Abstract | ||
---|---|---|
Classification of distorted patterns poses real problem for majority of classifiers. In this paper we analyse robustness of deep neural network in classification of such patterns. Using specific convolutional network architecture, an impact of different types of noise on classification accuracy is evaluated. For highly distorted patterns to improve accuracy we propose a preprocessing method of input patterns. Finally, an influence of different types of noise on classification accuracy is also analysed. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-39384-1_60 | ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, (ICAISC 2016), PT II |
Keywords | Field | DocType |
Noise, Image recognition, Convolutional neural networks | Pattern recognition,Convolutional neural network,Computer science,Network architecture,Robustness (computer science),Preprocessor,Artificial intelligence,Artificial neural network,Deep neural networks | Conference |
Volume | ISSN | Citations |
9693 | 0302-9743 | 2 |
PageRank | References | Authors |
0.39 | 6 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michal Koziarski | 1 | 18 | 3.66 |
Boguslaw Cyganek | 2 | 145 | 24.53 |