Contents Intro.

We present 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. We show that this algorithm 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. Additionally, we design a parallel algorithm for the longest step of the method, namely the connected component labeling of minimum spanning forests. 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.

Details

Publication year

2024

Form

電子化映像資料(1時間32分43秒）

Series title

情報科学領域・コロキアム ; 2024年度

Note

講演日: 2024年7月26日

講演場所: エーアイ大講義室, AI Inc. Seminar Hall （L1）

Country of publication

Japan

Title language

English (eng)

Language of texts

English (eng)

Author information

Jean Cousty