Results 281 to 290 of about 209,737 (306)

Improved Super-Resolution Reconstruction From Video

IEEE Transactions on Circuits and Systems for Video Technology, 2006
Super-resolution (SR) reconstruction usually consists of four steps: registration, interpolation, restoration, and postprocessing. The registration precision (RP) and the initial SR image estimation (ISIE) greatly influence the quality of reconstructed images. A scheme to enhance RP and ISIE is proposed in this paper.
null Ci Wang, null Ping Xue, W. Lin
openaire   +1 more source

Real time super resolution image reconstruction

2007 International Conference on Intelligent and Advanced Systems, 2007
The super-resolution (SR) imaging is a process of constructing high resolution image using several shifted low resolution images of the same scene. The process should ideally be fast, and should add sharpness and detail, both at edges and in regions without adding artifacts. SR imaging works in two major phases: registration and interpolation. Existing
Varsha H. Patil, Dattatraya S. Bormane, Hemant K. Patil   +2 more
openaire   +1 more source

Algorithms of Super-Resolution Image Reconstruction

2007 International Kharkiv Symposium Physics and Engrg. of Millimeter and Sub-Millimeter Waves (MSMW), 2007
A simple procedure of SR techniques consists of application of a low resolution (LR) image to form a SR image by estimation of the lost information from well-known information. The LR images are registered, and the result is an image with the values non-uniformly distributed through SR image grid, so, this point are sampled and interpolated on the SR ...
Francisco Gomeztagle, Volodymyr Ponomaryov   +1 more
openaire   +1 more source

Confidence map based super-resolution reconstruction

SPIE Proceedings, 2012
Magnetic Resonance Imaging and Computed Tomography usually provide highly anisotropic image data, so that the resolution in the slice-selection direction is poorer than in the in-plane directions. An isotropic high-resolution image can be reconstructed from two orthogonal scans of the same object.
Wissam El Hakimi, Stefan Wesarg
openaire   +1 more source

Spectrum learning for super-resolution tomographic reconstruction

Physics in Medicine & Biology
Abstract Objective. Computed Tomography (CT) has been widely used in industrial high-resolution non-destructive testing. However, it is difficult to obtain high-resolution images for large-scale objects due to their physical limitations.
Zirong Li, Kang An, Hengyong Yu, Fulin Luo, Jiayi Pan, Shaoyu Wang, Jianjia Zhang, Weiwen Wu, Dingyue Chang   +8 more
openaire   +2 more sources

Super-resolution reconstruction of terahertz images

SPIE Proceedings, 2008
A prototype of terahertz imaging system has been built in CSIRO. This imager uses a backward wave oscillator as the source and a Schottky diode as the detector. It has a bandwidth of 500-700 GHz and a source power 10 mW. The resolution at 610 GHz is about 0.85 mm.
Yue Li, Li Li, Andrew Hellicar, Y. Jay Guo   +3 more
openaire   +1 more source

Regularization for Super-Resolution Image Reconstruction

2006
Super-resolution image reconstruction estimates a high-resolution image from a sequence of low-resolution, aliased images. The estimation is an inverse problem and is known to be ill-conditioned, in the sense that small errors in the observed images can cause large changes in the reconstruction.
openaire   +2 more sources

Reconstructed Densenets for Image Super-Resolution

2018 25th IEEE International Conference on Image Processing (ICIP), 2018
Deep learning has been successfully applied to single image super-resolution problem due to its high data fitting ability. However, the trending of deeper layers and wider receptive field to acquire better performance brings high computation complexity and serious information vanishing. To address this problem, we proposed a new Reconstructed DenseNets
Lingfeng Wang, Linwei Qiu, Wei Sui, Chunhong Pan   +3 more
openaire   +1 more source

Super-resolution reconstruction of hyperspectral images

SPIE Proceedings, 2007
Hyperspectral imagery is used for a wide variety of applications, including target detection, tacking, agricultural monitoring and natural resources exploration. The main reason for using hyperspectral imagery is that these images reveal spectral information about the scene that are not available in a single band. Unfortunately, many factors such as
Mohamed Elbakary, Mohammad S. Alam
openaire   +1 more source

Super-resolution reconstruction of image sequences

IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999
In an earlier work (1999), we introduced the problem of reconstructing a super-resolution image sequence from a given low resolution sequence. We proposed two iterative algorithms, the R-SD and the R-LMS, to generate the desired image sequence.
M. Elad, A. Feuer
openaire   +1 more source