GraphBPT: An Efficient Hierarchical Data Structure for Image Representation and Probabilistic Inference
International audience This paper presents GraphBPT, a tool for hierarchical representation of images based on binary partition trees. It relies on a new BPT construction algorithm that have interesting tuning properties. Besides, access to image pixels from the tree is achieved efficiently with dat...
Main Authors: | , , |
---|---|
Other Authors: | , , , , , , , , , |
Format: | Conference Object |
Language: | English |
Published: |
HAL CCSD
2015
|
Subjects: | |
Online Access: | https://hal.archives-ouvertes.fr/hal-01168116 https://hal.archives-ouvertes.fr/hal-01168116/document https://hal.archives-ouvertes.fr/hal-01168116/file/ismm2015graphbpt.pdf https://doi.org/10.1007/978-3-319-18720-4_26 |
Summary: | International audience This paper presents GraphBPT, a tool for hierarchical representation of images based on binary partition trees. It relies on a new BPT construction algorithm that have interesting tuning properties. Besides, access to image pixels from the tree is achieved efficiently with data compression techniques, and a textual representation of BPT is also provided for interoperability. Finally, we illustrate how the proposed tool takes benefit from probabilistic inference techniques by empowering the BPT with its equivalent factor graph. The relevance of GraphBPT is illustrated in the context of image segmentation. |
---|