Contactless Hand Dorsal Images Database
This database has been acquired from 712 different subjects and provides contactless hand dorsal images for the major and minor finger knuckle based biometric identification. It also provides second session images that are acquired after several years of interval.
More details on this dataset are available at: http://www4.comp.polyu.edu.hk/~csajaykr/knuckleV2.htm
Contact-free 3D/2D Hand Images Database (Ver 1.0)
This database provides contactless 3D and 2D palmprint images from 177 different subjects. It’s a two-session database and images are acquired using a commercial 3D sensor.
More details on this dataset are available at: http://www4.comp.polyu.edu.hk/~csajaykr/myhome/database_request/3dhand/Hand3D.htm
PolyU Contact‐free 3D/2D Hand Images Database (Version 2.0)
This database provides contactless 3D and 2D hand images with different pose variations in 3D space. It has been acquired in a single session from 114 different subjects and has been used for the palmprint identification.
More details on this dataset are available at: http://www4.comp.polyu.edu.hk/~csajaykr/Database/3Dhand/Hand3DPose.htm
IITD Ear Image Database (Version 1.0)
This database has been acquired from 212 different subjects. Its two-session database and also provides normalized region of interest images for the biometric matching.
More details on this dataset are available at: http://www4.comp.polyu.edu.hk/~csajaykr/IITD/Database_Ear.htm
The IARPA Janus Benchmark A (IJB‐A)
The IARPA Janus Benchmark face challenge (IJB-B, IJB-C ) provides various databases for addressing verification, identification, detection, clustering, and processing of full motion videos. The IJB-C dataset consists of 138000 face images, 11000 face videos, and 10000 non-face images.
More details on this dataset are available at: http://www.nist.gov/itl/iad/ig/ijba_request.cfm
The Extended Annotated Web Ears (AWEx) Dataset
This dataset contains 4104 cropped ear images of 346 subjects. The AWEx images were collected from the web and therefore correspond to unconstrained acquisition settings.
More details on this dataset are available at: http://ears.fri.uni-lj.si/datasets.html
The full image Annotated Web Ears (AWE) dataset
This dataset consists of 1000 images belonging to 100 subjects with 10 images per subject. The dataset comes with manual annotations of the ear region and is dedicated to research into ear detection/segmentation. The images in this dataset were gathered from the web.
More details on this dataset are available at: http://ears.fri.uni-lj.si/datasets.html
