Incremental watershed cuts: Interactive segmentation algorithm with parallel strategy

作     者：Lebon, Quentin Lefevre, Josselin Cousty, Jean Perret, Benjamin 

作者机构：Univ Gustave Eiffel LIGM CNRS F-77454 Marne La Vallee France Thermo Fisher Sci Bordeaux France 

出 版 物：《PATTERN RECOGNITION LETTERS》 (Pattern Recogn. Lett.)

年 卷 期：2025年第189卷

页      面：256-263页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：French ANR [ANR-20-CE23-0019] French ANRT [2021/1698] Agence Nationale de la Recherche (ANR) [ANR-20-CE23-0019] Funding Source: Agence Nationale de la Recherche (ANR) 

主　　题：Interactive segmentation Watershed Binary partition tree Minimum spanning tree Parallel labeling 

摘      要：In this article, we design an incremental method for computing seeded watershed cuts for interactive image segmentation. We propose an algorithm based on the hierarchical image representation called the binary partition tree to compute a seeded watershed cut. Additionally, we leverage properties of minimum spanning forests to introduce a parallel method for labeling a connected component. We show that those algorithms fits perfectly in an interactive segmentation process by handling user interactions, seed addition or removal, in linear time with respect to the number of affected pixels. Run time comparisons with several state-of-the-art interactive and non-interactive watershed methods show that the proposed method can handle user interactions much faster than previous methods with a significant speedup ranging from 10 to 60 on both 2D and 3D images, thus improving the user experience on large images.