Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Babak Mazloom-Nezhad Maybodi"'
Publikováno v:
IET Image Processing, Vol 15, Iss 1, Pp 28-46 (2021)
Abstract The definition of an image's category from a database with huge texture categories needs massive computation and time cost. Existing texture classification works focus on texture representation to improve the accuracy and efficiency of class
Externí odkaz:
https://doaj.org/article/e30522f36909427184d46acc8279106a
Publikováno v:
IET Computer Vision, Vol 9, Iss 6, Pp 871-883 (2015)
Local binary patterns (LBPs) are a well‐known operator that shows the ability for rotation and scale invariant texture classification. A recent extension of this operator is the pyramid transform domain approach on LBPs (PLBP). Obtaining more accur
Externí odkaz:
https://doaj.org/article/17d557b65c9545a3b5b44aec10dd9a5b
Publikováno v:
IET Image Processing, Vol 15, Iss 1, Pp 28-46 (2021)
The definition of an image's category from a database with huge texture categories needs massive computation and time cost. Existing texture classification works focus on texture representation to improve the accuracy and efficiency of classification
Publikováno v:
Multimedia Tools and Applications. 79:19193-19214
Contrast is the difference in visual characteristics which make an object more recognizable. Despite the significance of contrast enhancement (CE) in image processing applications, few attempts have been made on assessment of the contrast change. In
Neuromorphic engineers develop event-based spiking neural networks (SNNs) in hardware. These SNNs closer resemble the dynamics of biological neurons than conventional artificial neural networks and achieve higher efficiency thanks to the event-based,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ee5b17413009ab0f0372334f3996ac73
https://www.zora.uzh.ch/id/eprint/200376/
https://www.zora.uzh.ch/id/eprint/200376/
Supervised, unsupervised, and reinforcement learning (RL) mechanisms are known as the most powerful learning paradigms empowering neuromorphic systems. These systems typically take advantage of unsupervised learning because they can learn the distrib
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f3ab16d1ed8031761ee99c870fa8dd8
https://www.zora.uzh.ch/id/eprint/200375/
https://www.zora.uzh.ch/id/eprint/200375/
Publikováno v:
AICAS
Highly efficient performance-resources trade-off of the biological brain is a motivation for research on neuromorphic computing. Neuromorphic engineers develop event-based spiking neural networks (SNNs) in hardware. Learning in SNNs is a challenging
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::30ace2444a7aa1acde84e43f61ea2a5a
https://www.zora.uzh.ch/id/eprint/188460/
https://www.zora.uzh.ch/id/eprint/188460/
Publikováno v:
2020 28th Iranian Conference on Electrical Engineering (ICEE).
Physical Unclonable Functions (PUFs) are one of the efficient approaches to authenticate Internet of Things (IoT) devices. PUFs are inherently noisy. In this paper, using a smart contract, in addition to authentication, one error can be corrected per
Spiking neural networks (SNNs) can achieve lower latency and higher efficiency compared with traditional neural networks if they are implemented in dedicated neuromorphic hardware. In both biological and artificial spiking neuronal systems, synaptic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ce3d701dd74edb967b2fd303d2261af1
https://www.zora.uzh.ch/id/eprint/200379/
https://www.zora.uzh.ch/id/eprint/200379/
Publikováno v:
AEU - International Journal of Electronics and Communications. 77:61-66
Although the contrast enhancement (CE) is a great challenge, few efforts have been conducted on evaluation of the contrast changes. In this paper, we propose a contrast-changed image quality (CCIQ) metric including a local index, named edge-based con