Paper
8 May 2024 A multi-center polarmask model for image segmentation
Ya-Lin Wang, Liu Li, Shu-Wang Zhou, Xin Chen
Author Affiliations +
Proceedings Volume 13162, Fourth Symposium on Pattern Recognition and Applications (SPRA 2023); 1316209 (2024) https://doi.org/10.1117/12.3030078
Event: Fourth Symposium on Pattern Recognition and Applications (SPRA2023), 2023, Napoli, Italy
Abstract
In this paper, we introduce a new multi-center instance segmentation model based on the deep learning technique, as a generalization of the classical polarmask model. In contrast to the original polarmask model which imposes a star-convexity shape to approximate the target region, we propose to establish a multi-center model which allows representing the target region via multiple star convex shapes. For this purpose, we extract a set of points, each of which is taken as the centers of star convex shapes, to compute multiple star convex shapes. As a consequence, the final segmentation mask can be naturally generated using the union of all of the detected star convex shapes. Experimental results show that the multi-center polarmask model can achieve more advanced performance on the COCO dataset. In addition, the introduced model provides the possibility for real-time applications.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Ya-Lin Wang, Liu Li, Shu-Wang Zhou, and Xin Chen "A multi-center polarmask model for image segmentation", Proc. SPIE 13162, Fourth Symposium on Pattern Recognition and Applications (SPRA 2023), 1316209 (8 May 2024); https://doi.org/10.1117/12.3030078
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Stars

Contour modeling

Data modeling

Object detection

Target detection

Visual process modeling

Back to Top