An Iterative Spanning Forest Framework for Superpixel Segmentation

• Published in: IEEE transactions on image processing Vol. 28; no. 7; pp. 3477 - 3489
• Main Authors: Vargas-Munoz, John E., Chowdhury, Ananda S., Alexandre, Eduardo B., Galvao, Felipe L., Vechiatto Miranda, Paulo A., Falcao, Alexandre X.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.07.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Computer science; Computer vision; connectivity function; Convergence; Datasets; Forestry; Graph theory; Image color analysis; Image foresting transform; Image processing; Image segmentation; Information systems; Iterative methods; mixed seed sampling; Seeds; spanning forests; superpixel/supervoxel segmentation; Vegetation
• ISSN: 1057-7149; 1941-0042; 1941-0042
• DOI: 10.1109/TIP.2019.2897941

Superpixel segmentation has emerged as an important research problem in the areas of image processing and computer vision. In this paper, we propose a framework, namely Iterative Spanning Forest (ISF), in which improved sets of connected superpixels (supervoxels in 3D) can be generated by a sequence of image foresting transforms. In this framework, one can choose the most suitable combination of ISF components for a given application-i.e., 1) a seed sampling strategy; 2) a connectivity function; 3) an adjacency relation; and 4) a seed pixel recomputation procedure. The superpixels in ISF structurally correspond to spanning trees rooted at those seeds. We present five ISF-based methods to illustrate different choices for those components. These methods are compared with a number of state-of-the-art approaches with respect to effectiveness and efficiency. Experiments are carried out on several datasets containing 2D and 3D objects with distinct texture and shape properties, including a high-level application, named sky image segmentation. The theoretical properties of ISF are demonstrated in the supplementary material and the results show ISF-based methods rank consistently among the best for all datasets.