Showing papers on "Distance transform published in 1994"

Representing moving images with layers

Abstract: We describe a system for representing moving images with sets of overlapping layers. Each layer contains an intensity map that defines the additive values of each pixel, along with an alpha map that serves as a mask indicating the transparency. The layers are ordered in depth and they occlude each other in accord with the rules of compositing. Velocity maps define how the layers are to be warped over time. The layered representation is more flexible than standard image transforms and can capture many important properties of natural image sequences. We describe some methods for decomposing image sequences into layers using motion analysis, and we discuss how the representation may be used for image coding and other applications. >

Matching 3-D anatomical surfaces with non-rigid deformations using octree-splines

Abstract: Presents a new method for determining the minimal nonrigid deformation between two 3D surfaces, such as those which describe anatomical structures in 3D medical images. Although the authors match surfaces, they represent the deformation as a volumetric transformation. Their method performs a least squares minimization of the distance between the two surfaces of interest. To quickly and accurately compute distances between points on the two surfaces, the authors use a precomputed distance map represented using an octree spline whose resolution increases near the surface. To quickly and robustly compute the deformation, the authors use a second octree-spline to model the deformation function. The coarsest level of the deformation encodes the global (e.g., affine) transformation between the two surfaces, while finer levels encode smooth local displacements which bring the two surfaces into closer registration. The authors present experimental results on both synthetic and real 3D surfaces. >

Automatic three‐dimensional correlation of CT‐CT, CT‐MRI, and CT‐SPECT using chamfer matching

Abstract: Image correlation is often required to utilize the complementary information in CT, MRI, and SPECT. A practical method for automatic image correlation in three-dimensions (3D) based on chamfer matching is described. The method starts with automatic extraction of contour points in one modality and automatic segmentation of the corresponding feature in the other modality. A distance transform is applied to the segmented volume and a cost function is defined that operates between the contour points and the distance transform. Matching is performed by iteratively optimizing the cost function for 3D translation, rotation, and scaling of the contour points. The complete matching process including segmentation requires no user interaction and takes about 100 s on an HP715/50 workstation. Perturbation tests on clinical data with cost functions based on mean, rms, and maximum distances in combination with two general purpose optimization procedures have been performed. The performance of the methods has been quantified in terms of accuracy, capture range, and reliability. The best results on clinical data are obtained with the cost function based on the mean distance and the simplex optimization method. The accuracy is 0.3 mm for CT-CT, 1.0 mm for CT-MRI, and 0.7 mm for CT-SPECT correlation of the head. The accuracy is usually at subpixel level but is limited by global geometric distortions, e.g., for CT-MRI correlation. Both for CT-CT and CT-MRI correlation the capture range is about 6 cm, which is higher than normal differences in patient setup found on the scanners (less than 4 cm). This means that the correlation procedure seldom fails (better than 98% reliability) and user interaction is unnecessary. For CT-SPECT matching the capture range is about 3 cm (80% reliability), and must be further improved. The method has already been introduced in clinical practice.

Proximity clouds—an acceleration technique for 3D grid traversal

Abstract: In this paper we present a new method for the acceleration of ray traversal through a regular 3D grid. A distance transformation is precomputed and mapped onto the empty grid space. A ray traversing the empty space is assisted by the distance values which permit it to perform long skips along the ray direction. We show that the City-Block metric simplifies the preprocessing with no penalty at the traversal phase. Different schemes are discussed and the trade-off between the preprocessing time and the speed-up is analyzed.

Fast Nonsupervised 3D Registration of PET and MR Images of the Brain

Abstract: We propose a fully nonsupervised methodology dedicated to the fast registration of positron emission tomography (PET) and magnetic resonance images of the brain. First, discrete representations of the surfaces of interest (head or brain surface) are automatically extracted from both images. Then, a shape-independent surface-matching algorithm gives a rigid body transformation, which allows the transfer of information between both modalities. A three-dimensional (3D) extension of the chamfer-matching principle makes up the core of this surface-matching algorithm. The optimal transformation is inferred from the minimization of a quadratic generalized distance between discrete surfaces, taking into account between-modality differences in the localization of the segmented surfaces. The minimization process is efficiently performed via the precomputation of a 3D distance map. Validation studies using a dedicated brain-shaped phantom have shown that the maximum registration error was of the order of the PET pix...

A Euclidean distance transform using grayscale morphology decomposition

Abstract: A fast and exact Euclidean distance transformation using decomposed grayscale morphological operators is presented. Applied on a binary image, a distance transformation assigns each object pixel a value that corresponds to the shortest distance between the object pixel and the background pixels. It is shown that the large structuring element required for the Euclidean distance transformation can be easily decomposed into 3/spl times/3 windows. This is possible because the square of the Euclidean distance matrix changes uniformly both in the vertical and horizontal directions. A simple extension for a 3D Euclidean distance transformation is discussed. A fast distance transform for serial computers is also presented. Acting like thinning algorithms, the version for serial computers focuses operations only on the potential changing pixels and propagates from the boundary of objects, significantly reducing execution time. Nonsquare pixels can also be used in this algorithm. An example application, shape filtering using arbitrary sized circular dilation and erosion, is discussed. Rotation-invariant basic morphological operations can be done using this example application. >

Efficient Computation of the Minimum Hausdorff Distance for Visual Recognition

Abstract: We have developed a method, using the minimum Hausdorff distance, for visually locating an object in an image. This method is very reliable, and fast enough for real-world applications. A visual recognition system takes an image and a model of an object which may occur in that image; these images and models are composed of features (points, line segments, etc.). The system locates instances of the model in the image by determining transformations of the model which bring a large number of model features close to image features. One of the unique strengths of the Hausdorff distance is the reverse distance which reduces the frequency of erroneous matching between a model and a cluttered portion of the image. The Hausdorff distance is a measure defined between two point sets representing a model and an image. Its properties make it attractive for model-based recognition; one of these properties is that the Hausdorff distance is a metric. The minimum Hausdorff distance is used to find a transformation of the model which brings it into closest correspondence with the image. This can be done by searching over a space of allowable transformations. In some cases, the minimum Hausdorff distance is also a metric. The Hausdorff distance can be modified so that it is reliable even when the image contains multiple objects, noise, spurious features, and occlusions. We construct lower bounds which show that finding the exact transformation that minimises the Hausdorff distance may be quite expensive. We develop a rasterised approach to the search and a number of techniques which allow this search to be performed efficiently. The principal search technique used is transformation space subdivision. The space of transformations is searched in a tree-like fashion: a large region is examined as a unit, and if the results of this examination are good, it is subdivided and each of the subregions examined in turn; if the results are not good, then the region is discarded. We discuss some implementations of this approach, together with their applications to practical problems such as motion tracking and mobile robot navigation.

Nonlinear global and local document degradation models

Abstract: Two sources of document degradation are modeled: (1) perspective distortion that occurs while photocopying or scanning thick, bound documents; and (2) degradation due to perturbation in the optical scanning and digitization process: speckle, blurr, jitter, and threshold. Perspective distortion is modeled by studying the underlying perspective geometry of the optical system of photocopiers and scanners. An illumination model is described to account for the nonlinear intensity change occurring across a page in a perspective-distorted document. The optical distortion process is modeled morphologically. First, a distance transform on the foreground is performed; this is followed by a random inversion of binary pixels in which the probability of flip is a function of the distance of the pixel to the boundary of the foreground. Correlating the flipped pixels is modeled by a morphological closing operation.©1994 John Wiley & Sons Inc

Height distributional distance transform methods for height field ray tracing

Abstract: Height distributional distance transform (HDDT) methods are introduced as a new class of methods for height field ray tracing. HDDT methods utilize results of height field preprocessing. The preprocessing involves computing a height field transform representing an array of cone-like volumes of empty space above the height field surface that are as wide as possible. There is one cone-like volume balanced on its apex centered above each height field cell. Various height field transforms of this type are developed. Each is based on distance transforms of height field horizontal cross-sections. HDDT methods trace rays through empty cone-like volumes instead of through successive height field cells. The performance of HDDT methods is evaluated experimentally against existing height field ray tracing methods.

Intermodality 3D medical image registration with global search

Abstract: Describes a new registration method for three-dimensional medical images. It is important clinically to bring images from different modalities into alignment so that equivalent points can be identified. Often, functional images (showing metabolism or blood flow) are registered to structural images in order to more accurately interpret and quantify these images. This is especially important in areas of decreased function. This registration method determines the optimal transformation between the images using a match metric based on the distance transform of a structure visible in both modalities. The globally optimal transform is determined using a genetic optimization method and a hybrid technique using both genetic and gradient optimization. This provides a feasible way of determining the global solution making this method robust to local minima and insensitive to initial positioning. >

Object keying in video images based on distance from camera

Abstract: A method for separating a first image into two or more portions, such as foreground and background portions, based on the distance of the portions from a camera. The method includes detecting a main image using the camera, such as a CCD video camera and measuring distances from the camera to points in the first image. The method further includes separating the main image into two or more portions, such as background and foreground, based on the measured distance of these portions of the image from the camera. One or more of the separated images can then be combined with a secondary image to produce a composite image. To further refine the separation of the two portions of the main image, the contrast is determined between the two portions of the main image in regions of the main image having sufficiently large distance variations. The combining of the two images is then based on the determined contrast in addition to the distances.

Fast computation of the grassfire transform using SKIPSM

Abstract: The principles of SKIPSM (Separated-Kernel Image Processing using Finite State Machines), a powerful new way to implement many standard image processing operations, are presented here and in a group of companion papers. This paper describes the application of SKIPSM to the computation of the Grassfire Transform (GT), the mapping of a binary image into a grey-level image in such a way that the output grey level of each interior pixel of each individual blob is proportional to the distance of that pixel from the blob boundary. Distance can be defined in terms of various norms: Euclidean distance, elliptical distance, 'boxcar' distance, etc. While potentially very useful, the GT has seen limited application because of the many computational steps required to calculate it. In comparison with conventional hardware-based and software-based approaches, SKIPSM allows implementation of the GT at higher speeds and/or lower hardware cost. The key developments upon which this improved performance is based are (1) the separation of 2D the binary erosions on which the GT is based into row operations followed by column operations, (2) the formulation of these row and column operations in a form compatible with pipelined operation, (3) the implementation of the resulting operations as simple finite-state machines, (4) the automated generation of the finite-state machine configuration data for structuring elements (SEs), and (5) the simultaneous application of all these nested SEs in a single pipeline pass. Some key features of SKIPSM, as applied to the GT, are listed below: (1) Because the SEs can be large and arbitrary, any distance measure can be used. There is no penalty involved in using true circles or ellipses, rather that the octagons or squares resulting from sequential application of 3 X 3 SEs. (2) The simultaneous application of six circular erosion stages (SEs of size 3 X 3, 5 X 5, ..., 13 X 13) has already been demonstrated. Eight or more simultaneous circular erosion stages may be possible (sizes 3 X 3, 5 X 5, ..., 17 X 17, ...). (3) The user specifies the SE or SEs. All other steps are automated. These results are can be achieved using conventional pipelined hardware in this new way. Alternatively, inexpensive off-the-shelf 'chips' can be configured to carry out the same operations as conventional image processing hardware. Corresponding 'speedups' are achieved in software-based implementations.2347© (1994) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Graphic symbol recognition using a signature technique

Abstract: The authors present a noise-robust and general-purpose method for the recognition of graphic symbols in line-drawing images. The method assumes that a noise-free symbol database is available, and that both the model symbols and the processed image have been broken down into elementary structures. Recognition is based on the hypothesis-and-test paradigm. The detection of an elementary structure allows us to use a signature filter, to hypothesize and then recursively reduce a set of matching symbols. Hypothesized symbols are then verified by exploiting distance transform and distance measurement.

Method for determining the orientation in which an object was placed when the image of the object was recorded

Abstract: An image signal, which represents an image capable of taking either a symmetric orientation or an asymmetric orientation with respect to a center line of the image serving as the axis of symmetry, is obtained. The image signal is made up of a series of image signal components representing picture elements in the image. A predetermined operation is then carried out to find the difference between values of image signal components representing at least a single pair of picture elements, which correspond symmetrically to each other with respect to the center line of the image, and to calculate a characteristic value, which represents symmetry or asymmetry of the image, from the value of the difference. A judgment is then made from the level of the characteristic value as to whether the image is a symmetric image or is an asymmetric image.

On-road object recognizing device for vehicle

Abstract: PURPOSE: To enable an on-road object recognizing device for vehicle to accurately recognize an object on a road ahead of its own vehicle by comparing the reference distance corresponding to a range which is decided at every line range and distance to an object detected by means of a distance measuring means. CONSTITUTION: Picture information from a stereo camera 2 is fetched to the forward distance measurement controller 3 of an object recognizing means 5. A distance measuring means 7 which measures the distance between the object, the picture of which is taken with the camera 2, and its own vehicle is connected to the controller 3. In addition, a range-corresponding object data eliminating means 8 compares range cutting distances (range-corresponding reference distances) which are decided at every window line (range) of the picture information and the distance to the object detected by the measuring means 7 and, when the distance to the object is longer than the reference distance, eliminates the object from object data. When the distance to the object is longer than the reference distance, the measuring means 7 recognizes the object as an object to be recognized. COPYRIGHT: (C)1995,JPO

Method and apparatus for accurately rendering half-bitted image pixels

Abstract: A method and apparatus for identifying regions within a first binary image where half-bitting may be present, converting those regions to a multiple-bit/pixel representation so as to accurately represent the image density and the intended edge structure for the region, and further generating an enhanced resolution representation of the region in either a second binary image, wherein the second binary image has a spatial resolution greater than the first image, or a multiple-bit per pixel (gray) image at the same resolution as the input image so as to enable an improved rendering of the first binary image.

Matching 3-D Anatomical Surfaces with Non-Rigid Volumetric Deformations

Abstract: This paper presents a new method for determining the minimal non-rigid deformation between two 3-D surfaces, such as those which describe anatomical structures in 3-D medical images. Although we match surfaces, we represent the deformation as a volumetric transformation. Our method performs a least squares minimization of the distance between the two surfaces of interest. To quickly and accurately compute dislances between points on the two surfaces, we use a precomputed distance map represented using an octree spline whose resolution increases near the surface. To quickly and robustly compute the deformation, we use a volumetric spline to model the deformation function. We present experimental results on both synthetic and real 3-D surfaces.

Approaches to registration using 3D surfaces

Abstract: This paper describes current iterative surface matching methods for registration, and our new extensions. Surface matching methods use two segmented surfaces as features (one dynamic and one static) and iteratively search parameter space for an optimal correlation. To compare the surfaces we use an anisotropic Euclidean chamfer distance transform, based on the static surface. This type of DT was analyzed to quantify the errors associated with it. Hierarchical levels are attained by sampling the dynamic surface at various rates. In using the reduced amount of data provided by the surface segmentation each hierarchical level is formed quickly and easily and only a single distance transform is needed, thus increasing efficiency. Our registrations were performed in a data-flow environment created for multipurpose image processing. The new modifications were tested on a large number of simulations, over a wide range of rigid body transformations and distortions. Multimodality, and multipatient registration tests were also completed. A thorough examination of these modifications in conjunction with various minimization methods was then performed. Our new approaches provide accuracy and robustness, while requiring less time and effort than conventional methods.© (1994) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Image transformation apparatus

Abstract: In an image transformation apparatus, the image formed by an input video signal is stored into a memory, and the input video signal is read based on a read-address data of a predetermined read-address generating means, to execute a predetermined image transformation with respect to an image. The transformed image is formed by using a function in which a distance from the center of the transformed image is changeable corresponding to an angle from the center of that, so as to obtain the lens effect transforming the image into images having various curvilinearly shapes.

Using multi-layer distance maps for motion planning on surfaces with moving obstacles

Abstract: This paper presents a new algorithm for planning the time-optimal motion of a robot traveling with limited velocity from a given location to a given destination on a surface in the presence of moving obstacles. Additional constraints such as space variant terrain traversability and fuel economy can be accommodated. A multilayer distance map is defined and applied in computing optimal trajectories. The multilayer distance map incorporates constraints imposed by the moving obstacles, surface topography and terrain traversability. It is generated by an efficient numerical curve propagation technique.

Method of measuring three-dimensional shape and device therefor

Abstract: PURPOSE:To precisely obtain a three-dimensional shape of an object. CONSTITUTION:Two image pick-up parts 30, 40 having zoom lenses 10, 20 pick up images from which a stereoscopic image is obtained, and a distance measuring part 80 obtains distant data ZS of an object to be picked up from the stereoscopic image with the use of a stereoscopic distance measuring process. Meanwhile, distance measuring parts 70, 90 obtain distance data ZR, ZL with the use of a zoom distance measuring process. A distance data synthesizing part 100 obtain weighted averages of the data ZS, ZR, ZL in accordance with reliabilities of the latter. Thereby it is possible to obtain a final distance to the object.

New descriptor for skeletons of planar shapes: the calypter

Abstract: The mathematical definition of the skeleton as the locus of centers of maximal inscribed discs is a nondigitizable one. The idea presented in this paper is to incorporate the skeleton information and the chain-code of the contour into a single descriptor by associating to each point of a contour the center and radius of the maximum inscribed disc tangent at that point. This new descriptor is called calypter. The encoding of a calypter is a three stage algorithm: (1) chain coding of the contour; (2) euclidean distance transformation, (3) climbing on the distance relief from each point of the contour towards the corresponding maximal inscribed disc center. Here we introduce an integer euclidean distance transform called the holodisc distance transform. The major interest of this holodisc transform is to confer 8-connexity to the isolevels of the generated distance relief thereby allowing a climbing algorithm to proceed step by step towards the centers of the maximal inscribed discs. The calypter has a cyclic structure delivering high speed access to the skeleton data. Its potential uses are in high speed euclidean mathematical morphology, shape processing, and analysis.