F Nous contacter


Post-edited Detection theory and novelty filters

Auteurs : Morel, Jean-Michel (Auteur de la Conférence)
CIRM (Editeur )

Loading the player...
detection principles variational method sparsity of patches number of tests building the image model number of false alarms example of detections in textures examples of multiscale detections questions of the audience

Résumé : In this presentation based on on-line demonstrations of algorithms and on the examination of several practical examples, I will reflect on the problem of modeling a detection task in images. I will place myself in the (very frequent) case where the detection task can not be formulated in a Bayesian framework or, rather equivalently that can not be solved by simultaneous learning of the model of the object and that of the background. (In the case where there are plenty of examples of the background and of the object to be detected, the neural networks provide a practical answer, but without explanatory power). Nevertheless for the detection without "learning", I will show that we can not avoid building a background model, or possibly learn it. But this will not require many examples.

Joint works with Axel Davy, Tristan Dagobert, Agnes Desolneux, Thibaud Ehret.

Codes MSC :
65D18 - Computer graphics, image analysis, and computational geometry
68T05 - Learning and adaptive systems
68U10 - Image processing

    Informations sur la Vidéo

    Réalisateur : Hennenfent, Guillaume
    Langue : Anglais
    Date de publication : 25/05/17
    Date de captation : 17/05/17
    Collection : Research talks
    Format : MP4 (.mp4) - HD
    Domaine : Numerical Analysis & Scientific Computing ; Computer Science
    Audience : Chercheurs ; Doctorants , Post - Doctorants
    Download : http://videos.cirm-math.fr/2017-05-17_Morel.mp4

Informations sur la rencontre

Nom du congrès : 19th workshop on stochastic geometry, stereology and image analysis / 19ème conférence en géométrie stochastique, stéréologie et analyse d'images
Organisteurs Congrès : Calka, Pierre ; Coeurjolly, Jean-François ; Coupier, David ; Estrade, Anne ; Molchanov, Ilya
Dates : 15/05/17 - 19/05/17
Année de la rencontre : 2017
URL Congrès : http://conferences.cirm-math.fr/1513.html

Citation Data

DOI : 10.24350/CIRM.V.19166203
Cite this video as: Morel, Jean-Michel (2017). Detection theory and novelty filters. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.19166203
URI : http://dx.doi.org/10.24350/CIRM.V.19166203

Voir aussi


  1. Boracchi, G., Carrera, D., & Wohlberg, B. (2014). Novelty detection in images by sparse representations. IEEE Symposium on Intelligent Embedded Systems, Orlando 2014, 47-54 - http://dx.doi.org/10.1109/INTELES.2014.7008985

  2. Carrera, D., Boracchi, G., Foi, A., & Wohlberg, B. (2016). Scale-invariant anomaly detection with multiscale group-sparse models. IEEE International Conference on Image Processing, Phoenix 2016, 3892-3896 - http://dx.doi.org/10.1109/ICIP.2016.7533089

  3. Delsolneux, A., Moisan, L., & Morel, J.-M. (2008). From Gestalt theory to image analysis. A probabilistic approach. New York: Springer - http://dx.doi.org/10.1007/978-0-387-74378-3

  4. Margolin, R., Tal, A., & Zelnik-Manor, L. (2013). What makes a patch distinct?. IEEE Conference on Computer Vision and Pattern Recognition, Portland 2013, 1139-1146 - http://dx.doi.org/10.1109/CVPR.2013.151

  5. Mishne, G., & Cohen, I. (2014). Multiscale anomaly detection using diffusion maps and saliency score. IEEE International Conference on Acoustics, Speech and Signal Processing, Florence 2014, 2823-2827 - http://dx.doi.org/10.1109/ICASSP.2014.6854115

  6. Raad, L., Desolneux, A., Morel, J.-M. (2015) Conditional Gaussian Models for Texture Synthesis. In J.-F. Aujol, M. Nikolova, & N. Papadakis (Eds.), Scale space and variational methods in computer vision (pp. 474-485). Cham: Springer - http://dx.doi.org/10.1007/978-3-319-18461-6_38