2019. p. 4690–4699.

[11] 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 (CVPR); 2020. p. 5203–5212.

[12] Turk M, Pentland A. Eigenfaces for recognition. Journal of Cognitive Neuroscience. 1991;3(1):71–86. https://doi.org/10.1162/jocn.1991.3.1.71

@article{1724422,
      author = {Dr. A. Parivazhagan, Mallu Sree Harika, Kota Koushik Reddy, Chala Venkata Srinivas, Chinthakayala Sriram},
      title = {ResQ ID: A Reproducible Face and Ear Retrieval Prototype for Disaster Identification Assistance},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {4},
      pages = {3967-3977},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1724422.pdf},
      abstract = {ResQ-ID is a reproducible local prototype for retrieving possible missing-person identities from face and ear photographs while retaining human decision authority. The implementation combines YuNet and pretrained SFace, a histogram of oriented gradients (HOG) ear descriptor, exact cosine retrieval, and a FastAPI service with SQLite persistence. Separate component experiments use 400 real Olivetti face images and 600 AMI right-ear images. Three image-disjoint gallery, validation, and test partitions include unseen identities; thresholds are selected only on validation probes. Mean rank-1 retrieval is 96.67% for SFace and 57.92% for HOG ears, while correct accepted identification is 81.11% and 35.83%. Fixed-threshold tests reveal substantial sensitivity to occlusion. The recorded software suite passes 31 checks; 30 loopback ear-query trials have median latency 18.68 ms in a ten-case registry. The datasets contain different subjects, so no paired fusion advantage is demonstrated. These findings establish a transparent component baseline; disaster-field reliability and deployment readiness remain unvalidated.},
      keywords = {biometric retrieval; face recognition; ear recognition; open-set identification; human verification; reproducible evaluation; disaster assistance},
      month = {October},
  }