IJCB 2017 Competitions
Unconstrained Ear Recognition Challenge (UERC)
Organizers: Žiga Emeršič, Vitomir Štruc and Peter Peer
Despite the numerous application possibilities in security, surveillance applications, forensics, criminal investigations or border control, the existing research in ear recognition has seldom gone beyond laboratory settings. This can mostly be attributed to the enormous appearance variability of ear images when captured in unconstrained settings. However, due to recent advances in computer vision, machine learning and artificial intelligence (e.g. with deep learning), many recognition problems are now solvable (to at least some extent) in unconstrained settings and many biometric modalities that were too difficult to use in real-life situations are now becoming a viable source of data for person recognition. The Unconstrained Ear Recognition Challenge (UERC) will build on the advances outlined above and address the problem of ear recognition “in the wild”. The goal of the challenge is to advance the state-of-technology in the field of automatic ear recognition, to provide participants with a challenging research problem and introduce a benchmark dataset and protocol for assessing the latest techniques, models, and algorithms related to ear recognition in the wild.
ICFVR 2017 - 3rd International Competition on Finger Vein Recognition
Organizers: Wenxin Li, Houjun Huang, Yi Zhang
Finger vein recognition has become a promising biometric recognition technology - it's hard to be counterfeited, yet achieves outstanding recognition performance. In the 3nd International Competition on Finger Vein Recognition organized by the Artificial Intelligence Laboratory of Peking University, we are going to track the state of the art of finger vein recognition algorithms, and introduce a platform and data sets for the evaluation of finger vein recognition algorithms. Typical finger vein recognition process consists of two main steps, template enrollment and template matching. The task in this competition is to write an algorithm for the two steps. To be more specific, given two finger vein images, the algorithm should first enroll the samples, create two templates and then match these two templates to answer how similar the two samples are. Participants from academia and industry are welcomed. Submit your algorithms!
Sclera Segmentation and Eye Recognition Benchmarking Competition 2017
Organizers: Abhijit Das, Umapada Pal, Michael Blumenstein, Miguel A. Ferrer
Due to recent independent research on sclera biometrics, it is required to benchmark the recent growth on this subject of research using a common dataset. To fulfil this aim and to attract the attention of researchers, 1st and 2nd Sclera Segmentation Benchmarking Competitions (SSBC 2015 and 2016) in conjunction with BTAS 2015 and 2016 respectively and 1st Sclera Segmentation and Recognition Benchmarking Competition (SSRBC 2016) in conjunction with ICB 2016 were organized. Inspired by the successful completion of these competitions and available scope of development, we plan this competition. Another significant growing aspect of research is ocular biometrics in the visible spectrum. Significant amounts of desecrate research interest can be recorded in the recent literature. Mainly three traits namely iris, sclera and peri-ocular individual or a combination of them are employed in these works. Therefore we plan to run a competition, where the participants can use any of these traits or a combination of them to report their highest recognition accuracy for ocular biometrics employing a common dataset.
Liveness Detection Competition – Iris (LivDet-Iris 2017)
Organizers: Stephanie Schuckers, Adam Czajka, Kevin Bowyer, Richa Singh, Mayank Vatsa, Afzel Noore
This competition, being the third edition of the LivDet-Iris competition series launched in 2013, aims at evaluating current solutions for iris liveness detection. It will be organized into two parts, Part 1: Algorithms and Part 2: Systems. Competitors may participate in only one part or both parts. Part 1: Algorithms will involve the evaluation of the software solutions on large and diversified datasets encompassing samples that simulate two of the most popular presentation attacks in iris recognition: 1) use of patterned contact lenses (of various manufacturers) and 2) use of iris paper printouts. Sequestered evaluation sets will be held for testing submitted algorithms. Testing datasets will consist of both known spoof types (same types as training datasets) and unknown spoof types (types not present in training datasets). Part 2: Systems will involve the systematic testing of submitted iris recognition systems based on physical artifacts presented to the sensors. An analysis of the performance in each part independently will be used to determine an overall winner whose algorithm and system have the lowest error rates, respectively.
Cross-Eyed 2017 - 2nd Cross-Spectral Iris/Periocular Recognition Competition
Organizers: James Ferryman, Ana F. Sequeira, Lulu Chen
This is the second edition of the Cross-Eyed competition, focusing on benchmarking the problem of cross-spectral periocular and iris recognition. Cross-spectral biometric recognition, especially using face, or the ocular region, is a relatively new topic, and presenting challenges in real-life applications such as automated border control. Little research have been presented in the past, therefore, this competition aims to address and promote research on this topic, and contribute new dataset to the research community. The competition is composed of two separate tasks, periocular and iris recognition, and the main challenge is to perform the matching between Near Infra-red (NIR) and Visible range (VIS) images. Ocular recognition under less constrained imaging scenarios poses a serious challenge. Even though iris is considered one of the most accurate biometric traits, its recognition performance may be largely affected under these conditions. The periocular trait, comprising the whole eye region, can be a solution to overcome some of the limitations caused by noisy and less quality iris images.
The IJCB 2017 competition on generalized face presentation attack detection in mobile authentication scenarios
Organizers: Zinelabidine Boulkenafet, Jukka Komulainen, Zahir Akhtar, Abdenour Hadid
The vulnerabilities of face-based biometric systems to presentation attacks have been finally recognized but yet we lack generalized software-based face Presentation Attack Detection (PAD) methods performing robustly in practical mobile authentication scenarios. During the last few years, many face PAD methods have been proposed. The evaluation of these methods on the existing face anti-spoofing databases (including the databases used in the previous competitions) shows good performances. However, some recent studies show that most of these methods are not able to generalize well under real world conditions. Thus, in this competition, we aim to compare and evaluate the generalization performances of the face PAD methods under some real world variations including camera device variation, Presentation Attack Instrument variation, and illumination variation.
The IJCB 2017 Face Recognition Challenge
Organizers: Terrance Boult, Patrick J. Flynn, P. Jonathon Phillips, Walter J. Scheirer
Face recognition remains one of the most significant challenges within the field of biometrics. In spite of advances in machine learning, algorithms that can generalize to new settings and tolerate the myriad configurations that the human face can take when acquired by a sensor are elusive. The IJCB 2017 Face Recognition challenge is designed to evaluate state-of-the-art face recognition systems with respect to cross dataset generalization, open set face detection, and open set face recognition — all of which remain unsolved problems. The competition consists of three distinct challenges. Participants are invited to compete on one or more of these.