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.
In this paper, we introduce a novel approach for video compression that explores spatial as well as temporal redundancies over sequences of many frames in a unified framework. Our approach supports “compressed domain vision” capabilities. To this end, we developed a sparse Steered Mixture-of-Experts (SMoE) regression network for coding video in the pixel domain. This approach drastically departs from...
Convolution serves as the basic computational primitive for various associative computing tasks ranging from edge detection to image matching. CMOS implementation of such computations entails significant bottlenecks in area and energy consumption due to the large number of multiplication and addition operations involved. In this paper, we propose an ultra-low power and compact hybrid spintronic-CMOS...
Images taken in low-light environments are often degraded due to camera shake and pixel saturation. In this paper, a motion deblurring method for non-uniform blur is proposed, in which an optimization problem is formulated using a maximum a posteriori approach. In the final deconvolution process, a modified Richardson-Lucy algorithm with regularization is used to reduce ringing artifacts and noise,...
Scale Invariant Feature Transform is a competent algorithm for extracting unique features from images. The fact that features extracted are invariant to image scaling, translation, rotation and partially invariant to illumination changes makes it attractive in many computer vision applications involving mobile robots such as obstacle recognition, dynamic obstacle motion estimation, generating topological...
Smartphone camera resolution is increasing fast to meet the user expectation. With the increase in resolution the need of storage capacity as well as power consumption in processing the images is increasing. Though a user can set the resolution of an image before capture, most of the time the user does not change the pre-selected resolution for capturing multiple images. If the pre-selected resolution...
In this paper we propose a new method for detecting blurred images based on sharpness of edges in image using Haar wavelet transform. This is a direct method which uses edge information in image. This method is time efficient and works for a wide range of images. We also propose a fast blind method for de-blurring an image. Many de-blurring algorithms in literature do not focus on running time. This...
Graphics Processing Units (GPUs) are used today as affordable energy-efficient method of acceleration for computationally exhaustive algorithms to decrease execution time exploiting the power of parallel programing techniques. In the field of medical imaging, GPUs became crucial acceleration method for computationally exhaustive algorithms. This paper presented the effect of memory optimization on...
The localization of eye corner is of great importance since it offers crucial information in various face-related applications including face tracking, gaze estimation, and facial expression recognition. In this paper, a new approach is proposed which localizes eye corners in a precise and robust way. In our approach, we first estimate a rough location about an eye corner. Then, a set of texture images...
The cross-depiction problem is that of recognising visual objects regardless of whether they are photographed, painted, drawn, etc. It introduces great challenge as the variance across photo and art domains is much larger than either alone. We extensively evaluate classification, domain adaptation and detection benchmarks for leading techniques, demonstrating that none perform consistently well given...
Automatic approximations of brain volumes are very useful in various researches and clinical practises. The conventional hand tracing is time consuming and the level of accuracy depends on the individual. The present work aims at the automatic estimation of brain volume and 3-D visualization using VTK in a pythonic environment after the edge enhancement and unsharp masking by quadratic filters for...
In this paper, we propose a Non-Local Means algorithm-based denoising method. In conventional NLM, the weighting functions are acquired based on the similarity between target patch and its neighboring patches and then Gaussian-range kernel is calculated based on the similarity. Then, target patch is replaced by weighted means value of neighboring patches. In comparison, our method extracts similar...
Focal plane ambiguity in depth map creation from defocus blur has remained an challenging problem. In this paper, we present a method to resolve this issue with the help of Chromatic Aberration(CA). CA is a distortion referred to focal length variation of the lens with wavelength of light. When light, a mixture of various monochromatic components, passes through a lens, multiple focal planes are generated...
A modern virtualized data center is highly multifarious environment shared among hundreds of co-located tenants hosting heterogeneous applications. The tenants' virtual machines generate a subset of elephants or mice flows (different in terms of rate, size, duration, and burstiness) based on the type of application they are running. Virtual traffic generated from the tenant's virtual machines traverses...
Blind image deblurring is a severely ill-posed inverse problem. To obtain a high quality latent image from a single blurred one, effective regularizations are required. In this paper, we propose a nonlocal regularization to improve blur kernel estimation. Under convolution operation, even similar patches could result in the quite different values. However, if the estimated kernel is correct, the nonlocal...
Edit propagation is a class of algorithms that propagates user-specified color adjustments across an image or video. The user-specified adjustments take the form of sparse paint strokes that give examples of the desired alterations. Existing edit propagation (EP) algorithms are based on color similarity, and thus will alter all objects that have a similar color. In this work, we describe an EP algorithm...
A disparity map is usually obtained by stereo images using a stereo matching method. Edge boundaries in the disparity map separate two different objects. Therefore, edge preservation is one of important issues in the stereo matching method. A conventional distance transform was proposed to preserve edge boundaries in the disparity map. However, this method has a complexity problem because of its iterative...
Road lane detection is a key problem in advanced driver-assistance systems (ADAS). For solving this problem, vision-based detection methods are widely used and are generally focused on edge information. However, only using edge information leads to miss detection and error detection in various road conditions. In this paper, we propose a neighbor-based image conversion method, called extremal-region...
The principle of sub-pixel edge detection based on Zernike moments were introduced in this paper. With the consideration of the limitation of the sub-pixel edge detection algorithm by Ghosal, this paper combine original algorithm with Otsu threshold algorithm and an improved algorithm for edge detection is proposed. First of all, a mask of size seven by seven was calculated and Zernike moment was...
State of the art methods for disparity estimation achieve good results for single stereo frames, but temporal coherence in stereo videos is often neglected. In this paper we present a method to compute temporally coherent disparity maps. We define an energy over whole stereo sequences and optimize their Conditional Random Field (CRF) distributions using mean-field approximation. We introduce novel...
Nonlinear PDEs (partial differential equations) offer a convenient formal framework for image regularization and are at the origin of several efficient algorithms. In this paper, we present a new approach which is based (i) on a set of half Gaussian kernel filters, and (ii) a nonlinear anisotropic PDE diffusion. On one hand, half Gaussian kernels provide oriented filters whose flexibility enables...
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.