Geometric Transformations Embedded into Convolutional Neural Networks
Ładowanie...
Data
2016
Autorzy
Tytuł czasopisma
ISSN czasopisma
Tytuł tomu
Wydawca
Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press
Lodz University of Technology Press
Abstrakt
This paper presents a novel extension to convolutional neural networks. While CNNs are known for invariance to object translation, changes to the other parameters could make the image recognition tasks diffcult – that includes rotations and scaling. Some improvement in this area could be achieved with embedded geometric transformations used inside the CNNs. In order to provide a practical solution, which allows fast propagation and learning of the modified networks, “fast geometric transformations” are introduced.
Opis
Słowa kluczowe
artificial intelligence, machine learning, deep learning, convolutional neural networks, image processing, image recognition, geometric transformations, sztuczna inteligencja, nauczanie maszynowe, głęboka nauka, splotowe sieci neuronowe, przetwarzanie obrazu, rozpoznawanie obrazu, przekształcenia geometryczne
Cytowanie
Tarasiuk, P., & Pryczek, M. (2016). Geometric Transformations Embedded into Convolutional Neural Networks. Journal of Applied Computer Science, 24(3), 33-48. https://doi.org/10.34658/jacs.2016.24.3.33-48