Results 1  10
of
12
Recursive photometric stereo when multiple shadows and highlights are present, in
 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
"... We present a recursive algorithm for 3D surface reconstruction based on Photometric Stereo in the presence of highlights, and self and cast shadows. We assume that the surface reflectance outside the highlights can be approximated by the Lambertian model. The algorithm works with as few as three lig ..."
Abstract

Cited by 11 (2 self)
 Add to MetaCart
(Show Context)
We present a recursive algorithm for 3D surface reconstruction based on Photometric Stereo in the presence of highlights, and self and cast shadows. We assume that the surface reflectance outside the highlights can be approximated by the Lambertian model. The algorithm works with as few as three light sources, and it can be generalised for N without any difficulties. Furthermore, this reconstruction method is able to identify areas where the majority of the lighting directions result in unreliable pixel intensities, providing the capability to adjust a reconstruction algorithm and improve its performance avoiding the unreliable sources. We report results for both artificial and real images and compare them with the results of other state of the art photometric stereo algorithms. 1.
Efficient Surface Reconstruction from Noisy Data using Regularized Membrane Potentials
"... A physicallymotivated method for surface reconstruction is proposed that can recover smooth surfaces from noisy and sparse data sets. No orientation information is required. By a new technique based on regularizedmembrane potentials the input sample points are aggregated, leading to improved noise ..."
Abstract

Cited by 10 (1 self)
 Add to MetaCart
A physicallymotivated method for surface reconstruction is proposed that can recover smooth surfaces from noisy and sparse data sets. No orientation information is required. By a new technique based on regularizedmembrane potentials the input sample points are aggregated, leading to improved noise tolerability and outlier removal, without sacrificing much with respect to detail (feature) recovery. After aggregating the sample points on a volumetric grid, a novel, iterative algorithm is used to classify grid points as exterior or interior to the surface. This algorithm relies on intrinsic properties of the smooth scalar field on the grid which emerges after the aggregation step. Second, a meshsmoothing paradigm based on a massspring system is introduced. By enhancing this system with a bendingenergy minimizing term we ensure that the final triangulated surface is smoother than piecewise linear. In terms of speed and flexibility, the method compares favorably with respect to previous approaches. Most parts of the method are implemented on modern graphics processing units (GPUs). Results in a wide variety of settings are presented, ranging from surface reconstruction on noisefree point clouds to greyscale image segmentation.
A graphspectral method for surface height recovery
 PATTERN RECOGNITION
, 2004
"... This paper describes a graphspectral method for 3D surface integration. The algorithm takes as its input a 2D field of surface normal estimates,delivered,for instance,by a shapefromshading or shapefromtexture procedure. We commence by using the surface normals to obtain an affinity weight matri ..."
Abstract

Cited by 9 (4 self)
 Add to MetaCart
(Show Context)
This paper describes a graphspectral method for 3D surface integration. The algorithm takes as its input a 2D field of surface normal estimates,delivered,for instance,by a shapefromshading or shapefromtexture procedure. We commence by using the surface normals to obtain an affinity weight matrix whose elements are related to the surface curvature. The weight matrix is used to compute a rownormalized transition probability matrix,and we pose the recovery of the integration path as that of finding the steadystate random walk for the Markov chain defined by this matrix. The steadystate random walk is given by the leading eigenvector of the original affinity weight matrix. By threading the surface normals together along the path specified by the magnitude order of the components of the leading eigenvector we perform surface integration. The height increments along the path are simply related to the traversed path length and the slope of the local tangent plane. The method is evaluated on needlemaps delivered by a shapefromshading algorithm applied to realworld data and also on synthetic data. The method is compared with the local geometric height reconstruction method of Bors,Hancock and Wilson, and the global methods of Horn and Brooks and Frankot and Chellappa.
Toward Spatial Reasoning about "Natural" Objects 13
 Computer Vision and Image Understanding
, 2006
"... This paper describes work aimed at developing a practical scheme for face analysis using shapefromshading. Existing methods have a tendency to recover surfaces in which convex features such as the nose are imploded. This is a result of the fact that subtle changes in the elements of the field of s ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
(Show Context)
This paper describes work aimed at developing a practical scheme for face analysis using shapefromshading. Existing methods have a tendency to recover surfaces in which convex features such as the nose are imploded. This is a result of the fact that subtle changes in the elements of the field of surface normals can cause significant changes in the corresponding integrated surface. To overcome this problem, in this paper we describe a localshape based method for imposing convexity constraints. We show how to modify the orientations in the surface gradient field using critical points on the surface and local shape indicators. The method is applied to both surface height recovery and face reillumination. Experiments show that altering the field of surface normals so as to impose convexity results in greatly improved height reconstructions and more realistic reilluminations. 2 1
Visionbased Online Process Control in Manufacturing Applications
, 2005
"... Applications such as layered manufacturing, or in general, solid freeform fabrication, pose a major challenge on online process control. For these parts to be functional, it is imperative that their mechanical and structural properties are strictly kept within respective tolerances. To that end, no ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
Applications such as layered manufacturing, or in general, solid freeform fabrication, pose a major challenge on online process control. For these parts to be functional, it is imperative that their mechanical and structural properties are strictly kept within respective tolerances. To that end, no internal or external defects, especially voids, can be tolerated. Since these parts are made layer by layer, it is then necessary to inspect top surface and boundary of each layer before the next layer is deposited. Two issues are of major concern here: (1) Inspection must be nondestructive, that is, layer surface and boundary must not be touched by the inspecting instruments, (2) the time window for inspection and any corrective measures should not exceed the maximum time limits necessary for two adjacent layers to properly bind together. Here, we present a closed loop online process control model where the process feedbacks are obtained from a 3D imaging system, and where the process dynamics model takes into account the correlation and dependency between adjacent layers. To ensure that the feedback is performed within the tolerable time windows, our 3D image processing parametric model takes advantage of physical characteristic of layer surface, and uses Gaussian function as a shape descriptor of image units. We obtain 2D profiles from representative signature(s), and then sweep along road path defined in the CAD model. The idea of reconstructing representative signature comprises some accuracy, but compared with classical shapefromshading method, the proposed approach is computationally more efficient. The 3D quality measures (such as volume or depth of voids) are then fed to process dynamics model, which computes the necessary compensation on the deposition flow rate for the next layer. We examine three process dynamics models to find out that a fuzzy model which takes into account correlation between adjacent layers and includes locally linear submodels for underfills and overfills is the most appropriate
ShapeFromShading Using the Heat Equation
 IEEE TRANSACTIONS ON IMAGE PROCESSING
"... This paper offers two new directions to shapefromshading, namely the use of the heat equation to smooth the field of surface normals and the recovery of surface height using a lowdimensional embedding. Turning our attention to the first of these contributions, we pose the problem of surface norma ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
(Show Context)
This paper offers two new directions to shapefromshading, namely the use of the heat equation to smooth the field of surface normals and the recovery of surface height using a lowdimensional embedding. Turning our attention to the first of these contributions, we pose the problem of surface normal recovery as that of solving the steady state heat equation subject to the hard constraint that Lambert’s law is satisfied. We perform our analysis on a plane perpendicular to the light source direction, where the component of the surface normal is equal to the normalized image brightness. The or azimuthal component of the surface normal is found by computing the gradient of a scalar field that evolves with time subject to the heat equation. We solve the heat equation for the scalar potential and, hence, recover the azimuthal component of the surface normal from the average image brightness, making use of a simple finite difference method. The second contribution is to pose the problem of recovering the surface height function as that of embedding the field of surface normals on a manifold so as to preserve the pattern of surface height differences and the lattice footprint of the surface normals. We experiment with the resulting method on a variety of realworld image data, where it produces qualitatively good reconstructed surfaces.
MultiModal Statistics of Local Image Structures . . .
, 2007
"... Processing in most artificial vision systems and in the human vision system starts with early vision which involves the extraction of local visual modalities (like optical flow, disparity and contrast transition etc.) and local image structures (edgelike, junctionlike and texturelike structures). ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
Processing in most artificial vision systems and in the human vision system starts with early vision which involves the extraction of local visual modalities (like optical flow, disparity and contrast transition etc.) and local image structures (edgelike, junctionlike and texturelike structures). Since information in early vision is processed only locally, it is inherently ambiguous. For example, estimation of optical flow faces the aperture problem, and thus, only the flow along the intensity gradient is computable for edgelike structures. Moreover, the extracted flow information at weaklytextured image areas are unreliable. Analogously, stereopsis needs to deal with the correspondence problem: as correspondences at weakly textured image areas cannot be found, the disparity information at such places is not accurate. One way to deal with the missing and ambiguous information is to make use of the redundancy of visual information by exploiting the statistical regularities of natural scenes. Such regularities are carried in the visual system using feedback mechanisms between different layers, or by lateral connections within a layer. This thesis is interested in the ambiguities and the biased and missing information in the processing of optic flow, stereo and junctions using statistical means. It uses statistical properties of images to analyze the extent of the ambiguous processing in optical flow estimation and whether the missing information in stereo can be recovered using interpolation of depth information at edgelike structures. Moreover, it proposes a feedback mechanism for dealing with the bias in junction detection, and another model for recovering the missing depth information in stereo computation using only the depth information at the edges.
Face Shape Recovery from a Single Image View
"... The problem of acquiring surface models of faces is an important one with potentially significant applications in biometrics, computer games and production graphics. For such task, the use of shapefromshading (SFS) is appealing since it is a noninvasive method that mimics the capabilities of the ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
The problem of acquiring surface models of faces is an important one with potentially significant applications in biometrics, computer games and production graphics. For such task, the use of shapefromshading (SFS) is appealing since it is a noninvasive method that mimics the capabilities of the human visual system. In this thesis, our interest lies on the recovery of facial shape from single image views. We make four novel contributions to this area. We commence by describing an algorithm for ensuring datacloseness and integrability in ShapefromShading. The combination of these constraints is aimed to overcome the problem of high dependency on the image irradiance. Next, we focus on developing a practical scheme for face analysis using SFS. We describe a localshape based method for imposing a novel convexity constraint. We show how to modify the orientations in the surface gradient field using critical points on the surface and local shape indicators. Then, we explore the use of statistical models that can be used in conjunction with SFS to reconstruct facial shape. We describe four different ways of constructing the 3D
Face Shape Recovery from a Single Image View
, 2006
"... The problem of acquiring surface models of faces is an important one with potentially significant applications in biometrics, computer games and production graphics. For such task, the use of shapefromshading (SFS) is appealing since it is a noninvasive method that mimics the capabilities of the ..."
Abstract
 Add to MetaCart
(Show Context)
The problem of acquiring surface models of faces is an important one with potentially significant applications in biometrics, computer games and production graphics. For such task, the use of shapefromshading (SFS) is appealing since it is a noninvasive method that mimics the capabilities of the human visual system. In this thesis, our interest lies on the recovery of facial shape from single image views. We make four novel contributions to this area. We commence by describing an algorithm for ensuring datacloseness and integrability in ShapefromShading. The combination of these constraints is aimed to overcome the problem of high dependency on the image irradiance. Next, we focus on developing a practical scheme for face analysis using SFS. We describe a localshape based method for imposing a novel convexity constraint. We show how to modify the orientations in the surface gradient field using critical points on the surface and local shape indicators. Then, we explore the use of statistical models that can be used in conjunction with
International Journal of Pattern Recognition and Artificial Intelligence c ○ World Scientific Publishing Company String Edit Distance, Random Walks and Graph Matching
"... This paper shows how the eigenstructure of the adjacency matrix can be used for the purposes of robust graphmatching. We commence from the observation that the leading eigenvector of a transition probability matrix is the steady state of the associated Markov chain. When the transition matrix is th ..."
Abstract
 Add to MetaCart
This paper shows how the eigenstructure of the adjacency matrix can be used for the purposes of robust graphmatching. We commence from the observation that the leading eigenvector of a transition probability matrix is the steady state of the associated Markov chain. When the transition matrix is the normalised adjacency matrix of a graph, then the leading eigenvector gives the sequence of nodes of the steady state random walk on the graph. We use this property to convert the nodes in a graph into a string where the nodeorder is given by the sequence of nodes visited in the random walk. We match graphs represented in this way, by finding the sequence of string edit operations which minimise edit distance. 1.