Showing papers on "Distance transform published in 1995"

Efficient color histogram indexing for quadratic form distance functions

Abstract: In image retrieval based on color, the weighted distance between color histograms of two images, represented as a quadratic form, may be defined as a match measure. However, this distance measure is computationally expensive and it operates on high dimensional features (O(N)). We propose the use of low-dimensional, simple to compute distance measures between the color distributions, and show that these are lower bounds on the histogram distance measure. Results on color histogram matching in large image databases show that prefiltering with the simpler distance measures leads to significantly less time complexity because the quadratic histogram distance is now computed on a smaller set of images. The low-dimensional distance measure can also be used for indexing into the database. >

Linear time Euclidean distance transform algorithms

Abstract: Two linear time (and hence asymptotically optimal) algorithms for computing the Euclidean distance transform of a two-dimensional binary image are presented. The algorithms are based on the construction and regular sampling of the Voronoi diagram whose sites consist of the unit (feature) pixels in the image. The first algorithm, which is of primarily theoretical interest, constructs the complete Voronoi diagram. The second, more practical, algorithm constructs the Voronoi diagram where it intersects the horizontal lines passing through the image pixel centers. Extensions to higher dimensional images and to other distance functions are also discussed. >

Recovering the position and orientation of free-form objects from image contours using 3D distance maps

Abstract: The accurate matching of 3D anatomical surfaces with sensory data such as 2D X-ray projections is a basic problem in computer and robot assisted surgery, In model-based vision, this problem can be formulated as the estimation of the spatial pose (position and orientation) of a 3D smooth object from 2D video images The authors present a new method for determining the rigid body transformation that describes this match The authors' method performs a least squares minimization of the energy necessary to bring the set of the camera-contour projection lines tangent to the surface To correctly deal with projection lines that penetrate the surface, the authors consider the minimum signed distance to the surface along each line (ie, distances inside the object are negative) To quickly and accurately compute distances to the surface, the authors introduce a precomputed distance map represented using an octree spline whose resolution increases near the surface This octree structure allows the authors to quickly find the minimum distance along each line using best-first search Experimental results for 3D surface to 2D projection matching are presented for both simulated and real data The combination of the authors' problem formulation in 3D, their computation of line to surface distances with the octree-spline distance map, and their simple minimization technique based on the Levenberg-Marquardt algorithm results in a method that solves the 3D/2D matching problem for arbitrary smooth shapes accurately and quickly >

Mathematical morphology: a modern approach in image processing based on algebra and geometry

Abstract: Mathematical morphology is a theory of image transformations and image functionals which is based on set-theoretical, geometrical, and topological concepts. The methodology is particularly useful for the analysis of the geometrical structure in an image. The main goal of this paper is to give an impression of the underlying philosophy and the mathematical theories which are relevant to this field. The following topics are discussed: introduction to mathematical morphology; generalization to complete lattices; morphological filters and their construction by iteration; geometrical aspects of morphology (e.g., convexity, distance, geodesic operators, granulometries, metric dilations, distance transform, cost functions); and extension of binary operators to grey-scale images.

Image pre-processor for character recognition system

Abstract: A personal imaging computer system, which is connectable to and operable with a computerized local or wide area network, identifies characters in a document on which the characters are formed. The system scans the document to obtain a gray-scale image of the document, de-skews the gray-scale image, generates a binary image from the de-skewed gray-scale image by comparing the gray-scale image with the threshold, segments the binary image to locate individual characters within the binary image and to determine the shape of the individual characters, extracts gray-scale image information from the gray-scale image for each such individual character based on the location and shape of the character in the binary image, recognition-processes the extracted gray scale image information to determine the identity of the character, and stores the identity of the character. Image pre-processing for the personal imaging computer system includes pre-processing for de-skewing the image, for obtaining and applying a global threshold which converts a gray-scale image to a binary image, for removing underlines from underlined characters in the image, for obtaining connected components within a binary image, and for applying plural sets of rules to the connected components so as to filter text-type connected components from non-text type connected components, whereby only text-type connected components are subjected to character recognition processing.

Image combining method and apparatus

Abstract: In image combining method of phototaking an object to be photographed by using a plurality of image taking systems with portions of fields of view thereof overlapping, and forming combined image information by combining pieces of image information obtained by the image taking systems, coordinates changing processing is performed by using the distance information of an object to be photographed, and image signals output from the respective image taking systems are compensated in accordance with the changed coordinates. One of the compensated image signals is selected with respect to a region where a far-distance portion of the object is concealed by a near-distance object, of the overlapping region of a combined image signal. With this operation, a plurality of image signals output from the respective image taking systems are combined into one image signal output in a state defined by an arbitrary object distance and the imaging magnification from an image taking system in which the viewpoint position and the optical axis direction are defined by the shift amount of the viewpoint position from each image taking system and the convergence angle of the optical axis.

Registration in Neurosurgery and Neuroradiotherapy Applications

Abstract: Because of the high level of accuracy needed in neurosurgery, many computer-assisted surgery (CAS) and augmented reality techniques have been developed in this field. A common issue with all of these techniques is registration between preoperative three-dimensional images (computed tomography and magnetic resonance imaging) and the patient in the operating room. We present, in the first part of this paper, a survey of the latest CAS technologies, using fully automatic registration without fiducial landmarks. All of the registration algorithms described are based on minimization of a cost function. We then describe our approach. Our cost function is simply the mean square error (MSE), minimized by the iterative closest point algorithm (ICP). Because the weak point of the ICP algorithm is the closest point computational cost, we precalculate it by a “closest point map,” inspired from classical distance map. We finally perturb the found solution to eliminate local minima close to the global minimum. This pap...

Hierarchical path planning in a multi-robot environment with a simple navigation function

Abstract: Considers the problem of robot motion planning using an approximate cell decomposition method for Cspace representation. By means of a hierarchical multilevel discretization the authors are able to reduce the complexity of the problem and to provide a practically feasible procedure for its solution. Hierarchical discretization is based on the use of a multisource distance field that is introduced and described in the paper. The developed procedure, used as an heuristic, systematically reduces the amount of memory needed for implementing the motion planning algorithm. Using such a procedure, several instances of the motion planning problem, involving for example two three-links manipulators acting in the same tridimensional environment, have been solved in a reasonable amount of time. >

Synthesising Objects and Scenes Using the Reverse Distance Transformation in 2D and 3D

Abstract: The reverse distance transformation has proved useful in image synthesis. This paper describes how digital objects are created from a number of seed labels in an image. The shape of the obtained objects depends on the metric used. In 2D the Euclidean and the 3-4 metrics are mentioned, and in 3D the D6, the D26, and the 3-4-5 metrics are discussed. The proposed method has no need of expensive CAD systems. It is an excellent image synthesising tool when developing image processing algorithms, i. e. shape quantification, visualisation, scene analysis and range imaging, as the obtained objects are well-defined in the image. The method is most advantageous in 3D, as there is an increasing need for volume images, but synthesising objects in 2D can also be useful.

Efficient Image Matching

Abstract: Image matching has played a key role in object recognition and localization. One central problem is to find an efficient and effective approach to search for the best matching between two image sets. In contrast to the conventional matching techniques, the innovation of our method detailed in this paper is to propose a hierarchical Chamfer matching scheme based on the dynamic detection of interesting points. The algorithm extends the traditional methods by introducing interesting points to replace edge points in distance transform for the matching measurement. The search for the best matching is guided by minimizing a given matching criterion in an interesting points pyramid from coarse level to fine level. The pyramid is created through a dynamic thresholding scheme and such a hierarchical structure aims to reduce the computation load. The processing speed is further improved by parallel implementation on a low cost heterogeneous PVM (Parallel Virtual Machine) network without specific software and hardware requirements. The experimental results demonstrate that our algorithm is simple to implement and quite insensitive to noise and other disturbances with reliability and efficiency.

Form dropout using distance transformation

Abstract: Forms are an important means for information gathering, storage, retrieval, approval, and distribution in business and government organizations. This paper presents a form dropout approach which employs a distance transform and its gradient flow. Form templates are pre-processed off-line to obtain their distance transforms and gradient flows. We demonstrate that various components in the form dropout algorithm can derive benefit from rich geometric information about the form template which are made explicit in the distance transform and its gradient flow. Experimental results are also presented.

Hierarchical image matching: a chamfer matching algorithm using interesting points

Abstract: Image matching in conjunction with a distance transform has played an important role in computer vision and image analysis. This paper presents a new hierarchical chamfer matching algorithm based on the detection of interesting points. The algorithm extends the traditional method by introducing interesting points to replace edge points in the distance transform for the matching measurement. A series of images, with different numbers of interesting points featuring in the original image, is created in a pyramid structure through a dynamic thresholding scheme. The matching is performed in this pyramid in a coarse-to-fine level order, by minimizing a given matching criterion in terms of the distance between selected interesting points. This hierarchical structure aims to reduce the computational load. The algorithm is simple to implement and quite insensitive to noise and other disturbances. In addition, such a hierarchical matching scheme is implemented on a low-cost heterogeneous PVM (Parallel Virtual Machine) network to speed up the processing without any specific software and hardware requirements.

A hierarchical image matching scheme based on the dynamic detection of interesting points

Abstract: This paper presents a parallel approach to a hierarchical image matching scheme using the Hausdorff distance for object recognition and localization in aerial images. Unlike the conventional matching methods in which edge pixels are considered as image feature pixels, the distance transform and the blind pointwise comparison procedure is simplified and extended in terms of the Hausdorff distance, and a guided image matching system is developed by the hierarchical detection of interesting points via a dynamic thresholding scheme for the search of the best matching between two image sets. Furthermore, the concept of remote procedure call (RPC) in distributed systems is introduced for the parallel implementation to achieve the speedup without specific software and hardware requirements.

A VLSI chip for computing the medial axis transform of an image

Abstract: We describe a new special purpose VLSI architecture for computing the medial axis transform of an image. The architecture is systolic and is based on an algorithm that achieves a high degree of parallelism. The proposed algorithm computes the skeleton of multiple objects in an image in linear time by making 2 scans over the 4 distance transform of the image. The algorithm is mapped onto a linear systolic array of simple processing elements (PEs) and for an N/spl times/N image, the architecture requires N PE's. The entire array can be realized in a single VLSI chip. The proposed hardware can perform thinning on a 512/spl times/512 image in 2.59 msec and on a 256/spl times/256 image in 0.327 msec. A prototype CMOS VLSI chip implementing the proposed architecture has been designed and verified.

An efficient 3D deformable model with a self-optimising topology

Abstract: Deformable models are a powerful and popular tool for image segmentation, but in 3D imaging applications the high computational cost of fitting such models can be a problem. A further drawback is the need to select the initial size and position of a model in such a way that it is close to the desired solution. This task may require particular expertise on the part of the operator, and, furthermore, may be difficult to accomplish in three dimensions without the use of sophisticated visualisation techniques. This article describes a 3D deformable model that uses an adaptive mesh to increase computational efficiency and accuracy. The model employs a distance transform in order to overcome some of the problems caused by inaccurate initialisation. The performance of the model is illustrated by its application to the task of segmentation of 3D MR images of the human head.

Constant time BSR solutions to L 1 metric and digital geometry problems

Abstract: In this paper we solve several geometric and image problems using the BSR (broadcasting with selective reduction) model of parallel computation. All of the solutions presented are constant time algorithms. The computational geometry problems are based on city block distance metrics: all nearest neighbors and furthest pairs ofm points in a plane are computed on a two criteria BSR withm processors, the all nearest foreign neighbors and the all furthest foreign pairs ofm points in the plane problems are solved on three criteria BSR withm processors while the area and perimeter ofm isooriented rectangles are found on a one criterion BSR withm2 processors. The problems on ann ×n binary image which are solved here all use BSR withn2 processors and include: histogramming (one criterion), distance transform (one criterion), medial axis transform (three criteria) and discrete Voronoi diagram of labeled images (two criteria).

Measurement of ring-shaped and toothed mechanical parts through image processing

Abstract: The automatic non-touch measurement of ring- shaped and toothed mechanical parts is an important task in the industry. This paper introduces two methods for image processing of such parts: the method using the dominant point detection and the method using the distance transform. The two methods are applied successfully to measure the characteristic quantities from practical scenes. The results are discussed and compared with each other.

Processing of text documents: straight line approximation and lost loop recovery

Abstract: This paper deals with two different problems in processing of text documents. Firstly, an integrated algorithm that finds a straight line approximation of a textual stroke is described. It has the advantage of using the distance transform of thinned binary images to identify, spurious bifurcation points which are unavoidable when thinning algorithms are used, remove them, and recover the original ones. Secondly, a method is presented to recover loops that become blobs due to blotting. The method depends on removing the pixels whose distance transform exceeds a calculated threshold.

Skeletonization via distance maps and level sets

Abstract: The medial axis transform (MAT) of a shape, better known as its skeleton, is frequently used in shape analysis and related areas. In this paper a new approach for determining the skeleton of an object, is presented. The boundary is segmented at points of maximal positive curvature and a distance map from each of the segments is calculated. The skeleton is then located by applying simple rules to the zero sets of distance maps differences. A framework is proposed for numerical approximation of distance maps that is consistent with the continuous case, hence does not suffer from digitization bias due to metrication errors of the implementation on the grid. Subpixel accuracy in distance map calculation is obtained by using gray level information along the boundary of the shape in the numerical scheme. The accuracy of the resulting efficient skeletonization algorithm is demonstrated by several examples.

Reciprocal-wedge transform: a space-variant image representation

Abstract: The problems in computer vision have traditionally been approached as recovery problems. In active vision, perception is viewed as an active process of exploratory, probing and searching activities rather than a passive re-construction of the physical world. To facilitate effective interaction with the environment, a foveate sensor coupled with fast and precise gaze control mechanism becomes essential for active data acquisition. In this thesis, the Reciprocal-Wedge Transform (RWT) is proposed as a spacevariant image model. The RWT has its merits in comparison with other alternative foveate sensing models such as the log-polar transform. The concise matrix representation makes it enviable for its simplified computation procedures. Similar to the log-polar transform, the RWT facilitates space-variant sensing which enables effective use of variable-resolution data and the reduction of the total amount of the sensory data. Most interestingly, its property of anisotropic mapping yields variable resolution primarily in one dimension. Consequently, the RWT preserves linear features and performs especially well on translations in the images. A projective model is developed for the transform, lending it to potential hardware implementation of RWT projection cameras. The CCD camera for the log-polar transform requires sensing elements of exponentially varying sizes. In contrast, the RWT camera achieves variable resolution with oblique image plane projection, thus alleviating the need for non-rectangular tessellation and sensitivity scaling on the sensing elements. A camera model making use of the available lens design techniques is investigated. The RWT is applied to motion analysis and active stereo to illustrate the effectiveness of the image model. In motion analysis, two types of motion stereo are investigated, namely, longitudinal and lateral motion stereo. RWT motion stereo algorithms are developed for linear and circular ego motions in road navigation, and depth recovery from moving parts on an assembly belt. The algorithms benefit from the perspective correction, linear feature preservation and efficient data reduction of the RWT. The RWT imaging model is also shown to be suitable for fixation control in active stereo. Vergence and versional eye movements and scanpath behaviors are studied. A computational interpretation of stereo fusion in relation to disparity limit in spacevariant imagery leads to the development of a computational model for binocular fixation. The unique oculomotor movements for binocular fixation observed in human system appears natural to space-variant sensing. The vergence-version movement sequence is implemented for an effective fixation mechanism in RWT imaging. An interactive fixation system is simulated to show the various modules of camera control, vergence and version. Compared to the traditional reconstructionist approach, active behavior is shown to be plausible.