A new formulation of the image partitioning problem is presented: construct a complete and stable description of an image, in terms of a specified descriptive language, that is simplest in the sense of being shortest. We show that a descriptive language limited to a low-order polynomial description of the intensity variation within each region and a chain-code-like description of the region boundaries yields intuitively satisfying partitions for a wide class of images. The advantage of this formulation is that it can be extended to deal with subsequent steps of the image-understanding problem (or to deal with other image attributes, such as texture) in a natural way by augmenting the descriptive language. Experiments performed on a variety of both real and synthetic images demonstrate the superior performance of this approach over partitioning techniques based on clustering vectors of local image attributes and standard edge-detection techniques. 1 Introduction The partitioning proble...

A methodology for evaluating range image segmentation algorithms is proposed. This methodology involves (a) a common set of 40 laser range finder images and 40 structured light scanner images that have manually specified ground truth and (b) a set of defined performance metrics for instances of correctly segmented, missed and noise regions, over- and under-segmentation, and accuracy of the recovered geometry. A tool is used to objectively compare a machine generated segmentation against the specified ground truth. Four research groups have contributed to evaluate their own algorithm for segmenting a range image into planar patches.

Abstract. Estimation techniques in computer vision applications must estimate accurate model parameters despite small-scale noise in the data, occasional large-scale measurement errors (outliers), and measurements from multiple populations in the same data set. Increasingly, robust estimation techniques, some borrowed from the statistics literature and others described in the computer vision literature, have been used in solving these parameter estimation problems. Ideally, these techniques should effectively ignore the outliers and measurements from other populations, treating them as outliers, when estimating the parameters of a single population. Two frequently used techniques are least-median of

This paper presents a new model for estimating optical flow based on the motion of planar regions plus local deformations. The approach exploits brightness information to organize and constrain the interpretation of the motion by using segmented regions of piecewise smooth brightness to hypothesize planar regions in the scene. Parametric flow models are estimated in these regions in a two step process which first computes a coarse fit and estimates the appropriate parameterization of the motion of the region (two, six, or eight parameters). The initial fit is refined using a generalization of the standard area-based regression approaches. Since the assumption of planarity is likely to be violated, we allow local deformations from the planar assumption in the same spirit as physically-based approaches which model shape using coarse parametric models plus local deformations. This parametric+deformation model exploits the strong constraints of parametric approaches while retaining the ada...

Abstract—A hybrid multidimensional image segmentation algorithm is proposed, which combines edge and region-based techniques through the morphological algorithm of watersheds. An edge-preserving statistical noise reduction approach is used as a preprocessing stage in order to compute an accurate estimate of the image gradient. Then, an initial partitioning of the image into primitive regions is produced by applying the watershed transform on the image gradient magnitude. This initial segmentation is the input to a computationally efficient hierarchical (bottomup) region merging process that produces the final segmentation. The latter process uses the region adjacency graph (RAG) representation of the image regions. At each step, the most similar pair of regions is determined (minimum cost RAG edge), the regions are merged and the RAG is updated. Traditionally, the above is implemented by storing all RAG edges in a priority queue. We propose a significantly faster algorithm, which additionally maintains the so-called nearest neighbor graph, due to which the priority queue size and processing time are drastically reduced. The final segmentation provides, due to the RAG, one-pixel wide, closed, and accurately localized contours/surfaces. Experimental results obtained with two-dimensional/three-dimensional (2-D/3-D) magnetic resonance images are presented. Index Terms — Image segmentation, nearest neighbor region merging, noise reduction, watershed transform. I.

Aprocedure for reconstructing solid models of conventional engineering objects from a multiple-view, 3D point cloud is described. (Conventional means bounded by simple analytical surfaces, swept surfaces and blends.) Emphasis is put on producing accurate and topologically consistent boundary representation models, ready to be used in computer aided design and manufacture. The basic phases of our approach to reverse engineering are summarised, and related computational difficulties are analysed. Four key algorithmic components are presented in more detail: efficiently segmenting point data into regions; creating translational and rotational surfaces with smooth, constrained profiles; creating the topology of B-rep models; and finally adding blends. The application of these algorithms in an integrated system is illustrated by means of various examples, including a well-known reverse engineering benchmark. 1.

This paper focuses on the experimental evaluation of a range image segmentation system which partitions range data into homogeneous surface patches using estimates of the sign of the mean and Gaussian curvatures. We report the results of an extensive testing programme aimed at investigating the behavior of important experimental parameters such as the probability of correct classification and the accuracy of curvature estimates, measured over variations of significant segmentation variables. Evaluation methods in computer vision are often unstructured and subjective: this paper contributes a useful example of extensive experimental assessment of surface-based range segmentation. 1 Introduction "In all the attempts made to date to show that 2 + 2 = 4, no one has ever considered the windspeed." R. Queneau, Quelques remarques sommaires relatives aux propri'et'es a'erodynam ' iques de l'addition. In this paper we present an example of experimental performance assessment for a range surfac...

We study the 3D shape similarity between closed surfaces. We represent a curved or polyhedral 3D object of genus zero using a mesh representation that has nearly uniform distribution with known connectivity among mesh nodes. We define a shape similarity metric based on the L 2 distance between the local curvature distributions over the mesh representations of the two objects. For both convex and concave objects, the shape metric can be computed in time O(n 2 ), where n is the number of tessellation of sphere or the number of meshes which approximate the surface. Experiments show that our method produces good shape similarity measurements. Table of Content 1 Introduction 1 2 Representation of a Closed Surface 6 2.1 Discrete Representation of a Curve ..................................................................................... 6 2.2 Spherical Representation of a 3D Surface........................................................................... 6 2.3 3D Local Curvature:...

Accurate segmentation of images is one of the most important objectives in image analysis. The two conventional methods of image segmentation, region based segmentation and boundary finding, often suffer from a variety of limitations. Many methods have been proposed to overcome the limitations but the solutions tend to be problem specific. Here we present a new region growing method with the capability of finding the boundary of a relatively bright/dark region in a textured background. The method relies on a measure of contrast of the region which represents the variation of the region gray level as a function of its evolving boundary during the growing process. It helps to identify the best external boundary of the region. The application of a reverse test using a gradient measure then yields the highest gradient boundary for the region being grown. A number of experiments have been performed both on synthetic and real images to evaluate the new approach. The proposed scheme can be ca...

Automatic extraction of CAD descriptions which are ultimately intended for human manipulation requires the accurate inference of geometric and topological information. We present a system which applies segmentation techniques from computer vision to automatically extract CAD models from range images of parts with curved surfaces. The output of the system is a B-rep of the object which is suitable for further manipulation in a modelling system. The segmentation process is an improvement upon Besl and Jain's variable-order surface fitting 1 , extracting general quadric surfaces and planes from the data, with a postprocessing stage to identify surface intersections and to extract a B-rep from the segmented image. We present results on a variety of machined objects, which illustrate the high-level nature of the acquired models, and discuss the numerical accuracy (feature sizes and separations) and the correctness of structural inferences of the system. Keywords: Feature-based reverse eng...