Adaptive Computer Vision: Online Learning for Object Recognition

Bekel H, Bax I, Heidemann G, Ritter H (2004)
In: Pattern Recognition. Proceedings. Rasmussen CE, Bülthoff HH, Giese MA, Schölkopf B (Eds); Lecture notes in computer science, 3175. Berlin: Springer-Verlag: 447-454.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
OA
Autor/in
; ; ;
Herausgeber*in
; ; ;
Abstract / Bemerkung
The "life" of most neural vision systems splits into a one-time training phase and an application phase during which knowledge is no longer acquired. This is both technically inflexible and cognitively unsatisfying. Here we propose an appearance based vision system for object recognition which can be adapted online, both to acquire visual knowledge about new objects and to correct erroneous classification. The system works in an office scenario, acquisition of object knowledge is triggered by hand gestures. The neural classifier offers two ways of training: Firstly, the new samples can be added immediately to the classifier to obtain a running system at once, though at the cost of reduced classification performance. Secondly, a parallel processing branch adapts the classification system thoroughly to the enlarged image domain and loads the new classifier to the running system when ready.
Erscheinungsjahr
2004
Titel des Konferenzbandes
Pattern Recognition. Proceedings
Band
3175
Seite(n)
447-454
Konferenz
26th DAGM Symposium
Konferenzort
Tübingen, Germany
Konferenzdatum
2004-08-30 – 2004-09-01
ISBN
3-540-22945-0
Page URI
https://pub.uni-bielefeld.de/record/1606464

Zitieren

Bekel H, Bax I, Heidemann G, Ritter H. Adaptive Computer Vision: Online Learning for Object Recognition. In: Rasmussen CE, Bülthoff HH, Giese MA, Schölkopf B, eds. Pattern Recognition. Proceedings. Lecture notes in computer science. Vol 3175. Berlin: Springer-Verlag; 2004: 447-454.
Bekel, H., Bax, I., Heidemann, G., & Ritter, H. (2004). Adaptive Computer Vision: Online Learning for Object Recognition. In C. E. Rasmussen, H. H. Bülthoff, M. A. Giese, & B. Schölkopf (Eds.), Lecture notes in computer science: Vol. 3175. Pattern Recognition. Proceedings (pp. 447-454). Berlin: Springer-Verlag.
Bekel, H., Bax, I., Heidemann, G., and Ritter, H. (2004). “Adaptive Computer Vision: Online Learning for Object Recognition” in Pattern Recognition. Proceedings, Rasmussen, C. E., Bülthoff, H. H., Giese, M. A., and Schölkopf, B. eds. Lecture notes in computer science, vol. 3175, (Berlin: Springer-Verlag), 447-454.
Bekel, H., et al., 2004. Adaptive Computer Vision: Online Learning for Object Recognition. In C. E. Rasmussen, et al., eds. Pattern Recognition. Proceedings. Lecture notes in computer science. no.3175 Berlin: Springer-Verlag, pp. 447-454.
H. Bekel, et al., “Adaptive Computer Vision: Online Learning for Object Recognition”, Pattern Recognition. Proceedings, C.E. Rasmussen, et al., eds., Lecture notes in computer science, vol. 3175, Berlin: Springer-Verlag, 2004, pp.447-454.
Bekel, H., Bax, I., Heidemann, G., Ritter, H.: Adaptive Computer Vision: Online Learning for Object Recognition. In: Rasmussen, C.E., Bülthoff, H.H., Giese, M.A., and Schölkopf, B. (eds.) Pattern Recognition. Proceedings. Lecture notes in computer science. 3175, p. 447-454. Springer-Verlag, Berlin (2004).
Bekel, Holger, Bax, Ingo, Heidemann, Gunther, and Ritter, Helge. “Adaptive Computer Vision: Online Learning for Object Recognition”. Pattern Recognition. Proceedings. Ed. Carl Edward Rasmussen, Heinrich H. Bülthoff, Martin A. Giese, and Bernhard Schölkopf. Berlin: Springer-Verlag, 2004.Vol. 3175. Lecture notes in computer science. 447-454.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-06T08:48:03Z
MD5 Prüfsumme
db1b3830ff6b63ef346bfde795b25a7f