Scholarlink

Superpixels are an effective image segmentation strategy, whose results apply and assist in classification tasks. However, by aiming for maximum performance with a minimum quantity of regions, the object delineation may be compromised, demanding re-segmentation. In this paper, we propose and evaluate three re-segmentation strategies that rely on a novel and accurate superpixel framework, named SICLE, and require minimal intervention from the user (i.e., up to three clicks). Our qualitative and quantitative results show significant improvement over the previous superpixel segmentation for separating the object of interest from the background.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Seed-Based Superpixel Re-Segmentation for Improving Object Delineation

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Lucca S. P. Lacerda,
  • Felipe C. Belém,
  • Zenilton Kleber Gonçalves do Patrocínio Júnior,
  • Alexandre X. Falcão,
  • Silvio J. F. Guimarães

摘要

Superpixels are an effective image segmentation strategy, whose results apply and assist in classification tasks. However, by aiming for maximum performance with a minimum quantity of regions, the object delineation may be compromised, demanding re-segmentation. In this paper, we propose and evaluate three re-segmentation strategies that rely on a novel and accurate superpixel framework, named SICLE, and require minimal intervention from the user (i.e., up to three clicks). Our qualitative and quantitative results show significant improvement over the previous superpixel segmentation for separating the object of interest from the background.