Image Quality Assessment using Deep Features for Object Detection

Poonam Beniwal, Pranav Mantini, Shishir K. Shah

2022

Abstract

Applications such as video surveillance and self-driving cars produce large amounts of video data. Computer vision algorithms such as object detection have found a natural place in these scenarios. The reliability of these algorithms is usually benchmarked using curated datasets. However, one of the core challenges of working with computer vision data is variability. Compression is one such parameter that introduces artifacts (variability) in the data and can negatively affect performance. In this paper, we study the effect of compression on CNN-based object detectors and propose a new full-reference image quality metric based on Discrete Cosine Transform (DCT) to quantify the quality of an image for CNN-based object detectors. We compare this metric with commonly used image quality metrics, and the results show that the proposed metric correlates better with object detection performance. Furthermore, we train a regression model to estimate the quality of images for object detection.

Paper Citation

in Harvard Style

Beniwal P., Mantini P. and Shah S. (2022). Image Quality Assessment using Deep Features for Object Detection. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 706-714. DOI: 10.5220/0010917000003124

in Bibtex Style

@conference{visapp22,
author={Poonam Beniwal and Pranav Mantini and Shishir K. Shah},
title={Image Quality Assessment using Deep Features for Object Detection},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={706-714},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010917000003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - Image Quality Assessment using Deep Features for Object Detection
SN - 978-989-758-555-5
AU - Beniwal P.
AU - Mantini P.
AU - Shah S.
PY - 2022
SP - 706
EP - 714
DO - 10.5220/0010917000003124
PB - SciTePress