Loading...
Loading...

Go to the content (press return)

A quaternion deterministic monogenic CNN layer for contrast invariance

Author
Moya, E.; Xambo, S.; Salazar-Colores, S.; Sánchez-Pérez, A.; Cortes, U.
Type of activity
Book chapter
Book
Systems, patterns and data engineering with geometric calculi
First page
133
Last page
152
Publisher
Springer
Date of publication
2021
ISBN
978-3-030-74486-1
DOI
10.1007/978-3-030-74486-1
Repository
http://hdl.handle.net/2117/349717 Open in new window
URL
https://link.springer.com/book/10.1007/978-3-030-74486-1 Open in new window
Abstract
Deep learning (DL) is attracting considerable interest as it currently achieves remarkable performance in many branches of science and technology. However, current DL cannot guarantee capabilities of the mammalian visual systems such as lighting changes. This paper proposes a deterministic entry layer capable of classifying images even with low-contrast conditions. We achieve this through an improved version of the quaternion monogenic wavelets. We have simulated the atmospheric degradation of t...
Citation
Moya, E. [et al.]. A quaternion deterministic monogenic CNN layer for contrast invariance. A: "Systems, patterns and data engineering with geometric calculi". Berlín: Springer, 2021, p. 133-152.
Group of research
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
KEMLG - Knowledge Engineering and Machine Learning Group

Participants