Preliminary Miscellaneous Results

May 2, 2022

Gender Classification Across Race on Ocular

Training and Testing Dataset used - VISOB + Notredame
Test Data is Limited and Imbalanced

TABLE I: Gender Classification results across race groups - Ocular Datasets.
Race	Male	Female
White	82.42	89.92
South Asian	96.51	88.88
Black	78.57	72.10
Middle Eastern	71.12	93.08
Latino	84.83	91.61

Face vs PeriOcular Modality (RGB Spectrum)

Dataset Under Investigation - FlickrFaceHQ Aging
Resolution - 1024 X 1024

TABLE II: Gender Classification results across Face vs Periocular on FFHQ-Aging.
Male	Female	Modality
97.6	96.8	Face
92.5	91.6	Ocular

---

Sreeraj Ramachandran

Graduate Research Assistant

My research interests include Computer Vision, Biometrics, Bias AI, GANs and adversarial Attacks

comments powered by Disqus