For both biological systems and machines, vision begins with a large and unwieldy array of measurements of the amount of light reflected from surfaces in the environment. The goal of vision is to recover physical properties of objects in the scene, such as the location of object boundaries and the structure, color and texture of object surfaces, from the two-dimensional image that is projected onto the eye or camera. This goal is not achieved in a single step; vision proceeds in stages, with each stage producing increasingly more useful descriptions of the image and then the scene. The first clue about the physical properties of the scene are provided by the changes of intensity in the image. The importance of intensity changes and edges in early visual processg has led to extensive research on their detection, description and .use, both in computer and biological vision systems. This article reviews some of the theory that underlies the detection of edges, and the methods used to carry out this analysis.

This article presents: (i) a multi-scale representation of grey-level shape called the scale-space primal sketch, which makes explicit both features in scale-space and the relations between structures at different scales, (ii) a methodology for extracting significant blob-like image structures from this representations, and (iii) applications to edge detection, histogram analysis, and junction classification demonstrating how the proposed method can be used for guiding later stage visual processes. The representation gives a qualitative description of image structure, which allows for detection of stable scales and associated regions of interest in a solely bottom-up data-driven way. In other words, it generates coarse segmentation cues, and can hence be seen as preceding further processing, which can then be properly tuned. It is argued that once such information is available, many other processing tasks can become much simpler. Experiments on real imagery demonstrate that the proposed theory gives intuitive results.

The extraction of curvilinear structures is an important low-level operation in computer vision that has many applications. Most existing operators use a simple model for the line that is to be extracted, i.e., they do not take into account the surroundings of a line. This leads to the undesired consequence that the line will be extracted in the wrong position whenever a line with different lateral contrast is extracted. In contrast, the algorithm proposed in this paper uses an explicit model for lines and their surroundings. By analyzing the scale-space behaviour of a model line profile, it is shown how the bias that is induced by asymmetrical lines can be removed. Furthermore, the algorithm not only returns the precise sub-pixel line position, but also the width of the line for each line point, also with sub-pixel accuracy.

: This paper describes a method for the enhancement of curvilinear structures such as vessels and bronchi in 3D medical images. A 3D line enhancement filter is developed with the aim of discriminating line structures from other structures and recovering line structures of various widths. The 3D line filter is based on a combination of the eigenvalues of the 3D Hessian matrix. Multi-scale integration is formulated by taking the maximum among single-scale filter responses, and its characteristics are examined to derive criteria for the selection of parameters in the formulation. The resultant multi-scale line-filtered images provide significantly improved segmentation and visualization of curvilinear structures. The usefulness of the method is demonstrated by the segmentation and visualization of brain vessels from MRI (magnetic resonance imaging) and MRA (magnetic resonance angiography), bronchi from a chest CT, and liver vessels (portal veins) from an abdominal CT. Keywords: 3D image ...

This paper continues ou,' work' on vlsuM representations of three-dimensional surfaces [Brady and Yuille 1984b]. The theoretical component o our work is a study of classes of surface curves as a source of constraint on the surface on which they lie, and as a basis for describing it. We analyze bounding contours, sin face intersections, lines of cunature, and asymptotes. Our experimental work hives.igates whether the information suggested by our theoretical study can be computed reliably mid efficiently. We demonstrate algorithms that compute lines of curvature of a (Gaussian smoothed) surface; determine planar patches and umbi!ic regions; extract axes of surfaces of revolution and tube surfaces. We report preliminary results on adapting the curvature primM sketch algorithms of Asada and Brady [1984] to detect and describe surface intersections. () Massachusetts Institute of Technology, 1984 This report describes research done at the Artificial Intelligeice Laboratory of the Massachusetts Institute of Technology. Support for the ]aboratory's Artificial Intelligence reseat.oh is provided in par. by the Adwmced Research Projects Agency of the Department of Defense under Office of Naval Research contract N00014-80-C-0505, the Office of Nax'al Research under contract number N000t4-77-C-0389, ,and the System Development Foundation. This wcrk was done while Haruo Asada was a visiting scientist at MIT on leave from Toshiba Corporation, Japan, and while Jean Ponce was a visking s.ientist on leave from I.'RIA, Paris, Fro,nee. ' Pr't of (t6:7)

In this paper a method to extract curvilinear structures from digital images is presented. The approach is based on differential geometric properties of the image function. For each pixel, the second order Taylor polynomial is computed by convolving the image with the derivatives of a Gaussian smoothing kernel. Line points are required to have a vanishing gradient and a high curvature in the direction perpendicular to the line. The use of the Taylor polynomial and the Gaussian kernels leads to a single response of the filter to each line. Furthermore, the line position can be determined with sub-pixel accuracy. Finally, the algorithm scales to lines of arbitrary width. An analysis about the scale-space behaviour of two typical line types (parabolic and bar-shaped) is given. From this analysis, requirements and useful values for the parameters of the filter can be derived. Additionally, an algorithm to link the individual line points into lines and junctions that preserves...

Localization based on visual landmarks requires feature extraction from views and map, matching of features between views and map, and viewpointhypothesis generation and veri #cation. In this paper, we describe lowerlevel image and map understanding procedures for extracting features and higher-level problem solving methods for establishing feature correspondences and making inferences about the viewpoint. Each of these processes, including the interaction of high-level and low-level subsystems, is demonstrated on real data. 1 Introduction. An essential aspect of map-based navigation is the determination of an agent's current location based on sensed data from the environment. Formally, this amounts to specifying the current viewpoint in some world model coordinate system. This localization process has two distinct components: one involving the establishmentof correspondences between aspects of the sensed data and the map or model and the other involving derivation of con...

We propose a unified approach to solve low, intermediate and high level computer vision problems for 3D object recognition from range images. All three levels of computation are cast in an optimization framework and can be implemented on neural network style architecture. In the low level computation, the tasks are to estimate curvature images from the input range data. Subsequent processing at the intermediate level is concerned with segmenting these curvature images into coherent curvature sign maps. In the high level, image features are matched against model features based on an object description called attributed relational graph (ARG). We show that the above computational tasks at each of the three different levels can all be formulated as optimizing a two-term energy function. The first term encodes unary constraints while the second term binary ones. These energy functions are minimized using parallel and distributed relaxation-based algorithms which are well suited for neural...

This paper describes how corner detection can be realised using a new feature representation that has recently been successfully exploited for edge and symmetry detection. The feature representation based on an magneto-static analogy. The idea is to compute a vector potential by appealing to an analogy in which the Canny edge-map is regarded as an elementary current density residing on the image plane. In our previous work we demonstrated that edges are the local maxima of the vector potential while points of symmetry correspond to the local minimum. In this paper we demonstrate that corners are located at the saddle points of the magnitude of the vector potential.

Recovering a hierarchical motion description of a long image sequence is one way to recognize objects and their motions. Intermediate-level and high-level motion analysis, i.e., recognizing a coordinated sequence of events such as walking and throwing, has been formulated previously as a process that follows high-level object recognition. This thesis develops an alternative approach to intermediate-level and high-level motion analysis. It does not depend on complex object descriptions and can therefore be computed prior to object recognition. Toward this end, a new computational framework for low and intermediate-level processing of long sequences of images is presented. Our new computational framework uses spatiotemporal (ST) surface flow and ST flow curves. As contours move, their projections into the image also move. Over time, these projections sweep out ST surfaces. Thus, these surfaces are direct representations of object motion. ST surface flow is defined as the natural extensio...