Optimizing GPU-Based Connected Components Labeling Algorithms

Stefano Allegretti, Federico Bolelli, Michele Cancilla, Costantino Grana

Abstract

Connected Components Labeling (CCL) is a fundamental image processing technique, widely used in various application areas. Computational throughput of Graphical Processing Units (GPUs) makes them eligible for such a kind of algorithms. In the last decade, many approaches to compute CCL on GPUs have been proposed. Unfortunately, most of them have focused on 4-way connectivity neglecting the importance of 8-way connectivity. This paper aims to extend state-of-the-art GPU-based algorithms from 4 to 8-way connectivity and to improve them with additional optimizations. Experimental results revealed the effectiveness of the proposed strategies.
BibTeX
@inproceedings{allegretti2018optimizing,
  author = {Stefano Allegretti and Federico Bolelli and Michele Cancilla and Costantino Grana},
  title = {{Optimizing GPU-Based Connected Components Labeling Algorithms}},
  booktitle = {IPAS},
  year = {2018},
  doi = {10.1109/ipas.2018.8708900},
}

Loading related content...

Figure