Image recognition with deep neural networks in presence of noise – Dealing with and taking advantage of distortions

Article type: Research Article

Authors: Koziarski, Michał^* | Cyganek, Bogusław

Affiliations: AGH University of Science and Technology, Kraków, Poland

Correspondence: [*] Corresponding author: Michał Koziarski, AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, Poland.

Abstract: Data classification in presence of noise can lead to much worse results than expected for pure patterns. In this paper we investigate this problem in the case of deep convolutional neural networks in order to propose solutions that can mitigate influence of noise. The main contributions presented in this paper are experimental examination of influence of different types of noise on the convolutional neural network, proposition of a deep neural network operating as a denoiser, investigation of a deep network training with noise contaminated patterns, and finally an analysis of noise addition during the training process of a deep network as a form of regularization. Our main findings are construction of the deep network based denoising filter which outperforms state-of-the-art solutions, as well as proposition of a practical method of deep neural network training with noisy patterns for improvement against the noisy test patterns. All results are underpinned by experiments which show high efficacy and possibly broad applications of the proposed solutions.

Keywords: Image recognition, deep neural networks, convolutional neural networks, noise, image denoising, regularization

DOI: 10.3233/ICA-170551

Journal: Integrated Computer-Aided Engineering, vol. 24, no. 4, pp. 337-349, 2017