An empirical study on the effects of different types of noise in image classification tasks
This addresses noise robustness in image classification for real-world applications like surveillance, but it is incremental as it builds on existing feature extraction and denoising methods.
The study analyzed the impact of three types of noise on image classification using LBP and HOG features, finding that noise significantly hinders performance and makes classes harder to separate, with denoising methods improving results for noisy data but not matching noise-free performance.
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.