Assessing Image Quality Issues for Real-World Problems
Abstract
We introduce a new large-scale dataset that links the assessment of image quality issues to two practical vision tasks: image captioning and visual question answering. First, we identify for 39,181 images taken by people who are blind whether each is sufficient quality to recognize the content as well as what quality flaws are observed from six options. These labels serve as a critical foundation for us to make the following contributions: (1) a new problem and algorithms for deciding whether an image is insufficient quality to recognize the content and so not captionable, (2) a new problem and algorithms for deciding which of six quality flaws an image contains, (3) a new problem and algorithms for deciding whether a visual question is unanswerable due to unrecognizable content versus the content of interest being missing from the field of view, and (4) a novel application of more efficiently creating a large-scale image captioning dataset by automatically deciding whether an image is insufficient quality and so should not be captioned. We publicly-share our datasets and code to facilitate future extensions of this work: https://vizwiz.org.
Cite
Text
Chiu et al. "Assessing Image Quality Issues for Real-World Problems." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.00370Markdown
[Chiu et al. "Assessing Image Quality Issues for Real-World Problems." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/chiu2020cvpr-assessing/) doi:10.1109/CVPR42600.2020.00370BibTeX
@inproceedings{chiu2020cvpr-assessing,
title = {{Assessing Image Quality Issues for Real-World Problems}},
author = {Chiu, Tai-Yin and Zhao, Yinan and Gurari, Danna},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2020},
doi = {10.1109/CVPR42600.2020.00370},
url = {https://mlanthology.org/cvpr/2020/chiu2020cvpr-assessing/}
}