Sejong face database: A multi-modal disguise face database

Commercial application of facial recognition demands robustness to a variety challenges such as illumination, occlusion, spoofing, disguise, etc. Disguised face is one the emerging issues for access control systems, security checkpoints at borders. However, lack availability databases with disguise add-ons limits development academic research in area. In this paper, we present multi-modal disguised dataset facilitate research. The presented database contains 8 and 7 additional combinations these create images. Each image captured visible, visible plus infrared, thermal spectra. Specifically, 100 subjects divided into Subset-A (30 subjects, 1 per modality) Subset-B (70 5 images modality). We also baseline detection results performed on proposed provide reference compare performance different modalities. Qualitative quantitative analysis evaluate challenging nature add-ons. will be publicly available acceptance article.