Publ3 search

Z6_60GI02O0O8IDC0QEJUJ26TJDI4

Error:

Javascript is disabled in this browser. This page requires Javascript. Modify your browser's settings to allow Javascript to execute. See your browser's documentation for specific instructions.

Publikační činnost

Probíhá načítání, čekejte prosím...

Record type:	stať ve sborníku (D)
Home Department:	Ústav pro výzkum a aplikace fuzzy modelování (94410)
Title:	Scale-Space Theory, F-transform kernels and CNN Realization
Citace	Molek, V. a Perfiljeva, I. Scale-Space Theory, F-transform kernels and CNN Realization. In: 15th International Work-Conference on Artificial Neural Networks: 15th International Work-Conference on Artificial Neural Networks 2019-06-12 Gran Canaria. Cham: Springer, 2019. s. 38-48. ISBN 978-3-030-20518-8.

Subtitle
Publication year:	2019
Obor:	Obecná matematika
Number of pages:	11
Page from:	38
Page to:	48
Form of publication:	Tištená verze
ISBN code:	978-3-030-20518-8
ISSN code:	0302-9743
Proceedings title:	15th International Work-Conference on Artificial Neural Networks
Proceedings:	Mezinárodní
Publisher name:	Springer
Place of publishing:	Cham
Country of Publication:	Sborník vydaný v zahraničí
Název konference:	15th International Work-Conference on Artificial Neural Networks
Conference venue:	Gran Canaria
Datum zahájení konference:
Typ akce podle státní příslušnosti účastníků:	Celosvětová akce
WoS code:
EID:	2-s2.0-85067569292

Key words in English:	F-transforminitializationscale-spaceconvolutional neural networkclassification
Annotation in original language:	We present scale-space and F-transform inspired modification to convolutional neural networks. The proposed modification improves network classification accuracy using multi-scale image representation and F-transform kernels pre-training. We evaluate our model on two databases and show better performance than networks without F-transform pre-training.
Annotation in english language:

References

Reference

R01:	RIV/61988987:17610/19:A2001ZU6

Complementary Content

${loading}