An empirical study on the effects of different types of noise in image classification tasks

TL;DR

This study investigates how different noise types affect image classification accuracy, analyzing the effectiveness of denoising methods on feature extraction techniques across multiple datasets.

Contribution

It provides an empirical analysis of noise impact on feature descriptors and evaluates denoising strategies to improve classification under noisy conditions.

Findings

Noise significantly reduces classification accuracy.

Denoising improves performance but does not fully restore noise-free results.

Different noise types and levels have varying impacts on feature extraction.

Abstract

Image classification is one of the main research problems in computer vision and machine learning. Since in most real-world image classification applications there is no control over how the images are captured, it is necessary to consider the possibility that these images might be affected by noise (e.g. sensor noise in a low-quality surveillance camera). In this paper we analyse the impact of three different types of noise on descriptors extracted by two widely used feature extraction methods (LBP and HOG) and how denoising the images can help to mitigate this problem. We carry out experiments on two different datasets and consider several types of noise, noise levels, and denoising methods. Our results show that noise can hinder classification performance considerably and make classes harder to separate. Although denoising methods were not able to reach the same performance of the noise-free scenario, they improved classification results for noisy data.