The SSRBC Dataset

The sclera segmentation and recognition benchmarking competition dataset aims to benchmark the sclera segmentation and recognition task with a common dataset. The dataset contains 2624 RGB images taken from 82 individuals. Both left and right eyes of the individuals were acquired, so in other words, 164 different eyes are considered. For each individual eye image, four angles (looking straight, left, right and up) are considered. For each angle 4 images are collected. The individuals encompassed both male and female participants and different colors, with a few of them wearing contact lenses and some images were taken at different times of the day. The database also contains images with blinking eyes, closed eyes and blurred eye images. High resolution images are provided in the database (300 dpi resolution and 7500 x 5000 dimensions). All the images are in JPEG format. A NIKON D 800 camera and 28300 lenses were used for image captured. A ground truth, or manual sclera segmentation of this dataset, was prepared. More details on this database and the download instructions are available at: ssrb2016/dataset

The QUIS‐CAMPI Multi‐Biometrics Dataset

The QUIS-CAMPI data feed is a tool to bridge the gap between surveillance and biometric recognition, whose acronym derives from the Latin and summarizes its goals: 'Quis' stands for 'Who is' and 'Campi' refers to a delimited space. Hence, the QUIS-CAMPI data feed aims at fostering the development of biometric recognition systems that work outdoor, in fully unconstrained and covert conditions. To this end, authors designed an automated master-slave surveillance system to capture both full body video sequences and high-resolution head samples of subjects in a parking lot.

The QUIS-CAMPI data feed has four major novelties: 1) biometric traits are automatically acquired by a master-slave surveillance system in a fully non-cooperative and covert manner. This allows the data to be acquired at-a-distance (up to 50~m) and on-the-move, and assures an effective representativeness of the covariates of biometric recognition in the wild; 2) it is an open dataset, i.e., new samples are continuously and automatically being added to the database and supplied to the research community. This singularity inhibits biased performance estimation - usually caused by parameter adjustment in the test set - without the burden of sequestered test data; 3) it is surveillance representative, i.e., the probe images truly encompass all the singularities of surveillance environments, and thus, advances in the recognition accuracy of these data have a direct impact on the deployment of a fully automated biometric recognition surveillance system; 4) the data include multiple biometric traits. Details on this database are available at:

The IARPA Janus Benchmark A (IJB‐A)

The The IARPA Janus Benchmark A (IJB-A), a publicly available media in the wild dataset containing 500 subjects with manually localized face images. Key features of the IJB-A dataset are: (i) full pose variation, (ii) joint use for face recognition and face detection benchmarking, (iii) a mix of images and videos, (iv) wider geographic variation of subjects, (v) protocols supporting both open-set identification (1:N search) and verification (1:1 comparison), (vi) an optional protocol that allows modeling of gallery subjects, and (vii) ground truth eye and nose locations. The dataset has been developed using 1,501,267 million crowd sourced annotations. More info available at:

The Kinship Faces in the Wild Dataset

The objective of this dataset is to determine whether there is a kin relation between a pair face images. There are two subsets in the kinship faces in the wild dataset: KinFaceW-I and KinFaceW-II. Face images are collected from the internet, including some public figure face images as well as their parents' or children's face images. The difference of KinFaceW-I and KinFaceW-II is that face images with a kin relation were acquired from different photos in KinFaceW-I and the same photo in KinFaceW-II in most cases. There are four kin relations in two datasets: Father-Son (F-S), Father-Daughter (F-D), Mother-Son (M-S), and Mother-Daughter (M-D). In the KinFaceW-I dataset, there are 156, 134, 116, and 127 pairs of kinship images for these four relations. For the KinFaceW-II dataset, each relation contains 250 pairs of kinship images. More details on this database and the download instructions are available at:

The Cox Face Dataset

The OU-ISIR Gait Speed Transition Dataset is the first publicly available gait database with speed transition within an image sequence. There are two datasets. Dataset 1 contains 179 subjects to record speed transition in gait sequences in indoor environment, while dataset 2 consists of 178 subjects walking at a constant speed based on an automatic speed transition protocol. The procedure to obtain the datasets is available at: GaitST.html

The Peking Finger Vein Recognition Dataset

This dataset aims to match how similar for a pair of finger vein samples. There are several subsets in this dataset: 1) DS0: 50 fingers in total, with 5 samples for each finger (50*5). This data set is for participants to test and debug their algorithms, might be used as a start point to develop algorithms. 2) DS1. DS1 contains 1000*5 samples, all of which were captured in indoor environment. The capturing process was under both guidelines and supervision. In general, the quality of the database should be very high, and participants are expected to obtain good performance in this dataset. 3) DS2: DS2 contains 1000*5 samples, all of which were captured from real usage, with a relatively longer time span, greater population variety, and an outdoor environment for no-guidance capture. This dataset is supposed to be relatively more difficult to achieve high performance compared to DS1. 4) DS3: DS3 contains 1000*5 samples, which would be difficult for the algorithm to verify. Some of the data may show low similarity in one class, and some show high similarity between different classes. The image format is bmp, 256 grayscale, 512*384 pixel resolution. More details on this database and the download instructions are available at:

Accessibility | Nondiscrimination Policy | Privacy & Opting Out of Cookies
© 2015 Biometrics Council - All Rights Reserved

cheap Dapoxetine Dapoxetine online