Research lines

HIGH PERFORMANCE COMPUTING

Modern microarchitectures combine an increasing number of multithreaded cores and highly complex caching schemes on die with the purpose of maximizing performance and hiding memory latencies. Herta Security conducts research on parallel algorithms and programming models that fully exploit the computing power of both CPUs and GPUs.

IMAGE ENHANCEMENT

Changing the lighting conditions in which a face image is captured may substantially impair the performance of face recognition systems. Research at Herta Security aims to develop reliable, real-time image enhancement modules for face recognition, which automatically compensate for strong lighting variations via photometric normalization and re-illumination techniques.

MULTIMODAL FUSION

Herta Security is developing smart algorithms that synergistically combine several biometric modalities (e.g. face, voice, iris) in a single recognition system. Multi-modal fusion improves the results of a single biometric feature and makes the system more reliable in the face of potential attacks.

Publications Patents Dataset

› D. Perez, C. Fernandez, C. Segura, J. Hernando, "New Approaches for Iris Boundary Localization", VI Jornadas de Reconocimiento Biométrico de Personas, Las Palmas de Gran Canaria, Spain, December, 2011

› C. Fernandez, D. Perez, C. Segura, J. Hernando, "A Novel Method for Low-constrained Iris Boundary Localization", International Conference on Biometrics, New Delhi, India, December, 2011

› D. Oro, C. Fernandez, J. Rodriguez Saeta, X. Martorell, J. Hernando, "Real-time GPU-based Face Detection in HD Video Sequences", 2011 IEEE International Conference on Computer Vision Workshops, Barcelona, Spain, November, 2011

› C. Fernandez, P. Baiget, X. Roca, J. Gonzalez, "Augmenting Video Surveillance Footage with Virtual Agents for Incremental Event Evaluation", Pattern Recognition Letters, , April, 2011

› C. Fernandez, P. Baiget, X. Roca, J. Gonzalez, "Determining the Best Suited Semantic Events for Cognitive Surveillance", Expert Systems with Applications, , April, 2011

› C. Fernandez, J. Gonzalez, X. Roca, "Automatic Learning of Background Semantics in Generic Surveilled Scenes", ECCV 2010, Hersonissos, Greece, September, 2010

› D. Oro, J. Luna, T. Felguera, M. Vilanova, J. Serna, "Benchmarking IP Blacklists For Financial Botnet Detection", 6th International Conference on Information Assurance and Security, Atlanta, August, 2010

› M. Farrus, M. Wagner, D. Erro, J. Hernando, "Automatic speaker recognition as a measurement of voice imitation and conversion", The Intenational Journal of Speech. Language and the Law, vol. 17, no. 1, , January, 2010

› N. Bellotto, E. Sommerlade, B. Benfold, C. Bibby, I. Reid, D. Roth, L. Van Gool, C. Fernandez, J. Gonzalez, "A Distributed Camera System for Multi-Resolution Surveillance", 3rd ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC2009), Como, Italy, September, 2009

› P. Ejarque, J. Hernando, "Score bi-Gaussian equalization for multimodal person verification", IET Signal Processing, , July, 2009

› M. Farrus, J. Hernando, "Using jitter and shimmer in speaker verification", IET Signal Processing, , July, 2009

› C. Fernandez, X. Roca, J. Gonzalez, "Providing Automatic Multilingual Text Generation to Artificial Cognitive Systems", Vigo International Journal of Applied Linguistics, , October, 2008

› C. Fernandez, P. Baiget, X. Roca, J. Gonzalez, "Interpretation of Complex Situations in a Semantic-Based Surveillance Framework", Signal Processing: Image Communication, , August, 2008

› A.A. Salah, R. Morros, J. Luque, C. Segura, J. Hernando, O. Ambekar, B. Schouten, E. Pauwels, "Multimodal identification and localization of users in a smart room environment", Journal on Multimodal User Interfaces, vol. 2, no. 2, , February, 2008

› C. Segura, A. Abad, J. Hernando and C. Nadeu, "Multispeaker Localization and Tracking in Intelligent Environments", MULTIMODAL TECHNOLOGIES FOR PERCEPTION OF HUMANS Lecture Notes in Computer Science, 2008, Volume 4625/2008, 82-90, DOI: 10.1007/978-3-540-68585-2_6, Berlin / Heidelberg, , 2008

› C. Segura, A. Abad , J. Hernando and C. Nadeu, "Speaker Orientation Estimation based on GCC-PHAT and HLBR hybridization", Proceedings International Conference on Spoken Language Processing, Brisbane, Australia, , 2008

› D. Hernando, D. Gomez, J. Rodriguez Saeta, P. Ejarque, J. Hernando, "Agatha: Multimodal Biometric Authentication Platform in Large-Scale Databases", ISSE 2008, Madrid (Spain), , 2008

› X. Anguera, C. Wooters, J. Hernando, "Acoustic beamforming for speaker diarization of meetings", IEEE Transactions on Audio, Speech and Language Processing, vol. 15, no. 7, , July, 2007

› C. Segura, C. Canton-Ferrer, A. Abad, J.R. Casas and J. Hernando, "Multimodal Head Orientation Towards Attention Tracking in Smartrooms", IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Honolulu, Hawaii, April, 2007

› J. Rodriguez Saeta, J.Hernando, "Assessment of on-line model quality and threshold estimation in speaker verification", IEICE Transactions on Information and Systems, vol. E90-D, no. 4, , April, 2007

› P. Ejarque, A. Garde, J. Anguita, J. Hernando, "On the use of genuine-impostor statistical information for score fusion in multimodal biometrics", Annals of Telecommunications, vol,. 62, no. 1-2, , January, 2007

› D. Oro, R. Canal, A. Gonzalez, J. E. Smith, "Power/Performance/Thermal trade-offs in microarchitecture", Intel Academic Forum 2006, Dublin, June, 2006

› D. Hernando, J.Rodriguez Saeta, J. Hernando, "Threshold Estimation with Continuously Trained Models in Speaker Verification", IEEE Odyssey 2006: The Speaker and Language Recognition Workshop, San Juan (Puerto Rico), June, 2006

› J. Rodriguez Saeta, J. Hernando, "Weighting Scores to Improve Speaker-Dependent Threshold Estimation in Text-Dependent Speaker Verification", Lecture Notes in Computer Science, ed. Springer-Verlag, , , 2006

› J. Anguita, J. Hernando, A.Abad, "Improved Jacobian adaptation for robust speaker verification", IEICE Transactions on Information and Systems, vol. E88-D, no. 7, , July, 2005

© The downloadable publications on this website are presented to ensure timely dissemination of scholarly and technical work. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the owner of the copyright.

BioSurveillance

Real-time recognition in movement
Multi camera
Not affected by glasses, hats, facial hair...
1 to 500.000 identification in less than a second
Runtime alarms

View product

Speaker recognition

Real-time recognition
Spanish, Catalan and English
Multiple simultaneous calls
Very reliable despite reverberation and in noisy environments
Windows / Linux
Identification and verification modes

View product

Iris access control

Real-time recognition
In movement and at a distance
Non-invasive
Unsupervised identification performance

View product

Join us

We are looking for people like you; professional, dynamic and experienced.

Send us your C.V.

Herta Security, Biometrics

Research lines

BioSurveillance

Speaker recognition

Iris access control

Join us