Efficient Parallel Connected Components Labeling with a Coarse-to-fine Strategy

no code implementations • 28 Dec 2017 • Jun Chen, Keisuke Nonaka, Ryosuke Watanabe, Hiroshi Sankoh, Houari Sabirin, Sei Naito

This paper proposes a new parallel approach to solve connected components on a 2D binary image implemented with CUDA.

An Optimized Union-Find Algorithm for Connected Components Labeling Using GPUs

no code implementations • 28 Aug 2017 • Jun Chen, Qiang Yao, Houari Sabirin, Keisuke Nonaka, Hiroshi Sankoh, Sei Naito

In this paper, we report an optimized union-find (UF) algorithm that can label the connected components on a 2D image efficiently by employing the GPU architecture.