The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The performance of smoothness-enforced Bayesian PET image reconstruction is strongly affected by the weight on regularization. Compromises need to be made between variance and spatial resolution. In this work, we propose to use an artificial neural network (ANN) to fuse the image versions reconstructed from a maximum a posteriori (MAP) algorithm with different regularizing weights for quantitative...
To reduce the potential radiation risk, low-dose CT has attracted much attention. However, simply lowering the radiation dose will lead to significant deterioration of the image quality. In this paper, we propose a noise reduction method for low-dose CT via deep neural network without accessing original projection data. A deep convolutional neural network is trained to transform low-dose CT images...
The promise of compressive sensing (CS) has been offset by two significant challenges. First, real-world data is not exactly sparse in a fixed basis. Second, current high-performance recovery algorithms are slow to converge, which limits CS to either non-real-time applications or scenarios where massive back-end computing is available. In this paper, we attack both of these challenges head-on by developing...
In this paper, we propose a blind motion deblurring method based on sparse representation and structural self-similarity from a single image. The priors for sparse representation and structural self-similarity are explicitly added into the recovery of the latent image by means of sparse and multi-scale nonlocal regularizations, and the down-sampled version of the observed blurry image is used as training...
Since the quality of depth maps produced by Time-of-Flight (TOF) cameras is low, color-guided recovery methods have been proposed to increase spatial resolution and suppress unwanted noise. Despite successful applications of deep neural networks in color image super-resolution (SR), their potential for depth map SR is largely unknown. In this paper, we present a deep neural network architecture to...
In this paper, we propose a novel method for face hallucination by learning a new distance metric in the low-resolution (LR) patch space (source space). Local patch-based face hallucination methods usually assume that the two manifolds formed by LR and high-resolution (HR) image patches have similar local geometry. However, this assumption does not hold well in practice. Motivated by metric learning...
Visual object counting (VOC) is important in many real-world applications. Our previous work approximated sparsity-constrain example-based VOC (ASE-VOC) works well with insufficient training data. It assumes that image patches share the similar local geometry with counterpart density maps, and then the density map of the image patch can be estimated by preserving such geometry. However. ASE-VOC has...
Conventional unsupervised image segmentation methods use color and geometric information and apply clustering algorithms over pixels. They preserve object boundaries well but often suffer from over-segmentation due to noise and artifacts in the images. In this paper, we contribute on a preprocessing step for image smoothing, which alleviates the burden of conventional unsupervised image segmentation...
Social media is rocking the world in recent year, which makes modeling social media contents important. However, the heterogeneity of social media data is the main constraint. This paper focuses on inferring emotions from large-scale social media data. Tweets on social media platform, always containing heterogeneous information from different combinations of modalities, are utilized to construct a...
This paper presents an exemplar-based image completion via a new quality measure based on phaseless texture features. The proposed method derives a new quality measure obtained by monitoring errors caused in power spectra, i.e., errors of phaseless texture features, converged through phase retrieval. Even if a target patch includes missing pixels, this measure enables selection of the best matched...
The compressed sensing using dictionary learning has led to state-of-the-art results for magnetic resonance imaging (MRI) reconstruction from highly under-sampled measurements. Dictionary learning had been considered time-consuming especially when the patch size or the number of training patches is large. Recently, double sparsity model and online dictionary learning algorithm were proposed to obtain...
We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the spatial correlation characteristics of the input, thus leading the output to have a more natural visual appearance and better perceptual quality. Based on recent...
In this paper, we propose to address the downscaling of ocean remote sensing data using image super-resolution models based on deep learning, and more particularly Convolutional Neural Networks (CNNs). The goal of this study, for which we focus on satellite-derived Sea Surface Temperature (SST) data, is to evaluate the efficiency and the relevance of deep learning architectures applied to oceanographic...
In the most of super-resolution reconstruction algorithms, high-resolution and low-resolution images are assumed in the same manifold space. However, due to distractions, this assumption is not suitable for the practical applications. This paper proposes a novel super-resolution reconstruction algorithm for face images. In order to consider the manifold inconsistency of high-resolution and low-resolution...
Low Light Level Images (LLLIs) are captured with exceptionally low brightness and low contrast, and cannot be enhanced satisfactorily with ordinary methods. In this paper, we propose a LLLI enhancement method using coupled dictionary learning. During the training stage, a pair of dictionaries and a linear mapping function are learned simultaneously. The dictionary pair aims to describe the raw LLLIs...
Recognition of handwritten numerals has gained much interest in recent years due to its various application potentials. Bangla is a major language in Indian subcontinent and is the first language of Bangladesh; but unfortunately, study regarding handwritten Bangla numeral recognition (HBNR) is very few with respect to other major languages such as English, Roman etc. Some noteworthy research works...
In this paper, a fast method for single image super-resolution using dictionary learning is proposed. In this method, a local high resolution (HR) dictionary is constructed for every patch in the input image. To do this, the information from neighboring patches of the corresponding patch is used. Also, a low resolution (LR) dictionary consists of features obtained from patches of LR images in the...
In this work, we discuss utility of Restricted Boltzmann Machine (RBM) in face-deidentification challenge. GRBM is a generative modeling technique and its unsupervised learning provides vantage of using raw faces data. Faces are deidentified by reconstructed face images from the trained GRBM model. The reconstructed image uses random information from the stochastic units which makes it hard to re-identify...
Several applications benefit from learning coupled representations able to describe data from multiple sources. For instance, cross-domain dictionary learning methods demonstrated to be particularly effective. In this paper we introduce Multi-Paced Dictionary Learning (MPDL) and propose an instantiation of it under the framework of cross-domain dictionary learning. MPDL is inspired by previous works...
In this paper, we propose a novel patch-based face hallucination method that consists of two patch-based sparse autoencoder (SAE) networks and a deep fully connected network (namely traversal network). The SAE networks are used to capture the intrinsic features of low-resolution (LR) images and high-resolution (HR) images in the hidden layers, while the traversal network is used to map features from...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.