Abstract | ||
---|---|---|
Various superpixel approaches have been published recently. These algorithms are assessed using different evaluation metrics and datasets resulting in discrepancy in algorithm comparison. This calls for a benchmark to compare the state-of-the-arts methods and evaluate their pros and cons. We analyze benchmark metrics, datasets and built a superpixel benchmark. We evaluated and integrated top 15 superpixel algorithms, whose code are publicly available, into one code library and, provide a quantitative comparison of these algorithms. We find that some superpixel algorithms perform consistently better than others. Clustering based superpixel algorithms are more efficient than graph-based ones. Furthermore, we also introduced a novel metric to evaluate superpixel regularity, which is a property that superpixels desired. The evaluation results demonstrate the performance and limitations of state-of-the-art algorithms. Our evaluation and observations give deep insight about different algorithms and will help researchers to identify the more feasible superpixel segmentation methods for their different problems. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1016/j.image.2017.04.007 | Signal Processing: Image Communication |
Keywords | Field | DocType |
Superpixel,Benchmark,Evaluation | Data mining,Graph,Computer vision,Computer science,Artificial intelligence,Cluster analysis,Machine learning,Superpixel segmentation | Journal |
Volume | ISSN | Citations |
56 | 0923-5965 | 20 |
PageRank | References | Authors |
0.71 | 32 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Murong Wang | 1 | 22 | 2.11 |
X. Liu | 2 | 32 | 8.04 |
Yixuan Gao | 3 | 20 | 0.71 |
Xiao Ma | 4 | 252 | 34.88 |
Nouman Qadeer Soomro | 5 | 29 | 2.25 |