Filters








75,858 Hits in 3.3 sec

An HVS-Directed Neural-Network-Based Image Resolution Enhancement Scheme for Image Resizing

Chin-Teng Lin, Kang-Wei Fan, Her-Chang Pu, Shih-Mao Lu, Sheng-Fu Liang
2007 IEEE transactions on fuzzy systems  
Bilinear interpolation is used to interpolate the nonsensitive regions and a neural network is proposed to interpolate the sensitive regions along edge directions.  ...  In this paper, a novel human visual system (HVS)directed neural-network-based adaptive interpolation scheme for natural image is proposed.  ...  The weighted interpolation is used and can be presented as (1) where the weights are derived from a neural network.  ... 
doi:10.1109/tfuzz.2006.889875 fatcat:teviyqmifzhbxbnhbrduawnnam

Neural-net modeling for direct and inverse problems of shell theory

O M Maximova, O A Maximova
2016 IOP Conference Series: Materials Science and Engineering  
Some results of neural-net interpolation and extrapolation for direct and inverse problems are discussed.  ...  Effectiveness of the use of neural-net technology for the solving of shell theory problems is shown.  ...  We consider the examples of solving direct and inverse problems [4] using neural networks. Similarly to the direct problem, we solved the problem of interpolation and extrapolation type.  ... 
doi:10.1088/1757-899x/155/1/012031 fatcat:fd2tef4evzceze6aicbafrl33e

A Fast and Accurate Wind Speed and Direction Nowcasting Model for Renewable Energy Management Systems

Saira Al-Zadjali, Ahmed Al Maashri, Amer Al-Hinai, Rashid Al Abri, Swaroop Gajare, Sultan Al Yahyai, Mostafa Bakhtvar
2021 Energies  
The proposed model uses perturbed observations to train the ensemble networks. The trained model is then used to predict the wind speed and direction.  ...  Furthermore, the paper presents an exhaustive investigation of the performance of neural network types and several techniques in training, data splitting, and interpolation.  ...  Acknowledgment: The authors would like to express their thanks and deep appreciation to the Directorate General of Meteorology, Civil Aviation Authority for providing the meteorological data used in this  ... 
doi:10.3390/en14237878 fatcat:a47342v4zrecbimuhe4i7evjhi

Content-adaptive neural filters for image interpolation using pixel classification

Hao Hu, Paul M. Hofman, Gerard de Haan, Nasser M. Nasrabadi, Syed A. Rizvi
2005 Applications of Neural Networks and Machine Learning in Image Processing IX  
We propose a new class of non-linear filters for image interpolation, content-adaptive neural filters using pixel classification.  ...  In this paper, we propose a new class of non-linear filters for image interpolation, content-adaptive neural (CN) filters using pixel classification, that is, the coefficients of the proposed neural filters  ...  CONCLUSION In this paper, we proposed content-adaptive neural filters for image interpolation as a direct extension of the content-adaptive linear filters using the same pixel classification.  ... 
doi:10.1117/12.592472 fatcat:jd2z6etvpregng25xpxczisryq

Scanned images resolution improvement using neural networks

Antigoni Panagiotopoulou, Vassilis Anastassopoulos
2007 Neural computing & applications (Print)  
A novel method of improving the spatial resolution of scanned images, by means of neural networks, is presented in this paper.  ...  Images of different resolution, originating from scanner, successively train a neural network, which learns to improve resolution from 25 to 50 pixels-per-inch (ppi), then from 100 to 200 ppi and finally  ...  A novel image interpolation scheme, using an artificial neural network, is described in [13] .  ... 
doi:10.1007/s00521-007-0106-x fatcat:fsebqqyebfheppzzkpt7h54eju

Comparison of Three Compensation Methods for the Touch-trigger Probe Pretravel Errors

Simi Li, Long Zeng, Pingfa Feng, Dingwen Yu
2020 IOP Conference Series: Materials Science and Engineering  
Subsequently, the calibration data are used in three compensation methods that the bilinear interpolation method, the bicubic Coons pitch interpolation method and the neural network method.  ...  On-machine inspection (OMI) system has been used extensively for automatic setting of the workpiece and determination of kinematic error in machine tool.  ...  Third, neural network method is used to calculate the pre-travel errors in un-calibrated directions.  ... 
doi:10.1088/1757-899x/751/1/012036 fatcat:nio6enfyurfi7all3s467qnmlq

Adaptive Demosaicking using Multiple Neural Networks

Yangjing Long, Yizhen Huang
2006 Machine Learning for Signal Processing  
And interpolation is edge-directed with different networks for different chosen directions.  ...  Based on this, an adaptive scheme is proposed that uses more complex neural networks to tackle steep areas in larger sizes of neighborhoods.  ...  This is an advantage to use neural networks.  ... 
doi:10.1109/mlsp.2006.275574 fatcat:m6fqvfqeundrpiacvzg5i7dxli

Artificial Neural Networks for Single-Image Super-Resolution

Gagandeep Singh, Gulshan Goyal
2015 International Journal of Computer Applications  
The performance of neural network is compared to bicubic interpolation method in terms of PSNR and MSE.  ...  The process is a tradeoff between efficiency, time and the quality of output images obtained .In present paper, a feed forward neural network using supervised training for image upscaling is proposed.  ...  The paper implements image upscaling via artificial neural networks using bicubic interpolation.  ... 
doi:10.5120/21786-5075 fatcat:h524gnmgezazjp4nv3sp5mcjlu

Deep-neural-network based sinogram synthesis for sparse-view CT image reconstruction

Hoyeon Lee, Jongha Lee, Hyeongseok Kim, Byungchul Cho, Seungryong Cho
2018 IEEE Transactions on Radiation and Plasma Medical Sciences  
In this work, we introduce a deep-neural-network-enabled sinogram synthesis method for sparse-view CT, and show its outperformance to the existing interpolation methods and also to the iterative image  ...  Interpolation methods have also been utilized to fill the missing data in the sinogram of sparse-view CT thus providing synthetically full data for analytic image reconstruction.  ...  directional interpolation), and images from the sinograms synthesized by two different deep neural networks.  ... 
doi:10.1109/trpms.2018.2867611 fatcat:7mb5jcn2jfacjlhka7e3pwgiu4

Mobile Position Estimation based on Three Angles of Arrival using an Interpolative Neural Network

Omar WaleedAbdulwahhab
2014 International Journal of Computer Applications  
General Terms Neural networks. Keywords Angle of arrival (AOA), average position, optimal position, interpolative neural network.  ...  In this paper, the memorization capability of a multilayer interpolative neural network is exploited to estimate a mobile position based on three angles of arrival.  ...  If , it is a heteroassociative neural network, while if , it is an interpolative neural network.  ... 
doi:10.5120/17534-8109 fatcat:kb2wbzbym5a6vbap6pqec6zcni

Light Source Storage and Interpolation for Global Illumination: A Neural Solution [chapter]

Samuel Delepoulle, Christophe Renaud, Philippe Preux
2009 Studies in Computational Intelligence  
The data describing the luminances distribution are used to train a dedicated neural network during a learning step.  ...  In this paper we propose to approximate any photometric solid by the way of artificial neural networks.  ...  Neural Networks for Photometric Representation Structure of the Neural Network For this work, we used a network with three layers.  ... 
doi:10.1007/978-3-642-03452-7_5 fatcat:7dzc3djq6fe2nn23bsevr2jq44

Video Frame Interpolation via Adaptive Separable Convolution [article]

Simon Niklaus, Long Mai, Feng Liu
2017 arXiv   pre-print
This deep neural network is trained end-to-end using widely available video data without any human annotation.  ...  To address this problem, this paper formulates frame interpolation as local separable convolution over input frames using pairs of 1D kernels.  ...  Figures 5 (top) , 6 (top) are used with permission from Gabor Tarnok.  ... 
arXiv:1708.01692v1 fatcat:5433jh62hfa6ppfn3d5zmeyi4a

Video Frame Interpolation via Adaptive Separable Convolution

Simon Niklaus, Long Mai, Feng Liu
2017 2017 IEEE International Conference on Computer Vision (ICCV)  
This deep neural network is trained end-to-end using widely available video data without any human annotation.  ...  To address this problem, this paper formulates frame interpolation as local separable convolution over input frames using pairs of 1D kernels.  ...  Figures 5 (top) , 6 (top) are used with permission from Gabor Tarnok.  ... 
doi:10.1109/iccv.2017.37 dblp:conf/iccv/NiklausML17 fatcat:6qa4dnf3cza5xm5swqyyx2n5sm

A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct Solar Radiation

Zina Boussaada, Octavian Curea, Ahmed Remaci, Haritza Camblong, Najiba Mrabet Bellaaj
2018 Energies  
As a result, a hybrid dataset is used as neural network input.  ...  For that, a Nonlinear Autoregressive Exogenous (NARX) neural network is used. All the specific conditions of the sailboat operation are taken into account.  ...  Figure 14 shows an example of predicted direct solar radiation day using the obtained NARX neural network model.  ... 
doi:10.3390/en11030620 fatcat:u2lhhywznfbmdn7kmgwciif6s4

Neural BTF Compression and Interpolation

Gilles Rainer, Wenzel Jakob, Abhijeet Ghosh, Tim Weyrich
2019 Computer graphics forum (Print)  
In light of these observations, we propose a neural network-based BTF representation inspired by autoencoders: our encoder compresses each texel to a small set of latent coefficients, while our decoder  ...  An alternative approach uses analytic model fitting to approximate the BTF data, using continuous functions that naturally interpolate well, but whose expressive range is often not wide enough to faithfully  ...  Neural Networks. Several recent works have started using neural networks to render and approximate light transport [RWG * 13, RDL * 15]. Maximov et al.  ... 
doi:10.1111/cgf.13633 fatcat:jdi53znepfbffanmzgnvbknq6u
« Previous Showing results 1 — 15 out of 75,858 results