Results 21 to 30 of about 1,112 (156)
Deep learning: Applications, architectures, models, tools, and frameworks: A comprehensive survey
CAAI Transactions on Intelligence Technology, Volume 8, Issue 3, Page 581-606, September 2023., 2023 Abstract Deep Learning (DL) is a subfield of machine learning that significantly impacts extracting new knowledge. By using DL, the extraction of advanced data representations and knowledge can be made possible. Highly effective DL techniques help to find more hidden knowledge.
Mehdi Gheisari +10 more
wiley +1 more source
Asymptotic Analysis of Inpainting via Universal Shearlet Systems [PDF]
, 2014 Recently introduced inpainting algorithms using a combination of applied harmonic analysis and compressed sensing have turned out to be very successful.
Genzel, Martin, Kutyniok, Gitta
core +2 more sources
Shearlet Coorbit Spaces: Compactly Supported Analyzing Shearlets, Traces and Embeddings [PDF]
Journal of Fourier Analysis and Applications, 2011 The authors show that compactly supported functions with sufficient smoothness and enough vanishing moments can serve as analyzing vectors for shearlet coorbit space. This approach has bee used to prove embedding theorems for subspaces of shearlet coorbit spaces resembling shearlets on the cone into Besov spaces.
Dahlke, Stephan +2 more
openaire +2 more sources
River boundary detection and autonomous cruise for unmanned surface vehicles
IET Image Processing, Volume 17, Issue 11, Page 3196-3215, 18 September 2023., 2023 The detection of river boundaries is important for judging the drivable area of USVs, and it can also be utilized to ensure driving safety by limiting the effective drivable areas of the USVs in the river areas. This work proposes a real‐time detection method for river boundaries based on a LiDAR sensor to detect the boundaries of incompletely ...
Kai Zhang +5 more
wiley +1 more source
SAR Interferogram Filtering of Shearlet Domain Based on Interferometric Phase Statistics
Applied Sciences, 2017 This paper presents a new filtering approach for Synthetic Aperture Radar (SAR) interferometric phase noise reduction in the shearlet domain, depending on the coherent statistical characteristics.
Yonghong He +5 more
doaj +1 more source
Digital Shearlet Transforms [PDF]
, 2012 Over the past years, various representation systems which sparsely approximate functions governed by anisotropic features such as edges in images have been proposed. We exemplarily mention the systems of contourlets, curvelets, and shearlets. Alongside the theoretical development of these systems, algorithmic realizations of the associated transforms ...
Gitta Kutyniok +2 more
openaire +3 more sources
TEXT LOCALIZATION IN SCENE IMAGES BY BENDELET TRANSFORM
International Journal of Advances in Signal and Image Sciences, 2019 In an automated text recognition system, one of the prerequisites is the localization of text. It is a challenging task in scene image due to their background and non uniform size of characters in the images.
Ajay Kumar Gupta, Rama Krishna K
doaj +1 more source
Iterative CT reconstruction using shearlet-based regularization [PDF]
, 2012 In computerized tomography, it is important to reduce the image noise without increasing the acquisition dose. Extensive research has been done into total variation minimization for image denoising and sparse-view reconstruction. However, TV minimization
Goossens, Bart +6 more
core +1 more source
Different Faces of the Shearlet Group [PDF]
The Journal of Geometric Analysis, 2015 Recently, shearlet groups have received much attention in connection with shearlet transforms applied for orientation sensitive image analysis and restoration. The square integrable representations of the shearlet groups provide not only the basis for the shearlet transforms but also for a very natural definition of scales of smoothness spaces, called ...
Dahlke, Stephan +5 more
openaire +4 more sources
Image interpolation using Shearlet based iterative refinement [PDF]
, 2013 This paper proposes an image interpolation algorithm exploiting sparse representation for natural images. It involves three main steps: (a) obtaining an initial estimate of the high resolution image using linear methods like FIR filtering, (b) promoting ...
Kutyniok, G. +5 more
core +2 more sources