RISF: Recursive Iterative Spanning Forest for Superpixel Segmentation
| Autor: | Felipe Lemes Galvão, Alexandre X. Falcão, Ananda S. Chowdhury |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Superpixel segmentation
Geodesic Computer science business.industry Spanning forest 020206 networking & telecommunications Pattern recognition 02 engineering and technology Image segmentation 3d image 0202 electrical engineering electronic engineering information engineering Adjacency list 020201 artificial intelligence & image processing Segmentation Adjacency relation Artificial intelligence business |
| Zdroj: | SIBGRAPI |
| DOI: | 10.1109/sibgrapi.2018.00059 |
| Popis: | Methods for superpixel segmentation have become very popular in computer vision. Recently, a graph-based framework named ISF (Iterative Spanning Forest) was proposed to obtain connected superpixels (supervoxels in 3D) based on multiple executions of the Image Foresting Transform (IFT) algorithm from a given choice of four components: a seed sampling strategy, an adjacency relation, a connectivity function, and a seed recomputation procedure. In this paper, we extend ISF to introduce a unique characteristic among superpixel segmentation methods. Using the new framework, termed as Recursive Iterative Spanning Forest (RISF), one can recursively generate multiple segmentation scales on region adjacency graphs (i.e., a hierarchy of superpixels) without sacrificing the efficiency and effectiveness of ISF. In addition to a hierarchical segmentation, RISF allows a more effective geodesic seed sampling strategy, with no negative impact in the efficiency of the method. For a fixed number of scales using 2D and 3D image datasets, we show that RISF can consistently outperform the most competitive ISF-based methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|