2026-04-14T02:07:10Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/1038652026-01-16T08:08:48Zcom_2072_1033col_2072_452950

Partition-based image representation as basis for user-assisted segmentation Marqués Acosta, Fernando Marcotegui Iturmendi, Beatriz Zanoguera, Francisca Correia Fernandez-Pereira, Paulo Mech, R. Wollborn, M Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions Universitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo Àrees temàtiques de la UPC::Enginyeria de la telecomunicació Telecommunication Image sequences Image representation Image segmentation Video signal processing Telecomunicació This paper discusses the usefulness of a partition-based image representation in the context of user-assisted segmentation, and compares it with the two other most common image representations in this framework: pixel-based and transition-based. Partition-based image representations allow user-interaction at the region level, which is a very natural and friendly manner to interact with images. The paper describes various region-based implementations of the most common types of user interaction; namely, initial object selection, object refinement, imposing object characteristics, selection of specific objects, selection of objects that are similar to a previously selected one. In all cases, partition-based image representations, and their associated region-based tools for user interaction, show up to be very suitable for interactive image segmentation. Peer Reviewed Postprint (published version) 2000 Conference report Marques, F., Marcotegui, B., Zanoguera, F., Correia, P., Mech, R., Wollborn, M. Partition-based image representation as basis for user-assisted segmentation. A: IEEE International Conference on Image Processing. "Proceedings ICIP 2000". Vancouver: Institute of Electrical and Electronics Engineers (IEEE), 2000. 0-7803-6300-0 https://hdl.handle.net/2117/103865 10.1109/ICIP.2000.900957 eng http://ieeexplore.ieee.org/document/900957/ Open Access 1 p. application/pdf Institute of Electrical and Electronics Engineers (IEEE)