Search results for "Convolution"
showing 10 items of 334 documents
Free segmentation in rendered 3D images through synthetic impulse response in integral imaging
2016
Integral Imaging is a technique that has the capability of providing not only the spatial, but also the angular information of three-dimensional (3D) scenes. Some important applications are the 3D display and digital post-processing as for example, depth-reconstruction from integral images. In this contribution we propose a new reconstruction method that takes into account the integral image and a simplified version of the impulse response function (IRF) of the integral imaging (InI) system to perform a two-dimensional (2D) deconvolution. The IRF of an InI system has a periodic structure that depends directly on the axial position of the object. Considering different periods of the IRFs we …
A time evolution model for total-variation based blind deconvolution
2007
Departamento Matematica Aplicada, Universidad de Valencia, Burjassot 46100, Spain.We propose a time evolution model for total-variation based blind deconvolution consisting of two evolution equations evolv-ing the signal by means of a nonlinear scale space method and the kernel by using a diffusion equation starting from the zerosignal and a delta function respectively. A preliminary numerical test consisting of blind deconvolution of a noiseless blurredimage is presented.
Automatic program for peak detection and deconvolution of multi-overlapped chromatographic signals
2005
Several interlinked algorithms for peak deconvolution by non-linear regression are presented. These procedures, together with the peak detection methods outlined in Part I, have allowed the implementation of an automatic method able to process multi-overlapped signals, requiring little user interaction. A criterion based on the evaluation of the multivariate selectivity of the chromatographic signal is used to auto-select the most efficient deconvolution procedure for each chromatographic situation. In this way, non-optimal local solutions are avoided in cases of high overlap, and short computation times are obtained in situations of high resolution. A new algorithm, fitting both the origin…
Sparse Deconvolution Using Support Vector Machines
2008
Sparse deconvolution is a classical subject in digital signal processing, having many practical applications. Support vector machine (SVM) algorithms show a series of characteristics, such as sparse solutions and implicit regularization, which make them attractive for solving sparse deconvolution problems. Here, a sparse deconvolution algorithm based on the SVM framework for signal processing is presented and analyzed, including comparative evaluations of its performance from the points of view of estimation and detection capabilities, and of robustness with respect to non-Gaussian additive noise. Publicado
Deconvolution by Regularized Matching Pursuit
2014
In this chapter, an efficient method that restores signals from strongly noised blurred discrete data is presented. The method can be characterized as a Regularized Matching Pursuit (RMP), where dictionaries consist of spline wavelet packets. It combines ideas from spline theory, wavelet analysis and greedy algorithms. The main distinction from the conventional matching pursuit is that different dictionaries are used to test the data and to approximate the solution. In addition, oblique projections of data onto dictionary elements are used instead of orthogonal projections, which are used in the conventional Matching Pursuit (MP). The slopes of the projections and the stopping rule for the …
A sensor-data-based denoising framework for hyperspectral images
2015
Many denoising approaches extend image processing to a hyperspectral cube structure, but do not take into account a sensor model nor the format of the recording. We propose a denoising framework for hyperspectral images that uses sensor data to convert an acquisition to a representation facilitating the noise-estimation, namely the photon-corrected image. This photon corrected image format accounts for the most common noise contributions and is spatially proportional to spectral radiance values. The subsequent denoising is based on an extended variational denoising model, which is suited for a Poisson distributed noise. A spatially and spectrally adaptive total variation regularisation term…
Learning to Navigate in the Gaussian Mixture Surface
2021
In the last years, deep learning models have achieved remarkable generalization capability on computer vision tasks, obtaining excellent results in fine-grained classification problems. Sophisticated approaches based-on discriminative feature learning via patches have been proposed in the literature, boosting the model performances and achieving the state-of-the-art over well-known datasets. Cross-Entropy (CE) loss function is commonly used to enhance the discriminative power of the deep learned features, encouraging the separability between the classes. However, observing the activation map generated by these models in the hidden layer, we realize that many image regions with low discrimin…
First M87 Event Horizon Telescope Results. IV. Imaging the Central Supermassive Black Hole
2019
We present the first Event Horizon Telescope (EHT) images of M87, using observations from April 2017 at 1.3 mm wavelength. These images show a prominent ring with a diameter of ~40 μas, consistent with the size and shape of the lensed photon orbit encircling the "shadow" of a supermassive black hole. The ring is persistent across four observing nights and shows enhanced brightness in the south. To assess the reliability of these results, we implemented a two-stage imaging procedure. In the first stage, four teams, each blind to the others' work, produced images of M87 using both an established method (CLEAN) and a newer technique (regularized maximum likelihood). This stage allowed us to av…
SuperHistopath: A Deep Learning Pipeline for Mapping Tumor Heterogeneity on Low-Resolution Whole-Slide Digital Histopathology Images.
2021
High computational cost associated with digital pathology image analysis approaches is a challenge towards their translation in routine pathology clinic. Here, we propose a computationally efficient framework (SuperHistopath), designed to map global context features reflecting the rich tumor morphological heterogeneity. SuperHistopath efficiently combines i) a segmentation approach using the linear iterative clustering (SLIC) superpixels algorithm applied directly on the whole-slide images at low resolution (5x magnification) to adhere to region boundaries and form homogeneous spatial units at tissue-level, followed by ii) classification of superpixels using a convolution neural network (CN…
GridNet with Automatic Shape Prior Registration for Automatic MRI Cardiac Segmentation
2018
In this paper, we propose a fully automatic MRI cardiac segmentation method based on a novel deep convolutional neural network (CNN) designed for the 2017 ACDC MICCAI challenge. The novelty of our network comes with its embedded shape prior and its loss function tailored to the cardiac anatomy. Our model includes a cardiac center-of-mass regression module which allows for an automatic shape prior registration. Also, since our method processes raw MR images without any manual preprocessing and/or image cropping, our CNN learns both high-level features (useful to distinguish the heart from other organs with a similar shape) and low-level features (useful to get accurate segmentation results).…