Showing papers on "Distance transform published in 1990"

Generating skeletons and centerlines from the medial axis transform

Abstract: An algorithm for generating connected skeletons of objects in binary images is described. Three main properties of the algorithm are that: (1) it is noniterative, taking a fixed number of passes through the image to produce the skeleton regardless of the width of the objects; (2) it is based on a distance transform that uses a good approximation to the Euclidean distance, giving skeletons that are well centered and robust with respect to rotation; and (3) the skeletons it produces are connected. In addition, the skeletons are thin and allow the objects to be nearly reconstructed. The algorithm can also be run in a mode to produce centerlines, a connected approximation to the skeleton that is less sensitive to border noise and that is useful in image analysis applications. >

The Measurement of Wood Cell Parameters Using the Distance Transform

Abstract: In this paper we present a new approach to the quantitative assessment of cell wood boundaries, using image processing techniques based upon the distance transform. It is demonstrated that the method produces the parameters of wall thickness and boundary perimeter using objective measures to estimate these parameters. Further, it is possible, using this technique, to segment the image of a sample of Eucalyptus regnans (mountain ash) into rays, lumens, and cell walls with minimum human intervention.

Dynamic digital distance maps in two dimensions

Abstract: An efficient means for dealing with obstacles in motion is provided to extend the usefulness of digital distance maps. An algorithm is presented that allows one to compute what portions of a map will probably be affected by an obstacle's motion. The algorithm is based on an analysis of the distance transform as a problem in wave propagation. The regions that must be checked for possible updates when an obstacle moves are those that are in its or in the shadow of obstacles that are partially in the shadow of the moving obstacle. The technique can handle multiple fixed goals, multiple obstacles moving and interacting in an arbitrary fashion, and it is independent of the technique used for calculation of the distance map. The algorithm is demonstrated on a number of synthetic two-dimensional examples, and example timing results are reported. >

Triangulation type distance sensor for moving objects with window forming means

Abstract: A distance sensor is disclosed composed of a pair of objective lenses 1 and 2 separated by a base length L, and a pair of two-dimensional image sensors 3 and 4. A left and a right image of a moving object 5, shifted from each other by a horizontal distance corresponding to a distance R to the object 5, is formed on the sensors 3 and 4. The left or the right image formed on the sensor is displayed on the display 11. A human operator initially sets, via the window forming device 12, the dimension and position of a window within the screen of the display. Thereafter, the microcomputer 10A samples at a predetermined sampling period the pixel signals of the image sensors 3 and 4, adjusts the dimension and the position of the window such that the window just covers the image of the object, and determines the amount of shift of the left and the right images on the basis of the image within the window.

A new distance measure for binary images

Abstract: A distance measure, called the generalized Euclidean distance, is developed for binary images to take into account perceptual distortions. Based on this distance measure, a type of transformation is devised to ensure that the generalized Euclidean distance of two images is the same as the Euclidean distance of two transformed images. A set of transformed images is then used to train and test a feed-forward neural network for handwritten numeral recognition. It is shown that the recognition rate is significantly improved by incorporating human perception into the neural network, and that the transformation step can be merged into the trained neural network so that no transformation is required during the recognition stage. >

Local path planning: a brute force approach

Abstract: The issues involved in providing a generic and domain-independent local planning module for the mobile robot called TURNIP (Turing's navigation and image processing system) are discussed, focusing on the role of local planning as a prerequisite to modularity and autonomy. The problem of obstacle avoidance as a low-level, nonintellectual task that should operate in complex, noisy, dynamic, and 3-D domains is considered. Two algorithms are presented, each generating qualitatively different solutions. The first generates the shortest path between two locations; the second generates the clearest path between two locations. Both are based on the distance transform. >

Distance driven skeletonization

Abstract: A sequential algorithm to generate the labeled skeleton of a single-valued digital figure is presented. The algorithm can be seen as an improvement of the authors' previous algorithm (1989), based on the use of the city-block distance transform. The skeleton is obtained within one sequential raster scan of the array where the distance transform is stored, and is a one-pixel-wide 8-connected subset of the figure. The problems faced to obtain the skeleton are discussed, and the criteria adopted to overcome them are illustrated. >

Antiskeleton: some theoretical properties and application

Abstract: Noting that the skeleton is defined by means of the distance function to the nearest point, an analog notion named anti-skeleton is derived when substituting to that distance the distance to the farthest point. A complete parallel is constructed, concerning the mathematical definitions and properties of the skeleton and the anti-skeleton. An example of its use in image analysis is then presented.