Filtering, segmentation and depth
This volume reports new developments in computer vision research. The authors manage to make some progress at several levels of visual reconstruction by working in a restricted world of single, stationary pictures of interposed objects with uniform non-textured surfaces where shadows are not present. In the attempt to develop a computer algorithm that finds ``the 2.1D sketch of an image (i.e., performing image segmentation along with computing the relative depth of objects in an image), the authors suggest a practical way of incorporating occlusion information into the task of finding object outlines. Accordingly, the model proposed in this book determines the nearness relations of the objects from overlap analysis. The book is organized in sections that describe the algorithm stages. Chapter 2 is concerned with a new edge-enhancing filter, in fact a nonlinear filter that localizes edges while preserving corners and \(T\)- junctions, the crucial cues to occlusion. Chapter 3 covers the contour- detection problem by providing a fast curve smoothing algorithm. Chapter 4 is devoted to the computation of continuations of disrupted edges. Chapter 5 treats the final stage that seeks to find the optimal segmentation and the depth relations between regions. Results are analyzed for a number of images that yield correct results and others that yield wrong interpretations. Finally, Chapter 6 reviews the strengths and limitations of the algorithm and discusses areas of potential improvement. The text is supplemented by appendices giving the filter algorithm and the contour tracing algorithm in pseudo-\(C\) code. The program code takes up more than one third of the book (51 pages). The reviewer was rather disappointed to find out several errors (e.g., an infinite FOR loop on page 104 where a BREAK condition is missing, the function TraceContour is defined on page 104 as having 4 arguments and called on page 100 with only 3, the functions GrowContours and DeleteStray are called with real arguments although they are defined with integer ones). It is worth mentioning that, by making the actual programs used in this book available via internet, the authors serve the computer vision community in the efforts to have serious long-term progress. The possibility of sharing computer code is essential for the researchers who, in this way, are enabled to achieve future results in short time by combining the best parts of the previous ones.
- Maximal meaningful events and applications to image analysis
- Image segmentation with depth information via simplified variational level set formulation
- Regularized non-local total variation and application in image restoration
- Bendlets: a second-order shearlet transform with bent elements
- Characterization and representation of the lower semicontinuous envelope of the elastica functional
- Functionals depending on curvatures with constraints
- A linear framework for region-based image segmentation and inpainting involving curvature penalization
- Image reconstruction by minimizing curvatures on image surface
- Approximating the total variation with finite differences or finite elements
- Convex relaxation of a class of vertex penalizing functionals
- A cortical-inspired geometry for contour perception and motion integration
- A novel Euler's elastica-based segmentation approach for noisy images using the progressive hedging algorithm
- An anisotropic PDE model for image inpainting
- Image segmentation using the Cahn-Hilliard equation
- A linear fourth-order PDE-based gray-scale image inpainting model
- Geodesic path based digital inpainting
- A variational model for capturing illusory contours using curvature
- A finite element method for surface restoration with smooth boundary conditions
- Beamlets are densely embedded in \(H^{-1}\)
- A numerical study of a mean curvature denoising model using a novel augmented Lagrangian method
- Total roto-translational variation
- A gauge field model of modal completion
- Coefficient identification in PDEs applied to image inpainting
- Sub-Riemannian mean curvature flow for image processing
- A nested variational time discretization for parametric anisotropic Willmore flow
- A fast relaxed normal two split method and an effective weighted TV approach for Euler's elastica image inpainting
- Alternating direction method of multiplier for Euler's elastica-based denoising
- Convex lifting-type methods for curvature regularization
- The $\Gamma $-limit and the related gradient flow for singular perturbation functionals of Perona-Malik type
- A variational model in image processing with focal points
- Recovering relative depth from low-level features without explicit T-junction detection and interpretation
- Image segmentation using Euler's elastica as the regularization
- Variational image inpainting
- Fast numerical schemes related to curvature minimization: a brief and elementary review
- Fast algorithm for color texture image inpainting using the non-local CTV model
- Classification of edges using compactly supported shearlets
- Augmented Lagrangian method for an Euler's elastica based segmentation model that promotes convex contours
- Cahn-Hilliard inpainting with the double obstacle potential
- Variational image regularization with Euler's elastica using a discrete gradient scheme
- An efficient segmentation method based on dynamic graph merging
- Approximation by Γ-convergence of a curvature-depending functional in visual reconstruction
- A Color Elastica Model for Vector-Valued Image Regularization
- Sparse inpainting with smoothed particle hydrodynamics
- Shared Prior Learning of Energy-Based Models for Image Reconstruction
- Convex Splitting Method for Strongly Anisotropic Solid-State Dewetting Problems in Two Dimensions
- On a Cahn–Hilliard–Oono model for image segmentation
- A New Operator Splitting Method for the Euler Elastica Model for Image Smoothing
- Topology- and perception-aware image vectorization
- Elastic bending total variation model for image inpainting with operator splitting method
- A heterogeneous model of boundary and figure completion in V₁
- Vertex characterization via second-order topological derivatives
- Image vectorization with depth: convexified shape layers with depth ordering
- Neural networks for the approximation of Euler's elastica
- Network inpainting via optimal transport
- Advanced curvature estimation with ADMM in image processing
- An accelerated operator splitting algorithm for solving Euler's elastica-based image inpainting and segmentation models
- A total scaled-gradient variation model with box-constraint for image reconstruction problems
- Classification of equilibria and \(\Gamma \)-convergence for the discrete Perona-Malik functional
- Total variation wavelet inpainting
- Convergence of discrete schemes for the Perona-Malik equation
This page was built for publication: Filtering, segmentation and depth
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q684557)
