Classifying degraded images over various levels of degradation

TL;DR

This paper introduces a convolutional neural network that combines restoration and ensemble learning to classify images with varying degradation levels, highlighting the impact of training data quality on performance.

Contribution

It proposes a novel CNN architecture integrating restoration and ensemble methods for classifying degraded images across different degradation levels.

Findings

The network effectively classifies images with various degradation levels.

Training data quality significantly influences classification accuracy.

Ensemble learning enhances robustness against image degradation.

Abstract

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.