Disguise and Makeup Faces Database

This database is organized from 410 different subjects and provides 2460 different face images under real-world make-up variations.

More details on this dataset are available at: http://www4.comp.polyu.edu.hk/~csajaykr/DMFaces.htm

IITD Near IR Face Database (Version 2.0)

The two-session database from 102 different subject has been acquired using a low resolution NIR camera. There are 612 images in this database.

More details on this dataset are available at: http://www4.comp.polyu.edu.hk/~csajaykr/IITD/FaceIR.htm

DroneSURF Database

More details on this dataset are available at: http://iab-rubric.org/index.php/dronesurf

Disguised Faces in the Wild Database (DFW)

The DFW dataset consists of 1000 subjects and 11157 images. Pre-defined training and testing splits are provided, where 400 subjects form the training set, while the remaining 600 subjects form the test set. Each subject may contain normal, validation, disguised, and impersonator images.

More details on this dataset are available at:  http://iab-rubric.org/index.php/dfw

FaceSurv: A Benchmark Video Dataset for Face Detection and Recognition Across Spectra and Resolutions

This database contains videos captured both daytime and nighttime where the subject is at a standoff distance of 1-10 mts from the camera. It can be used to perform experiments for cross-spectral and cross resolution face recognition.

More details on this dataset are available at:  http://iab-rubric.org/index.php/facesurv

Multispectral Latex Mask based Video Face Presentation Attack

Multispectral Latex Mask based Video Face Presentation Attack (MLFP) is collected by Indraprastha Institute of Information Technology-Delhi (IIIT-D) and West Virgina University-USA (WVU-USA). The prime focus of the database is the development of face presentation attack detection algorithms in multiple spectrum. The database is publicly available only for research purpose.

More details on this dataset are available at:  http://iab-rubric.org/index.php/MLFP

Silicone Mask Face Attack Database

Silicone Mask Attack Database (SMAD) consists of 65 videos of face biometric presentation attacks through real life silicone masks and 65 genuine face biometric access videos. The database is assembled to facilitate research efforts in building algorithms for unconstrained face presentation attack detection

More details on this dataset are available at:

IdentifyMe

The dataset contains 464 skull images, and is divided into two parts: (i) skull and digital face image pairs, and (ii) unlabeled supplementary skull images. The first component consists of pairs collected from real world examples of solved skull identification cases, while the second part contains unlabeled skull images.

More details on this dataset are available at:  http://iab-rubric.org/index.php/identify

IIIT-D Sketch Database

IIIT-Delhi sketch database consist of three different types of sketches, namely, viewed, semi-forensic, and forensic sketches. Each user in the database has a sketch and a corresponding digital photograph. It introduces semi-forensic sketches that are drawn based on the memory of sketch artist to act as an intermediate representation between viewed and forensic sketches.

More details on this dataset are available at:  http://iab-rubric.org/index.php/iiit-d-sketch-database