Segmentation of Partially Occluded Objects by Local Classification

Heidemann G, Lücke D, Ritter H (2000)
In: IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000., 1. Como, Italy: IEEE: 152-157.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Heidemann, Gunther; Lücke, D.; Ritter, HelgeUniBi
Abstract / Bemerkung
An algorithm for supervised learning the segmentation of partially occluded objects is presented. It is based on the classification of object windows which are small compared to the object size but large enough to evaluate structural object features as well as colour. From the input windows, features are extracted by local principal component analysis and subsequently classified by a neural network of the local linear map type. The performance is checked on images of objects with partial occlusion which were artificially generated from the Columbia Object Image Library
Erscheinungsjahr
2000
Titel des Konferenzbandes
IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000
Band
1
Seite(n)
152-157
Konferenz
IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000
Konferenzort
Como
ISSN
1098-7576
Page URI
https://pub.uni-bielefeld.de/record/2714790

Zitieren

Heidemann G, Lücke D, Ritter H. Segmentation of Partially Occluded Objects by Local Classification. In: IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000. Vol 1. Como, Italy: IEEE; 2000: 152-157.
Heidemann, G., Lücke, D., & Ritter, H. (2000). Segmentation of Partially Occluded Objects by Local Classification. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000, 1, 152-157. doi:10.1109/IJCNN.2000.857829
Heidemann, G., Lücke, D., and Ritter, H. (2000). “Segmentation of Partially Occluded Objects by Local Classification” in IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000, vol. 1, (Como, Italy: IEEE), 152-157.
Heidemann, G., Lücke, D., & Ritter, H., 2000. Segmentation of Partially Occluded Objects by Local Classification. In IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000. no.1 Como, Italy: IEEE, pp. 152-157.
G. Heidemann, D. Lücke, and H. Ritter, “Segmentation of Partially Occluded Objects by Local Classification”, IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000, vol. 1, Como, Italy: IEEE, 2000, pp.152-157.
Heidemann, G., Lücke, D., Ritter, H.: Segmentation of Partially Occluded Objects by Local Classification. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000. 1, p. 152-157. IEEE, Como, Italy (2000).
Heidemann, Gunther, Lücke, D., and Ritter, Helge. “Segmentation of Partially Occluded Objects by Local Classification”. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000. Como, Italy: IEEE, 2000.Vol. 1. 152-157.

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar