Abstract:
In this work, we address the problem of unsuper vised image segmentation, subject to high-level constraints ex pected for the objects of interest. More specifically, we handle the segmentation of a hierarchy of objects with nested boundaries, each with its own expected boundary polarity constraint. To this end, this work successfully extends Hierarchical Layered Oriented Image Foresting Transform (HLOIFT), with the inclu sion of nested object relations, to the unsupervised segmentation paradigm. On the other hand, this work can also be seen as an extension of Unsupervised OIFT (UOIFT) to include structural relationships of nested objects. The method is demonstrated in the segmentation of three datasets of colored images with superior performance compared to other existing techniques in graphs, requiring a smaller number of connected partitions to isolate the objects of interest in the images.
Referência:
KLEINE, Felipe Augusto de Souza; SANTOS, Luiz F.D.; CAPPABIANCO, Fábio A.M.; MIRANDA, Paulo A.V. Unsupervised image segmentation by oriented image foresting tranform in layered graphs. In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES, 36., 2023, Rio Grande. Proceedings… 6p.
Documento com acesso restrito. Logar na BiblioInfo, Biblioteca GITEB/IPT para acessar o trabalho em PDF:
