Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Snigdha Tariyal"'
Publikováno v:
IEEE Access, Vol 4, Pp 10096-10109 (2016)
Two popular representation learning paradigms are dictionary learning and deep learning. While dictionary learning focuses on learning “basis” and “features” by matrix factorization, deep learning focuses on extracting features via learning
Externí odkaz:
https://doaj.org/article/c9a867b7603a4d1583fd9c31a49983c3
Publikováno v:
IEEE Transactions on Information Forensics and Security. 12:1713-1723
In movies, film stars portray another identity or obfuscate their identity with the help of silicone/latex masks. Such realistic masks are now easily available and are used for entertainment purposes. However, their usage in criminal activities to de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1d7806fa4a24eec3639efcb46292ee44
https://doi.org/10.1109/tifs.2017.2676720
https://doi.org/10.1109/tifs.2017.2676720
This work proposes a new framework for deep learning that has been particularly tailored for hyperspectral image classification. We learn multiple levels of dictionaries in a robust fashion. The last layer is discriminative that learns a linear class
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ee3c508e6119f78c3ac300b490844997
Publikováno v:
WHISPERS
In this work we propose a new deep learning tool — deep dictionary learning. We give an alternate neural network type interpretation to dictionary learning. Based on this, we build a deep architecture by cascading one dictionary after the other. Th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d5d99de7bd5effb91939d2d0c2b0deb
https://doi.org/10.1109/whispers.2016.8071740
https://doi.org/10.1109/whispers.2016.8071740
Publikováno v:
WHISPERS
There have been a number of studies for addressing the recovery of compressively sampled hyper-spectral images in the presence of Gaussian noise; this work proposes a recovery technique in the presence of impulse noise. Owing to the sparse nature of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0c4649bf619c7234efc35f1f413e132a
https://doi.org/10.1109/whispers.2015.8075396
https://doi.org/10.1109/whispers.2015.8075396
Publikováno v:
WHISPERS
There are various studies on hyperspectral image denoising most of which consider Gaussian denoising problem. There are few studies on reducing impulse noise from correlated hyperspectral images. To reduce impulse noise, in our prior work we exploite
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9d76cfbcecb4f2d39b7a5d006722d13b
https://doi.org/10.1109/whispers.2015.8075397
https://doi.org/10.1109/whispers.2015.8075397
Publikováno v:
Journal of Electronic Imaging. 25:020501
In diffraction grating, at times, there are defective pixels on the focal plane array; this results in horizontal lines of corrupted pixels in some channels. Since only a few such pixels exist, the corruption/noise is sparse. Studies on sparse noise
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::46009c246e061000e0214e56eabb64e2
https://doi.org/10.1117/1.jei.25.2.020501
https://doi.org/10.1117/1.jei.25.2.020501