Abstract | ||
---|---|---|
Superpixel segmentation has become a popular preprocessing step in computer vision with a great variety of existing algorithms. Almost all algorithms claim to compute compact superpixels, but no one showed how to measure compactness and no one investigated the implications. In this paper, we propose a novel metric to measure superpixel compactness. With this metric, we show that there is a trade-off between compactness and boundary recall. In addition, we propose an algorithm that allows to precisely control this trade-off and that outperforms the current state-of-the-art. As a demonstration, we show the importance of considering compactness with the help of an example application. |
Year | Venue | Keywords |
---|---|---|
2012 | Pattern Recognition | computer vision,image representation,image resolution,image segmentation,boundary recall,computer vision,image representation,novel metric,preprocessing step,superpixel compactness,superpixel segmentation |
Field | DocType | ISSN |
Computer vision,Scale-space segmentation,Feature detection (computer vision),Pattern recognition,Computer science,Image representation,Compact space,Image segmentation,Preprocessor,Artificial intelligence,Image resolution,Superpixel segmentation | Conference | 1051-4651 |
ISBN | Citations | PageRank |
978-1-4673-2216-4 | 17 | 0.66 |
References | Authors | |
13 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alexander Schick | 1 | 17 | 0.66 |
Mika Fischer | 2 | 17 | 0.66 |
Rainer Stiefelhagen | 3 | 3512 | 274.86 |