Deep Convolutional Neural Networks and Noisy Images

Author(s)

Nazare, Tiago S. ; da Costa, Gabriel B. Paranhos ; Contato, Welinton A. ; Ponti, Moacir

• Document type: Journal article
• Source: PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS, CIARP 2017; v. 10657, p. 9-pg., 2018-01-01.

Abstract

The presence of noise represent a relevant issue in image feature extraction and classification. In deep learning, representation is learned directly from the data and, therefore, the classification model is influenced by the quality of the input. However, the ability of deep convolutional neural networks to deal with images that have a different quality when compare to those used to train the network is still to be fully understood. In this paper, we evaluate the generalization of models learned by different networks using noisy images. Our results show that noise cause the classification problem to become harder. However, when image quality is prone to variations after deployment, it might be advantageous to employ models learned using noisy data. (AU)

• FAPESP's process: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry
• Grantee: Francisco Louzada Neto
• Support Opportunities: Research Grants - Research, Innovation and Dissemination Centers - RIDC
• FAPESP's process: 16/16111-4 - Feature learning applied to sketch-based image retrieval and low-altitude remote sensing
• Grantee: Moacir Antonelli Ponti
• Support Opportunities: Regular Research Grants
• FAPESP's process: 15/05310-3 - Representation Learning of spatio-temporal features from video
• Grantee: Gabriel de Barros Paranhos da Costa
• Support Opportunities: Scholarships in Brazil - Doctorate
• FAPESP's process: 15/04883-0 - Unusual event detection in surveillance videos
• Grantee: Tiago Santana de Nazare
• Support Opportunities: Scholarships in Brazil - Doctorate (Direct)