La descarga está en progreso. Por favor, espere

La descarga está en progreso. Por favor, espere

How reliable is the result? Who are these people? Are you sure? 1 2 3 4 1.

Presentaciones similares


Presentación del tema: "How reliable is the result? Who are these people? Are you sure? 1 2 3 4 1."— Transcripción de la presentación:

1 How reliable is the result? Who are these people? Are you sure?

2 Defining Reliability Ground truth Accurate landmark Inaccurate landmark Estimation based on intensity model of each landmark Intrinsic precision A. Martinez (2002) IEEE Transactions on Pattern Analysis and Machine Intelligence,, 24(6):748–763,

3 Mutual Information Intrinsic precision Reliability Reliability estimate Maximize information given by the estimate:

4 Examples from IOF-ASM Reliable Unreliable

5 Examples from IOF-ASM Reliable Unreliable

6 Examples from IOF-ASM Reliable Unreliable

7 Examples from IOF-ASM

8 Reliability of a shape Intrinsic precision (average error) Outlier threshold (unacceptable error) 8

9 Incremental accumulation of evidence

10 ReliableUnreliable Undefined 10

11 Segmentation results: IOF-ASM 2214 images 1.92 (±0.01) pix avg 146 images 3.67 (±0.18) pix avg 2360 images XM2VTS database Avg p2c error = 2.03 (±0.02) pix

12 Segmentation results: ASM 2141 images 2.69 (±0.04) pix avg 219 images 6.80 (±0.72) pix avg 2360 images XM2VTS database Avg p2c error = 3.06 (±0.08) pix

13 Application I: Automatic model selection ?

14 Application I: Automatic model selection Accuracy: 89.6 %Accuracy: 82.1 % Confusion Matrices (color-coded)

15 Application II: Reliable Identification XM2VTS Database w/ BAD initialization 15

16 Application II: Reliable Identification

17 Conclusions on Reliability Estimation High correlation of proposed measure with accuracy Generic approach for ASM methods Only requirement is a local metric for each landmark Does not introduce changes in the algorithms Very low false positives rate Useful to provide robustness to biometric systems Based on consistency with training data 17

18 Journal publications F.M. Sukno, S. Ordas, C. Butakoff, S. Cruz, and A.F. Frangi. Active shape models with invariant optimal features: Application to facial analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(7): , F.M. Sukno and A.F. Frangi. Reliability Estimation for Statistical Shape Models. Conditionally accepted for publication in IEEE Transactions on Image Processing, pending minor revision F.M. Sukno, J.J. Guerrero and A.F. Frangi. Projective Active Shape Models for Posevariant Image Analysis of Quasi-Planar Objects: Application to Facial Analysis. Submitted for publication C. Hoogendoorn, F.M. Sukno, S. Ordas, and A.F. Frangi. Bilinear Models for Spatiotemporal Point Distribution Analysis: Application to Extrapolation of Left Ventricular, Biventricular and Whole Heart Cardiac Dynamics. Submitted for publication 18

19 Conferences A. Ortega, F.M. Sukno, E. Lleida, A.F. Frangi, A. Miguel, L. Buera, and E. A spanish multichannel multimodal corpus for in-vehicle automatic audiovisual speech recognition. In Proc. 4th Int. Conf. on Language Resources and Evaluation, Lisbon, Portugal, volume 3, pages (www.cilab.upf.edu/ac), A. Ortega, F.M. Sukno, E. Lleida, A.F. Frangi, A. Miguel, L. Buera, and E. Zacur. Base de datos audiovisual y multicanal en castellano para reconocimiento automático del habla multimodal en el automóvil. In III Jornadas en Tecnologías del Habla, pages , (www.cilab.upf.edu/ac), F.M. Sukno, S. Ordas, C. Butakoff, S. Cruz, and A.F. Frangi. Active shape models with invariant optimal features (IOF-ASMs). In Proc. 5th Int. Conf. on Audio- and Video-Based Biometric Person Authentication, New York, NY, USA. Lecture Notes in Computer Science vol. 3546, pages , F.M. Sukno, J.J. Guerrero and A.F. Frangi. Homographic active shape models for viewindependent facial analysis. In Proc. SPIE Biometric Technologies for Human Identification, Orlando, FL, USA, volume 5779, pages , F.M. Sukno and A.F. Frangi. Exploring reliability for automatic identity verification with statistical shape models. In Proc. IEEE Workshop on Automatic Identification Advanced Technologies, Alguero, Italy, pages 80-86, D. González-Jiménez, F.M. Sukno, J.L. Alba-Castro and A.F. Frangi. Automatic pose correction for local feature-based face authentication. In Proc. 4th IEEE Workshop on Motion of Non-Rigid and Articulated Objects, Mallorca, Spain. Lecture Notes in Computer Science vol. 4069, pages , C. Hoogendoorn, F.M. Sukno, S. Ordas, and A.F. Frangi. Bilinear models for spatiotemporal point distribution analysis: Application to extrapolation of whole heart cardiac dynamics. In Proc. IEEE ICCV th Int. Workshop on Mathematical Methods in Biomedical Image Analysis, Rio de Janeiro, Brazil,,

20 Projects BIOSECURE: Biometrics for Secure Authentication (IST ) European Excellence Network of FP6/2002/IST/1. Comisión Europea. iE-VULTUS: Desarrollo de un sistema centralizado de biometría facial de tercera generación para el control de acceso y seguridad en entornos inteligentes (Proyecto Coordinado TIC C02). Ministerio de Ciencia y Tecnología HERMES: Análisis biométrico de actividades óculo-faciales con técnicas de modelado estadístico robusto para sistemas de asistencia a la conducción segura de vehículos, (Plan Nacional de I+D+i, Proyectos de Investigación Aplicada TEC /TCM). Ministerio de Educación y Ciencia. iEYE: (en conjunto con Scati Labs) Definición de un sistema de tercera generación para seguridad en entornos inteligentes mediante técnicas de visión por ordenador (Programa de Fomento de la Investigación Tecnológica PROFIT FIT , FIT , FIT , Proyecto Iberoeka IBK ). Ministerio de Industria, Turismo y Comercio. eMedusa: (en conjunto con Scati Labs). Estrategias de adquisición, análisis, vi-sualización y fusión de información y su integración en un sistema avanzado de seguridad para entornos complejos. Programa de Fomento de la Investigación Tecnológica (PROFIT/Iberoeka FIT , FIT ). Ministerio de Industria, Turismo y Comercio. 20

21 Automatic Face Recognition demo 21

22 Automatic Face Recognition demo 22

23 Conclusions IOF-ASM demonstrated consistently superior to ASM Different databases with frontal images (30% more accurate) Multi-view databases (70% more accurate) The coplanar face model w/ PASM Adds robustness to head rotations Requires stronger image intensity models Average performance of ASM methods is acceptable - Adding reliability estimates: Helps to automatically discards outliers Allows for model selection and convergence assessment 23

24 Acknowledgements 24

25 THE END 25


Descargar ppt "How reliable is the result? Who are these people? Are you sure? 1 2 3 4 1."

Presentaciones similares


Anuncios Google