Segment My Object: A Pipeline to Extract Segmented Objects in Images based on Labels or Bounding Boxes

Robin Deléarde, Robin Deléarde, Camille Kurtz, Philippe Dejean, Laurent Wendling

2021

Abstract

We propose a pipeline (SegMyO – Segment my object) to automatically extract segmented objects in images based on given labels and / or bounding boxes. When providing the expected label, our system looks for the closest label in the list of outputs, using a measure of semantic similarity. And when providing the bounding box, it looks for the output object with the best coverage, based on several geometric criteria. Associated with a semantic segmentation model trained on a similar dataset, or a good region proposal algorithm, this pipeline provides a simple solution to segment efficiently a dataset without requiring specific training, but also to the problem of weakly-supervised segmentation. This is particularly useful to segment public datasets available with weak object annotations (e.g., bounding boxes and labels from a detection, labels from a caption) coming from an algorithm or from manual annotation. An experimental study conducted on the PASCAL VOC 2012 dataset shows that these simple criteria embedded in SegMyO allow to select the proposal with the best IoU score in most cases, and so to get the best of the pre-segmentation.

Paper Citation

in Harvard Style

Deléarde R., Kurtz C., Dejean P. and Wendling L. (2021). Segment My Object: A Pipeline to Extract Segmented Objects in Images based on Labels or Bounding Boxes. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 618-625. DOI: 10.5220/0010324006180625

in Bibtex Style

@conference{visapp21,
author={Robin Deléarde and Camille Kurtz and Philippe Dejean and Laurent Wendling},
title={Segment My Object: A Pipeline to Extract Segmented Objects in Images based on Labels or Bounding Boxes},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={618-625},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010324006180625},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Segment My Object: A Pipeline to Extract Segmented Objects in Images based on Labels or Bounding Boxes
SN - 978-989-758-488-6
AU - Deléarde R.
AU - Kurtz C.
AU - Dejean P.
AU - Wendling L.
PY - 2021
SP - 618
EP - 625
DO - 10.5220/0010324006180625
PB - SciTePress