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.
This paper presents a novel Robust Deep Appearance Models (RDAMs) approach to learn the non-linear correlation between shape and texture of face images. In this approach, two crucial components of face images, i.e. shape and texture, are represented by Deep Boltzmann Machines and Robust Deep Boltzmann Machines (RDBM), respectively. The RDBM, an alternative form of Robust Boltzmann Machines, can separate...
Online 3D reconstruction has been an active research area for a long time. Since the release of the Microsoft Kinect Camera and publication of KinectFusion [11] attention has been drawn how to acquire dense models in real-time. In this paper we present a method to make online 3D reconstruction which increases robustness for scenes with little structure information and little texture information. It...
This paper proposes an original method for extracting the centerline of 3D objects given only partial mesh scans as input data. Its principle relies on the construction of a normal vector accumulation map build by casting digital rays from input vertices. This map is then pruned according to a confidence voting rule: confidence in a point increases if this point has maximal votes along a ray. Points...
Low rank matrix algorithm has attracted widely attention since it was put forward. There are many algorithms proposed to improve it. Most methods take each sample as a column, but Robust Generalized Low Rank Approximations of Matrices(RGLRAM) treats each sample as a matrix, thus we can find the low rank approximations on a collection of matrices not just a single matrix. RGLRAM are not only robust...
Point sets generated by image-based 3D reconstruction techniques are often much noisier than those obtained using active techniques like laser scanning. Therefore, they pose greater challenges to the subsequent surface reconstruction (meshing) stage. We present a simple and effective method for removing noise and outliers from such point sets. Our algorithm uses the input images and corresponding...
We represent human body shape estimation from binary silhouettes or shaded images as a regression problem, and describe a novel method to tackle it using CNNs. Utilizing a parametric body model, we train CNNs to learn a global mapping from the input to shape parameters used to reconstruct the shapes of people, in neutral poses, with the application of garment fitting in mind. This results in an accurate,...
In order to solve the problems of face image super-resolution, a robust online dictionary learning method based on sparse representation is proposed in this paper. The online dictionary learning algorithms which can be used to train big sample datasets is introduced in the dictionary learning phase to generate better overcomplete dictionaries. Additionally, the classic L2-regularization is replaced...
The algorithms for dense correspondences in stereo images are an extensively researched topic, since it is an essential step in a large number of applications. Despite the fact that the first stereo matching algorithms were proposed some decades ago, novel approaches regarding typical, but also cutting-edge applications, are always in demand. Stereo matching is an inverse, ill-posed problem, which...
Attenuation correction is critical to accurate PET quantitation. Accurate and robust attenuation correction remains challenging in hybrid PET/MR because it is difficult to segment bones, internal air and lungs accurately in MR images and MR often suffers from artifacts due to metal implants and signal shading. Joint estimation (JE) of activity and attenuation from time-of-flight (TOF) PET data has...
We previously proposed a fast maximum a posteriori (MAP) algorithm, limited-memory Broyden-Fletcher-Goldfarb-Shanno with boundary constrains (LBFGS-B-PC), combining LBFGS-B with diagonal preconditioning. Previous results have shown in simulations that it converges using around 40 projections independent of many factors. The aim of this study is to improve the algorithm further by using a better initial...
Digital multimedia has drastically increased the production and distribution of digital data in the recent years. Unauthorized manipulation and ownership of digital image have become a serious issue. In this paper, we propose a watermarking scheme which uses block-based Tchebichef moments considering psychovisual threshold. The psychovisual threshold is used to prescribe the potential location of...
Sonar imaging has seen vast improvements over the last few decades due in part to advances in synthetic aperture Sonar (SAS). Because of this, sophisticated classification techniques originally developed for other tasks can be used in Sonar automatic target recognition (ATR) to locate mines and other threatening objects. Among the most promising of these methods is sparse reconstruction-based classification...
Most of current clustering methods are designed for general purpose other than a specific color pixel classification use. Color Line model representation emerged as the ultimate method for clustering pixels using RGB color components. However, this method is strongly sensitive to the adjustment of input parameters, which cannot conform to the frequent change of image structures and compositions. In...
Over the last decade, a lot of research has been done on sound event classification. But a main problem with sound event classification is that the performance sharply degrades in the presence of noise. As spectrogram-based image features and denoising auto encoder reportedly have superior performance in noisy conditions, this paper proposes a new robust feature called denoising auto encoder image...
In this paper we describe a straightforward, yet effective method of recovering angles from a set of tomographic projections when the view-angles are completely unknown. Existing works on this problem have consistently assumed availability of projections from a large number of angles as well as made assumptions on the underlying distribution of angles to aid reconstruction. We make no such assumptions,...
This work considers reconstructing a target signal in a context of distributed sparse sources. We propose an efficient reconstruction algorithm with the aid of other given sources as multiple side information (SI). The proposed algorithm takes advantage of compressive sensing (CS) with SI and adaptive weights by solving a proposed weighted 𝓃-ℓ1 minimization. The proposed algorithm computes the adaptive...
Document is unavailable: This DOI was registered to an article that was not presented by the author(s) at this conference. As per section 8.2.1.B.13 of IEEE's "Publication Services and Products Board Operations Manual," IEEE has chosen to exclude this article from distribution. We regret any inconvenience.
Due to the irregularity in respiratory patterns observed clinically, the acquired data in cardiac SPECT with respiratory-gating can exhibit high variability among both gate intervals and acquisition angles. Such variability can lead to differing noise characteristics among respiratory gates, which would adversely affect the accuracy of motion estimation. To address this difficulty, we develop a joint...
Keypoint detection and description in a continuous scale space achieves better robustness to scale change than those in a discretized scale space. State-of-the-art methods first decompose a continuous scale space into M + 1 component images weighted by M-order polynomials of scale σ, and then reconstruct the value at an arbitrary point in the scale space by a linear combination of the component images...
Adaptive sparse representation has been heavily exploited in signal processing and computer vision. Recently, sparsifying transform learning received interest for its cheap computation and optimal updates in the alternating algorithms. In this work, we develop a methodology for learning a Flipping and Rotation Invariant Sparsifying Transform, dubbed FRIST, to better represent natural images that contain...
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.