CNN-Based Classification of Degraded Images With Awareness of Degradation Levels

Image classification needs to consider the existence of image degradations in practice. Although degraded images have various levels of degradation, the degradation levels are usually unknown. This paper proposes a convolutional neural network to classify degraded images by using a restoration network and an ensemble learning. The proposed network can automatically infer ensemble weights by using estimated degradation levels of degraded images and features of restored images, where the degradation levels are estimated internally. The proposed network is mainly discussed with JPEG distortion, while degradations of both Gaussian noise and blurring are also examined. We demonstrate that the proposed network can classify degraded images over various levels of degradation. This paper also reveals how the image-quality of training data for a classification network affects the classification performance of degraded images.

Automated summary

A convolutional neural network is proposed in this paper that can automatically infer ensemble weights in classifying degraded images of various levels of degradation. It also reveals how the image quality of training data for a classification network affects the classification performance of degraded images.