Showing papers on "Distance transform published in 2002"

Measurement of dimensions of solid objects from two-dimensional image(s)

Abstract: The present invention facilitates solid object reconstruction from a two-dimensional image. If an object is of known and regular shape, information about the object can be extracted from at least one view by utilizing appropriate constraints and measuring a distance between a camera and the object and/or by estimating a scale factor between a camera image and a real world image. The same device can perform both the image capture and the distance measurement or the scaling factor estimation. The following processes can be performed for object identification: parameter estimation; image enhancement; detection of line segments; aggregation of short line segments into segments; detection of proximity clusters of segments; estimation of a convex hull of at least one cluster; derivation of an object outline from the convex hull; combination of the object outline, shape constraints, and distance value.

A continuous skeletonization method based on level sets

Abstract: A robust and efficient method in 2D and 3D for the calculation of skeletons for arbitrary objects is presented. The method is based on the calculation of the distance function with respect to the object boundary. This is combined, in a post processing step, with a new indicator to identify the skeleton, which coincides with the singularity set of the distance map. The indicator is defined as a suitable function of certain local momenta of this distance map and allows a robust and accurate computation of the distance from the skeleton set. This distance is then extended, again via the level set method, onto the whole space. Several applications in 2D and 3D are presented.

Tracking nonparameterized object contours in video

Abstract: We propose a new method for contour tracking in video. The inverted distance transform of the edge map is used as an edge indicator function for contour detection. Using the concept of topographical distance, the watershed segmentation can be formulated as a minimization. This new viewpoint gives a way to combine the results of the watershed algorithm on different surfaces. In particular, our algorithm determines the contour as a combination of the current edge map and the contour, predicted from the tracking result in the previous frame. We also show that the problem of background clutter can be relaxed by taking the object motion into account. The compensation with object motion allows to detect and remove spurious edges in background. The experimental results confirm the expected advantages of the proposed method over the existing approaches.

3-D face structure extraction and recognition from images using 3-D morphing and distance mapping

Abstract: We describe a novel approach for creating a three-dimensional (3-D) face structure from multiple image views of a human face taken at a priori unknown poses by appropriately morphing a generic 3-D face. A cubic explicit polynomial in 3-D is used to morph a generic face into the specific face structure. The 3-D face structure allows for accurate pose estimation as well as the synthesis of virtual images to be matched with a test image for face identification. The estimation of a 3-D person's face and pose estimation is achieved through the use of a distance map metric. This distance map residual error (geometric-based face classifier) and the image intensity residual error are fused in identifying a person in the database from one or more arbitrary image view(s). Experimental results are shown on simulated data in the presence of noise, as well as for images of real faces, and promising results are obtained.

Analysis of blood and bone marrow smears using digital image processing techniques

Abstract: In the paper, we deal with the analysis of blood and bone marrow smears. The main aim of this long term project is to obtain a relative frequency histogram of the white blood cells of different lineage and maturity. Especially for clinical application, a proper image normalization and segmentation of the color images of blood and bone marrow smears are necessary. For the image normalization, two approaches were adopted: a) active image processing for pre acquisition standardization and b) a histogram based method for post acquisition standardization. Both methods are based on the HSI (Hue Saturation Intensity) Transform. We have developed a robust method for the declustering of the inevitable clusters of white blood cells based on a thresholded distance transform and an extended region growing algorithm that in contrast to active contours does not need any parameterization. For a successful classification, medical morphologic features are translated into feature extraction operators: the mesh structure of the cells' nucleus is analyzed using watershed transform and Gabor features, the shape of cell and nucleus is analyzed using a set of rotational invariant contour based features. The color and granularity of the cytoplasm yield further features for classification. Current work is focused on classification using the presented features.

Method and system for detecting a geometrically transformed copy of an image

Abstract: A method for detecting a geometrically transformed copy of content in at least a portion of an image, comprises the steps of: (a) providing first and second digital images; (b) searching for objects of interest within each digital image; (c) identifying pairs of corresponding objects of interest in the digital images, wherein each pair of corresponding objects of interest comprises a located object of interest in the first digital image and a corresponding located object of interest in the second digital image that corresponds to the located object of interest in the first image; (d) locating feature points on each located object of interest in each digital image; (e) matching feature points on the located object of interest in the first digital image to the feature points on the corresponding object of interest in the second digital image, thereby generating a set of correspondence points for each image; (f) determining parameters of a geometric transformation that maps the set of correspondence points in the first digital image into the set of correspondence points in the second digital image; (g) transforming the first digital image according to the parameters of the geometric transformation determined in step (f); and (h) detecting regions of similarity between the content of the transformed first digital image and the second digital image, thereby determining if the second image contains a region that is a geometrically transformed copy of a region in the first image.

Region growing in anatomical images

Abstract: A region-growing method for identifying nodules in an anatomical volume segments a 3-D image volume by controlled voxel growth from seed points. The process is based on creation and use of a distance map for tracking the distance of vessel voxels from a predetermined location. A volume map is created that identifies the largest sphere that can pass between a voxel and a predetermined location without touching a non-vessel voxel. The ratio between the distance map and the volume map is analyzed to find regions more likely to contain nodules, the features of which can be extracted or otherwise highlighted.

Fast visualization of plane-like structures in voxel data

Abstract: We present a robust, noise-resistant criterion characterizing plane-like skeletons in binary voxel objects. It is based on a distance map and the geodesic distance along the object's boundary. A parameter allows us to control the noise sensitivity. If needed, homotopy with the original object might be reconstructed in a second step, using an improved distance ordered thinning algorithm. The skeleton is analyzed to create a geometric representation for rendering. Plane-like parts are transformed into an triangulated surface not enclosing a volume by a suitable triangulation scheme. The resulting surfaces have lower triangle count than those created with standard methods and tend to maintain the original geometry, even after simplification with a high decimation rate. Our algorithm allows us to interactively render expressive images of complex 3D structures, emphasizing independently plane-like and rod-like structures. The methods are applied for visualization of the microstructure of bone biopsies.

Image recognition system and method and its program

Abstract: PROBLEM TO BE SOLVED: To correctly classify an input image regardless of a fluctuation in illumination and a state of occlusion of the input image. SOLUTION: An input image sub-region extracting means 2 extracts the sub-region of an input image. An inter-pattern distance calculating means 3 calculates an inter-pattern distance between the sub-region and the sub-region of a registration image pre-filed in a dictionary filing means 5 for each sub-region. A region distance value integrating means 10 integrates the inter-pattern distances obtained for each sub-region. This is conducted for the registration image of each category. An identifying means 4 calculates the minimum value of the integrated inter-pattern distances, and when the minimum value is smaller than a threshold, outputs the category having the minimum distance as a recognition result. COPYRIGHT: (C)2004,JPO

Image retrieval using distance measure

Abstract: A Mahalanobis distance measure is used to identify a query image among plural images in a database. The measure may be used to rank the similarity of one or more images to the query image. A varance-covariance matrix is calculated for all images in the database. The variance-covariance matrix is used to calculate the Mahalanobis distance between the query image and one or more images in the database. A range tree may be used to identify likely image candidates for performing the Mahalanobis distance measurement.

Fast and reliable space leaping for interactive volume rendering

Abstract: We present a fast and reliable space-leaping scheme to accelerate ray casting during interactive navigation in a complex volumetric scene, where we combine innovative space-leaping techniques in a number of ways. First, we derive most of the pixel depths at the current frame by exploiting the temporal coherence during navigation, where we employ a novel fast cell-based reprojection scheme that is more reliable than the traditional intersection-point based reprojection. Next, we exploit the object space coherence to quickly detect the remaining pixel depths, by using a precomputed accurate distance field that stores the Euclidean distance from each empty (background) voxel toward its nearest object boundary. In addition, we propose an effective solution to the challenging new-incoming-objects problem during navigation. Our algorithm has been implemented on a 16-processor SGI Power Challenge and reached interactive rendering rates at more than 10 Hz during the navigation inside 512/sup 3/ volume data sets acquired from both a simulation phantom and actual patients.

Fast two dimensional object localization based on oriented edges

Abstract: A method for object localization comprises defining an edge model for object localization, and searching an image for an object matching the edge model. Searching comprises defining a region of interest, including a portion of the object, sub-sampling the region of interest, and extracting an edge image comprising edges from the region of interest. Searching further comprises thinning at least one edge of the edge image, determining a distance map between the image and the edge image according to a distance transformation, and matching the edge model to the edge image within a search area defined according to the distance map.

Modification on distance transform to avoid over-segmentation and under-segmentation

Abstract: Many techniques, both conventional and morphological, have been proposed in the literature for the segmentation of images. Morphological image segmentation methods, particularly those using a watershed algorithm, have found wide applications. The popular method of F. Meyer and S. Beucher (see J. Visual Comm. Image Representation., vol.1, p.21-46, 1990), based on a marker constrained watershed algorithm which uses only the binary image and its distance transform, can lead to over-segmentation or under-segmentation if the image objects are of irregular shape and they are overlapping or touching. Another problem with the Beucher and Meyer method is that the watersheds constructed may not agree/coincide with the actual image object junctions as only the binary image is used and information contained in the gray scale image is not utilised. We present an approach addressing both these problems. Morphological area-opening on the distance transform is used for choosing markers to avoid over-segmentation and under-segmentation. The second problem is addressed by using a gray scale image instead of a distance transform to force the watersheds to coincide with the actual junctions of the image objects. The proposed procedure has been applied to images with almost similar objects and the results of our procedure of segmentation are found to be very efficient and encouraging.

Efficient estimation of 3D Euclidean distance fields from 2D range images

Abstract: Several existing algorithms for reconstructing 3D models from range data first approximate the object's 3D distance field to provide an implicit representation of the scanned object and then construct a surface model of the object using this distance field. In these existing approaches, computing and storing 3D distance values from range data contribute significantly to the computational and storage requirements. This paper presents an efficient method for estimating the 3D Euclidean distance field from 2D range images that can be used by any of these algorithms. The proposed method uses Adaptively Sampled Distance Fields to minimize the number of distance evaluations and significantly reduce storage requirements of the sampled distance field. The method is fast because much of the computation required to convert the line-of-sight range distances to Euclidean distances can be done during a pre-processing step in the 2D coordinate space of each range image.

Three-dimensional object surface shape modeling apparatus, method and program

Abstract: In order to provide a curved surface model generating technique which makes use of both advantages of a modeling method by using distance image data and a modeling method by using silhouette data while photographic and measurement data from less angles are utilized, firstly a curved surface model generating section inputs 2D color image data and distance image data. When silhouette image data are extracted from the 2D color image data, initial model data are generated by the Volume Intersection method or the like. The distance image data are converted into world coordinate values by using photographing position/posture data. In a fitting processing section, a fidelity where the distance with the distance image data is used as a measure and a fidelity where the distance with the silhouette image data is used as a measure are added to be evaluated, and a curved surface is fitted to initial model data so that curve surface model data are generated.

Enhancing textured range images using a 2D editor

Abstract: A method edits a 3D model using 2D images. First, a projected range image is generated from a 3D model. The projected range image is edited using a 2D editor. A projected distance and a cliff distance from a plurality of 3D points to a 3D surface of the 3D model are determined using the edited projected range image. The projected distance and the cliff distance of each of the 3D points are combined to determine a distance from each 3D point to the 3D surface so that the distances forming a distance field of the edited 3D model.

A comparative analysis of two distance measures in color image databases

Abstract: The Euclidean distance measure has been used in comparing feature vectors of images, while the cosine angle distance measure is used in document retrieval. We theoretically analyze these two distance measures based on feature vectors normalized by image size and experiment with them in the context of a color image database. We find that the cosine angle distance, in general, works equally well for image databases. We show, for a given query vector, the characteristics of feature vectors that will be favored by one measure but not by the other. We compute k-nearest neighbors for query images using both Euclidean and cosine angle distance for a small image database. The experimental data corroborate our theoretical results.

Multiresolution distance volumes for progressive surface compression

Abstract: We present a surface compression method that stores surfaces as wavelet-compressed signed-distance volumes. Our approach enables the representation of surfaces with complex topology and arbitrary numbers of components within a single multiresolution data structure. This data structure elegantly handles topological modification at high compression rates. Our method does not require the costly and sometimes infeasible base mesh construction step required by subdivision surface approaches. We present several improvements over previous attempts at compressing signed-distance functions, including an O(n) distance transform, a zero set initialization method for triangle meshes, and a specialized thresholding algorithm. We demonstrate the potential of sampled distance volumes for surface compression and progressive reconstruction for complex high genus surfaces.

An FPGA Co-processor for Real-Time Visual Tracking

Abstract: This paper presents the design overview and the post-synthesis simulation results of a digital co-processor for real-time visual tracking implemented in a Virtex-E field programmable gate array. The hardware description of the system was made in VHDL and the simulations show that the system performs up to 79 frames per second in a half-resolution VGA image format (320 × 240 pixels). The co-processor calculates edge/corner detection, stationary background and noise filtering, and the distance transform algorithm; these optimized operations implemented in the FPGA and the Hausdorff distance algorithm programmed in a general purpose processor implement a real-time visual tracking system.

Quality image metrics for synthetic images based on perceptual color differences

Abstract: Due to the improvement of image rendering processes, and the increasing importance of quantitative comparisons among synthetic color images, it is essential to define perceptually based metrics which enable to objectively assess the visual quality of digital simulations. In response to this need, this paper proposes a new methodology for the determination of an objective image quality metric, and gives an answer to this problem through three metrics. This methodology is based on the LLAB color space for perception of color in complex images, a modification of the CIELab1976 color space. The first metric proposed is a pixel by pixel metric which introduces a local distance map between two images. The second metric associates, to a pair of images, a global value. Finally, the third metric uses a recursive subdivision of the images to obtain an adaptative distance map, rougher but less expensive to compute than the first method.

A volumetric approach for interactive 3D modeling

Abstract: Range image registration and surface reconstruction have been traditionally considered as two independent problems where the latter relies on the results of the former. This paper presents a new approach to surface recovery from range images where these two processes are integrated and performed in a common volumetric representation. The volumetric representation contains both implicitly represented reconstructed surface as the signed distance field and corresponding matching information in the form of the gradient of the distance field. This allows both simultaneous and incremental registration where matching complexity is linear with respect to the number of images. This improvement leads to incremental modeling from range image acquisition to surface reconstruction. It is shown that the approach is tolerant to initial registration errors as well as to measurement errors while keeping the details of the initial range images. The paper describes the formalism of the approach. Experimental results demonstrate performance advantages, tolerance to aforementioned types of errors and, as an application, filtering using redundant range data without loss of sharp details on the reconstructed surface.

Using grey-level and distance information for medial surface representation of volume images

Abstract: A medial surface representation of a grey-level volume image is computed. The foreground is reduced to a subset topologically equivalent to the initial foreground and mainly consisting of surfaces centred within regions having locally higher intensities, here, regarded as more informative. This result is obtained by combining distance information with grey-level information. A surface skeleton is first computed, where excessive shortening is prevented by a regularity condition defined on the distance transform. The structure of the surface skeleton is then simplified by removing some peripheral surfaces, so obtaining the desired medial surface representation.

Hand Gesture Recognition Based on Hausdorff Distance

Abstract: With the development of the advanced techniques of human computer interaction(HCI), gesture recognition is becoming one of the key techniques of HCI. Due to some notable advantages of vision based gesture recognition(VGR), e.g. more naturalness to HCI, now VGR is an active research topic in the fields of image processing, pattern recognition, computer vision and others. The method of model matching using Hausdorff distance has the characters of low computing cost and strong adaptability. The system described in this paper applies the hausdorff distance for the first time to visually recognize the chinese finger alphabet(CFA) gestures(total 30 gestures) with the recognition features of edge pixels in the distance transform space. In order to improve the robust performance of the system, the modified hausdorff distance(MHD) has been proposed and applied in the recognition process. The average recognition rate of the system using MHD is up to 96 7% on the testing set. The experimental result of the system shows that using the method of model matching based on the Hausdorff distance to realize the vision based static gesture recognition is feasible.