期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 43, 期 10, 页码 3724-3738出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2020.2980827
关键词
Clustering algorithms; Partitioning algorithms; Image segmentation; Image edge detection; Merging; Correlation; Vegetation; Image segmentation; partitioning algorithms; greedy algorithms; optimization; integer linear programming; machine learning; convolutional neural networks
资金
- Deutsche Forschungsgemeinschft (DFG, German Research Foundation) [240245660 - SFB 1129]
- Baden-Wurttemberg Stiftung Elite PostDoc Program
The Mutex Watershed algorithm proposed in this study offers an efficient solution for image partitioning, capable of detecting different image segments based on attractive and repulsive cues, achieving global optimality in segmentation.
Image partitioning, or segmentation without semantics, is the task of decomposing an image into distinct segments, or equivalently to detect closed contours. Most prior work either requires seeds, one per segment; or a threshold; or formulates the task as multicut / correlation clustering, an NP-hard problem. Here, we propose an efficient algorithm for graph partitioning, the Mutex Watershed. Unlike seeded watershed, the algorithm can accommodate not only attractive but also repulsive cues, allowing it to find a previously unspecified number of segments without the need for explicit seeds or a tunable threshold. We also prove that this simple algorithm solves to global optimality an objective function that is intimately related to the multicut / correlation clustering integer linear programming formulation. The algorithm is deterministic, very simple to implement, and has empirically linearithmic complexity. When presented with short-range attractive and long-range repulsive cues from a deep neural network, the Mutex Watershed gives the best results currently known for the competitive ISBI 2012 EM segmentation benchmark.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据