The BANCA Database and Evaluation Protocol

By E. Bailly-Bailliére, Samy Bengio, Frédéric Bimbot, M. Hamouz, Josef Kittler, J. Mariéthoz, Jiri Matas, K. Messer, Vlad Popovici, F. Porée and 2 more. International Conference on Audio- and Video-Based Biometric Person Authentication, 2003

515 citations recorded by the source corpus.

In this paper we describe the acquisition and content of a new large, realistic and challenging multi-modal database intended for training and testing multi-modal verification systems. The BANCA database was captured in four European languages in two modalities (face and voice). For recording, both high and low quality microphones and cameras were used. The subjects were recorded in three different scenarios, controlled, degraded and adverse over a period of three months. In total 208 people were captured, half men and half women. In this paper we also describe a protocol for evaluating verification algorithms on the database. The database will be made available to the research community through http://www.ee.surrey.ac.uk/Research/VSSP/banca.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/8f83e1a0c05da3a2f316b75b4a178fadf709dd68

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Biometrics Evaluation Under Spoofing Attacks (2014, methodology): “The optimal threshold, also referred to as operating point , is a tuning parameter, and it is usually determined using the development set [16], [18].”
Past, Present, and Future of Face Recognition: A Review (2020, background): “The BANCA dataset [26] is a tremendous, practical, and challenging multi-modal dataset proposed in 2003 for training and testing multi-modal biometric verification systems.”
Face recognition: A literature survey (2003, methodology): “Fortunately, relatively large video databases exist, for example, the XM2TV database [Messer et al. 1999], the BANCA database [Bailly-Bailliere et al. 2003], and the addition of video into the FERET and FRVT2002 16Stereo is less sensitive to illumination change but still has dif.culty in handling”
The DIARETDB1 Diabetic Retinopathy Database and Evaluation Protocol (2007, methodology): “For example, commonly accepted strict guidelines for the evaluation of biometric authentication methods, such as the FERET and BANCA protocols for face recognition methods [16, 2], have enabled the rapid progress in that field, and the same can be expected in medical image processing related to diab”
Neighborhood repulsed metric learning for kinship verification (2012, background): “Generally, there are two types of protocols for verification tasks: closed-set and open-set [4].”
The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations (2008, background): “Of course, there are other face databases internationally including CMU PIE [5], AR [6], XM2VTS [7], ORL, MPI, UMIST, MIT, Yale and Yale B, BANCA [8], KFDB [10], etc.”
Audio-Visual Speech Synchrony Measure for Talking-Face Identity Verification (2007, methodology): “Experiments are performed on the BANCA database following the Pooled protocol [7].”
Gabor wavelets and General Discriminant Analysis for face identification and verification (2007, methodology): “Each set thus consists of 130 training images, and test images consisting of 1170 client accesses and 1560 impostor accesses [19].”
On the Use of SIFT Features for Face Authentication (2006, methodology): “In fact, in all the recent databases (such as BANCA [1]) the positions of the eyes are given in order to permit the pre-registration of the images: only the matching methodology is analyzed.”
The Big Brother Database: Evaluating Face Recognition in Smart Home Environments (2009, background): “For example, the BANCA [1] or the Notre Dame Human ID [4] databases have been acquired over a period of about 3 months, but the acquisition conditions are rather controlled and/or the number of different acquisition sessions is limited.”
Multimodal fusion for multimedia analysis: a survey (2010, background): “For example, BANCA [14] that contains face and speech modalities; XM2VTS [82] that con-”
DIARETDB 1 diabetic retinopathy database and evaluation protocol (2007, methodology): “For example, commonly accepted strict guidelines for the evaluation of biometric authentication methods, such as the FERET and BANCA protocols for face recognition methods [16, 2], have enabled the rapid progress in that field, and the same can be expected in medical image processing related to diab”
SDUMLA-HMT: A Multimodal Biometric Database (2011, background): “BANCA [6] and XM2VTS [7] include face and voice; MYCT [8] includes fingerprint and signature.”
A review on Gabor wavelets for face recognition (2006, methodology): “To make the testing be as close as possible to the real authentication applications, the BANCA database [39, 79 ] has been released to replace the XM2VT database [80, 81] for evaluation of face verification algorithms.”