Classification for degraded images having various levels of degradation is very important in practical applications. This paper proposes a convolutional neural network to classify degraded images by using a restoration network and an ensemble learning. The results demonstrate that the proposed network can classify degraded images over various levels of degradation well. This paper also reveals how the image-quality of training data for a classification network affects the classification performance of degraded images.
@article{arxiv.2006.08145,
title = {Classifying degraded images over various levels of degradation},
author = {Kazuki Endo and Masayuki Tanaka and Masatoshi Okutomi},
journal= {arXiv preprint arXiv:2006.08145},
year = {2020}
}
Comments
Accepted by the 27th IEEE International Conference on Image Processing (ICIP 2020)