Electronic Letters on Computer Vision and Image Analysis (ELCVIA - Universitat Autònoma de Barcelona)
Not a member yet
343 research outputs found
Sort by
Special Issue on Partial Differential Equations in Computer Graphics and Vision
Get PDFDifferential equations is an essential tool for describing the nature of the physical universe and naturally also an essential part of models for computer graphics and vision
SnakeCut: An Integrated Approach Based on Active Contour and GrabCut for Automatic Foreground Object Segmentation
Get PDFInteractive techniques for extracting the foreground object from an image have been the interest of research in computer vision for a long time. This paper addresses the problem of an efficient, semi-interactive extraction of a foreground object from an image. Snake (also known as Active contour) and GrabCut are two popular techniques, extensively used for this task. Active contour is a deformable contour, which segments the object using boundary discontinuities by minimizing the energy function associated with the contour. GrabCut provides a convenient way to encode color features as segmentation cues to obtain foreground segmentation from local pixel similarities using modified iterated graph-cuts. This paper first presents a comparative study of these two segmentation techniques, and illustrates conditions under which either or both of them fail. We then propose a novel formulation for integrating these two complimentary techniques to obtain an automatic foreground object segmentation. We call our proposed integrated approach as ";SnakeCut";, which is based on a probabilistic framework. To validate our approach, we show results both on simulated and natural images
Optimal Geometric Matching for Patch-Based Object Detection
Get PDFWe present an efficient method to determine the optimal matching of two patch-based image object representations under rotation, scaling, and translation (RST). This use of patches is equivalent to a fullyconnected part-based model, for which the presented approach offers an efficient procedure to determine the best fit. While other approaches that use fully connected models have a high complexity in the number of parts used, we achieve linear complexity in that variable, because we only allow RST-matchings. The presented approach is used for object recognition in images: by matching images that contain certain objects to a test image, we can detect whether the test image contains an object of that class or not. We evaluate this approach on the Caltech data and obtain very competitive results
A PDE Method to Segment Image Linear Objects with Application to Lens Distortion Removal
Get PDFIn this paper, we propose a partial differential equation based method to segment image objects, which have a given parametric shape based on energy functional. The energy functional is composed of a term that detects object boundaries and a term that constrains the contour to find a shape compatible with the parametric shape. While the shape constraints guiding the PDE may be determined from object\\u27s shape statistical models, we demonstrate the proposed approach on the extraction of objects with explicit shape parameterization, such as linear image segments. Several experiments are reported on synthetic and real images to evaluate our approach. We also demonstrate the successful application of the proposed method to the problem of removing camera lens distortion, which can be significant in medium to wide-angle lenses
List of reviewers
Get PDFThe following is a list of reviewers who from January 2007 to December 2007, have contributed their time and talent to the success of the publication of the ELECTRONIC LETTERS ON COMPUTER VISION AND IMAGE ANALYSIS
Fast image processing with constraints by solving linear PDEs
Get PDFWe present a general framework that allows image filtering by minimization of a functional using a linear and positive definite partial differential equation (PDE) while also permitting to control the weight of each pixel individually. Linearity and positive definiteness allow to use fast algorithms to calculate the solution. Pixel weighting allows to enforce the preservation of edge information without the need for nonlinear diffusion by making use of information coming from an external source. The proof of existence and uniqueness of the solution is outlined and based on that a numerical scheme for finding the solution is introduced. Using this framework we developed two applications. The first is simple and fast denoising, which incorporates an edge detection algorithm. In this case the functional is designed to enhance the weight of the approximation term over the smoothing term at those places where an edge is detected. The second application is a background suppression algorithm that is robust against noise, shadows thrown by the object, and on the background and varying illumination. The results are qualitatively not quite as good as the ones obtained with nonlinear PDEs, but this disadvantage is compensated by the processing speed, which allows analysis of a 320x240 color frame in about 0.3s on a standard PC
Separating Rigid Motion for Continuous Shape Evolution
Get PDFA method is proposed for the construction of descent directions for the minimization of energy functionals defined for plane curves. The method is potentially useful in a number of image analysis problems, such as image registration and shape warping, where the standard gradient descent curve evolutions are not always feasible. The descent direction is constructed by taking a weighted average of the three components of the gradient corresponding to translation, rotation, and deformation. Our approach differs from previous work in the field by the use of implicit representation of curves and the notion of normal velocity of a curve evolution. Thus our theory is morphological and well suited for implementation in the level set framework
A novel approach to sparse histogram image lossless compression using JPEG2000
Get PDFIn this paper a novel approach to the compression of sparse histogram images is proposed. First, we define a sparsity index which gives hints on the relationship between the mathematical concept of matrix sparsity and the visual information of pixel distribution. We use this index to better understand the scope of our approach and its preferred field of applicability, and to evaluate the performance. We present two algorithms which modify one of the coding steps of the JPEG2000 standard for lossless image compression. A theoretical study of the gain referring to the standard is given. Experimental results on well standardized images of the literature confirm the expectations, especially for high sparse images
Noise reduction on mammographic phantom images
Get PDFA noise reduction scheme on digitized mammographic phantom images is presented. This algorithm is based on a direct contrast modification method with an optimal function, obtained by using the mean squared error as a criterion. Computer simulated images containing objects similar to those observed in the phantom are built to evaluate the performance of the algorithm. Noise reduction results obtained on both simulated and real phantom images show that the developed method may be considered as a good pre-processing step from the point of view of automating phantom film evaluation by means of image processing
Architectural Scene Reconstruction from Single or Multiple Uncalibrated Images
Get PDFIn this paper we present a system for the reconstruction of 3D models of architectural scenes from single or multiple uncalibrated images. The partial 3D model of a building is recovered from a single image using geometric constraints such as parallelism and orthogonality, which are likely to be found in most architectural scenes. The approximate corner positions of a building are selected interactively by a user and then further refined automatically using Hough transform. The relative depths of the corner points are calculated according to the perspective projection model. Partial 3D models recovered from different viewpoints are registered to a common coordinate system for integration. The 3D model registration process is carried out using modified ICP (iterative closest point) algorithm with the initial parameters provided by geometric constraints of the building. The integrated 3D model is then fitted with piecewise planar surfaces to generate a more geometrically consistent model. The acquired images are finally mapped onto the surface of the reconstructed 3D model to create a photo-realistic model. A working system which allows a user to interactively build a 3D model of an architectural scene from single or multiple images has been proposed and implemented