Results 11 to 20 of about 198,293 (212)
Some properties of the spinor fourier transform [PDF]
, 2015 In this paper, the theory of the spinor Fourier transform introduced in [Batard T, Berthier M, Saint-Jean C, Clifford-Fourier Transform for Color Image Processing, Geometric Algebra Computing for Engineering and Computer Science (E.
Batard, Thomas, Raeymaekers, Tim
core +1 more source
TripleMAsk Spatial Linear Filter and Neutrosophic Entropy for Video Denoising, Face Detection and Recognition in Forensic Crime Analysis Using Deep Learning [PDF]
Neutrosophic Sets and SystemsForensic Science is the application of Scientific methods to resolve crime and legal issues. It involves various disciplines, such as Computer Science, Biology, Chemistry and Anthropology.
Anita Sigamani, Dr. Prema Selvaraj
doaj +1 more source
Nonlinear Time-Domain Strip Theory Formulation for Low-Speed Manoeuvering and Station-Keeping [PDF]
Modeling, Identification and Control, 2004 This paper presents a computer effective nonlinear time-domain strip theory formulation for dynamic positioning (DP) and low-speed manoeuvring. Strip theory or 2D potential theory, where the ship is divided in 20 to 30 cross sections, can be used to ...
Thor I. Fossen, Øyvind N. Smogeli
doaj +1 more source
Invariance of visual operations at the level of receptive fields [PDF]
, 2012 Receptive field profiles registered by cell recordings have shown that mammalian vision has developed receptive fields tuned to different sizes and orientations in the image domain as well as to different image velocities in space-time.
Lindeberg, Tony
core +3 more sources
IEEE Access, 2020 A method to extract the retina characteristic points for the purpose of medical diagnosis of the human eye is presented in this research. The proposed method helps to make the primary decision about the illness faster and can be used on mobile devices ...
Maciej Szymkowski +5 more
doaj +1 more source
Brain Network Analysis and Classification Based on Convolutional Neural Network
Frontiers in Computational Neuroscience, 2018 Background: Convolution neural networks (CNN) is increasingly used in computer science and finds more and more applications in different fields. However, analyzing brain network with CNN is not trivial, due to the non-Euclidean characteristics of brain ...
Lu Meng, Jing Xiang
doaj +1 more source
Recurrent Multimodal Interaction for Referring Image Segmentation [PDF]
, 2017 In this paper we are interested in the problem of image segmentation given natural language descriptions, i.e. referring expressions. Existing works tackle this problem by first modeling images and sentences independently and then segment images by ...
Lin, Zhe +5 more
core +2 more sources
Random convolution ensembles [PDF]
, 2007 A novel method for creating diverse ensembles of image classifiers is proposed. The idea is that, for each base image classifier in the ensemble, a random image transformation is generated and applied to all of the images in the labeled training set. The
Mayo, Michael
core +2 more sources
Deformable kernels for early vision [PDF]
, 1995 Early vision algorithms often have a first stage of linear-filtering that `extracts' from the image information at multiple scales of resolution and multiple orientations.
Perona, Pietro
core +1 more source
Detection of exomoons in simulated light curves with a regularized convolutional neural network
, 2020 Many moons have been detected around planets in our Solar System, but none has been detected unambiguously around any of the confirmed extrasolar planets.
Alshehhi, Rasha +3 more
core +1 more source