Results 221 to 230 of about 36,154 (265)

Radar-Based Road Surface Classification Using Range-Fast Fourier Transform Learning Models. [PDF]

Sensors (Basel)
Lee H, Kim J, Ko K, Han H, Youm M.
europepmc   +1 more source

Blur Kernel Estimation by Using Bees Algorithm

, 2016
openaire   +2 more sources

Some of the next articles are maybe not open access.

Related searches:

Partial Deconvolution With Inaccurate Blur Kernel

IEEE Transactions on Image Processing, 2018
Most non-blind deconvolution methods are developed under the error-free kernel assumption, and are not robust to inaccurate blur kernel. Unfortunately, despite the great progress in blind deconvolution, estimation error remains inevitable during blur kernel estimation. Consequently, severe artifacts such as ringing effects and distortions are likely to
Dongwei Ren, Wangmeng Zuo, David Zhang   +2 more
exaly   +3 more sources

Variational Dirichlet Blur Kernel Estimation

IEEE Transactions on Image Processing, 2015
Blind image deconvolution involves two key objectives: 1) latent image and 2) blur estimation. For latent image estimation, we propose a fast deconvolution algorithm, which uses an image prior of nondimensional Gaussianity measure to enforce sparsity and an undetermined boundary condition methodology to reduce boundary artifacts. For blur estimation, a
Xu Zhou, Javier Mateos, Fugen Zhou
exaly   +3 more sources

Robust Image Deblurring With an Inaccurate Blur Kernel

IEEE Transactions on Image Processing, 2012
Most existing nonblind image deblurring methods assume that the blur kernel is free of error. However, it is often unavoidable in practice that the input blur kernel is erroneous to some extent. Sometimes, the error could be severe, e.g., for images degraded by nonuniform motion blurring. When an inaccurate blur kernel is used as the input, significant
Hui Ji
exaly   +3 more sources

Unsupervised Blur Kernel Learning for Pansharpening

IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, 2020
Deep learning (DL) for pansharpening has recently attracted considerable attentions. To construct training data, DL based pansharpening approaches often downsample the original multispectral image (MSI) and panchromatic image (PAN) with fixed blur kernel, which can be different from the real point spread functions (PSF) of the satellites.
Anjing Guo, Renwei Dian, Shutao Li
exaly   +2 more sources

Blur kernel estimation to improve recognition of blurred faces

2012 19th IEEE International Conference on Image Processing, 2012
This paper proposes an efficient blind deconvolution method to deblur face images for face recognition. The method involves a salient edge map construction, blur kernel estimation and face image deconvolution. The combined Yale and Extended Yale face database B containing different illumination changes and blur conditions are used to evaluated the face
Chan, CH, Kittler, J
openaire   +2 more sources

Blur-Kernel Bound Estimation From Pyramid Statistics

IEEE Transactions on Circuits and Systems for Video Technology, 2016
This letter presents an approach for automatically estimating the spatial bound of the blur kernel in a motion-blurred image based on the statistics of multilevel image gradients. We observe that blur has a significant impact on the histogram of oriented gradients (HOGs) at higher levels of an image pyramid, but has much less of an impact at coarser ...
Jue Wang
exaly   +2 more sources

Automatic blur-kernel-size estimation for motion deblurring

Visual Computer, 2014
Existing image deblurring approaches often take the blur-kernel-size as an important manual parameter. When set improperly, this parameter can lead to significant errors in the estimated blur kernels. However, manually specifying a proper kernel size for an input image is usually a tedious trial-and-error process.
Jue Wang, Sunghyun Cho
exaly   +2 more sources

Joint Image Registration and Blur Kernel Learning for Pansharpening

2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2021
Image registration and the estimation of spatial and spectral blur kernels are essential steps before fusing panchromatic image (PAN) and multispectral image (MSI). Usually, these basic steps are performed separately, which will lead to error accumulation and ultimately affect the fusion performance. In this paper, we propose a novel deep learning (DL)
Anjing Guo, Yue Wu 0007, Shutao Li
openaire   +1 more source