Showing papers on "Distance transform published in 2010"

Image Processing and Pattern Recognition: Fundamentals and Techniques

Abstract: PART I: FUNDAMENTALS. 1 INTRODUCTION. 1.1 The World of Signals. 1.2 Digital Image Processing. 1.3 Elements of an Image Processing System. Appendix 1.A Selected List of Books on Image Processing and Computer Vision from Year 2000. References. 2 MATHEMATICAL PRELIMINARIES. 2.1 Laplace Transform. 2.2 Fourier Transform. 2.3 Z-Transform. 2.4 Cosine Transform. 2.5 Wavelet Transform. 3 IMAGE ENHANCEMENT. 3.1 Grayscale Transformation. 3.2 Piecewise Linear Transformation. 3.3 Bit Plane Slicing. 3.4 Histogram Equalization. 3.5 Histogram Specification. 3.6 Enhancement by Arithmetic Operations. 3.7 Smoothing Filter. 3.8 Sharpening Filter. 3.9 Image Blur Types and Quality Measures. 4 MATHEMATICAL MORPHOLOGY. 4.1 Binary Morphology. 4.2 Opening and Closing. 4.3 Hit-or-Miss Transform. 4.4 Grayscale Morphology. 4.5 Basic Morphological Algorithms. 4.6 Morphological Filters. 5 IMAGE SEGMENTATION. 5.1 Thresholding. 5.2 Object (Component) Labeling. 5.3 Locating Object Contours by the Snake Model. 5.4 Edge Operators. 5.5 Edge Linking by Adaptive Mathematical Morphology. 5.6 Automatic Seeded Region Growing. 5.7 A Top-Down Region Dividing Approach. 6 DISTANCE TRANSFORMATION AND SHORTEST PATH PLANNING. 6.1 General Concept. 6.2 Distance Transformation by Mathematical Morphology. 6.3 Approximation of Euclidean Distance. 6.4 Decomposition of Distance Structuring Element. 6.5 The 3D Euclidean Distance. 6.6 The Acquiring Approaches. 6.7 The Deriving Approaches. 6.8 The Shortest Path Planning. 6.9 Forward and Backward Chain Codes for Motion Planning. 6.10 A Few Examples. 7 IMAGE REPRESENTATION AND DESCRIPTION. 7.1 Run-Length Coding. 7.2 Binary Tree and Quadtree. 7.3 Contour Representation. 7.4 Skeletonization by Thinning. 7.5 Medial Axis Transformation. 7.6 Object Representation and Tolerance. 8 FEATURE EXTRACTION. 8.1 Fourier Descriptor and Moment Invariants. 8.2 Shape Number and Hierarchical Features. 8.3 Corner Detection. 8.4 Hough Transform. 8.5 Principal Component Analysis. 8.6 Linear Discriminate Analysis. 8.7 Feature Reduction in Input and Feature Spaces. 9 PATTERN RECOGNITION. 9.1 The Unsupervised Clustering Algorithm. 9.2 Bayes Classifier. 9.3 Support Vector Machine. 9.4 Neural Networks. 9.5 The Adaptive Resonance Theory Network. 9.6 Fuzzy Sets in Image Analysis. PART II: APPLICATIONS. 10 FACE IMAGE PROCESSING AND ANALYSIS. 10.1 Face and Facial Feature Extraction. 10.2 Extraction of Head and Face Boundaries and Facial Features. 10.3 Recognizing Facial Action Units. 10.4 Facial Expression Recognition in JAFFE Database. 11 DOCUMENT IMAGE PROCESSING AND CLASSIFICATION. 11.1 Block Segmentation and Classification. 11.2 Rule-Based Character Recognition System. 11.3 Logo Identification. 11.4 Fuzzy Typographical Analysis for Character Preclassification. 11.5 Fuzzy Model for Character Classification. 12 IMAGE WATERMARKING. 12.1 Watermarking Classification. 12.2 Spatial Domain Watermarking. 12.3 Frequency-Domain Watermarking. 12.4 Fragile Watermark. 12.5 Robust Watermark. 12.6 Combinational Domain Digital Watermarking. 13 IMAGE STEGANOGRAPHY. 13.1 Types of Steganography. 13.2 Applications of Steganography. 13.3 Embedding Security and Imperceptibility. 13.4 Examples of Steganography Software. 13.5 Genetic Algorithm-Based Steganography. 14 SOLAR IMAGE PROCESSING AND ANALYSIS. 14.1 Automatic Extraction of Filaments. 14.2 Solar Flare Detection. 14.3 Solar Corona Mass Ejection Detection. INDEX.

Segmenting Clustered Nuclei Using H-minima Transform-Based Marker Extraction and Contour Parameterization

Abstract: In this letter, we present a novel watershed-based method for segmentation of cervical and breast cell images. We formulate the segmentation of clustered nuclei as an optimization problem. A hypothesis concerning the nuclei, which involves a priori knowledge with respect to the shape of nuclei, is tested to solve the optimization problem. We first apply the distance transform to the clustered nuclei. A marker extraction scheme based on the H -minima transform is introduced to obtain the optimal segmentation result from the distance map. In order to estimate the optimal h-value, a size-invariant segmentation distortion evaluation function is defined based on the fitting residuals between the segmented region boundaries and fitted models. Ellipsoidal modeling of contours is introduced to adjust nuclei contours for more effective analysis. Experiments on a variety of real microscopic cell images show that the proposed method yields more accurate segmentation results than the state-of-the-art watershed-based methods.

Interactive SPH simulation and rendering on the GPU

Abstract: In this paper we introduce a novel parallel and interactive SPH simulation and rendering method on the GPU using CUDA which allows for high quality visualization. The crucial particle neighborhood search is based on Z-indexing and parallel sorting which eliminates GPU memory overhead due to grid or hierarchical data structures. Furthermore, it overcomes limitations imposed by shading languages allowing it to be very flexible and approaching the practical limits of modern graphics hardware. For visualizing the SPH simulation we introduce a new rendering pipeline. In the first step, all surface particles are efficiently extracted from the SPH particle cloud exploiting the simulation data. Subsequently, a partial and therefore fast distance field volume is rasterized from the surface particles. In the last step, the distance field volume is directly rendered using state-of-the-art GPU raycasting. This rendering pipeline allows for high quality visualization at very high frame rates.

Parallel Banding Algorithm to compute exact distance transform with the GPU

Abstract: We propose a Parallel Banding Algorithm (PBA) on the GPU to compute the exact Euclidean Distance Transform (EDT) for a binary image in 2D and higher dimensions. Partitioning the image into small bands to process and then merging them concurrently, PBA computes the exact EDT with optimal linear total work, high level of parallelism and a good memory access pattern. This work is the first attempt to exploit the enormous power of the GPU in computing the exact EDT, while prior works are only on approximation. Compared to these other algorithms in our experiments, our exact algorithm is still a few times faster in 2D and 3D for most input sizes. We illustrate the use of our algorithm in applications such as computing the Euclidean skeleton using the integer medial axis transform, performing morphological operations of 3D volumetric data, and constructing 2D weighted centroidal Voronoi diagrams.

Unsupervised Segmentation of Overlapped Nuclei Using Bayesian Classification

Abstract: In a fully automatic cell extraction process, one of the main issues to overcome is the problem related to extracting overlapped nuclei since such nuclei will often affect the quantitative analysis of cell images. In this paper, we present an unsupervised Bayesian classification scheme for separating overlapped nuclei. The proposed approach first involves applying the distance transform to overlapped nuclei. The topographic surface generated by distance transform is viewed as a mixture of Gaussians in the proposed algorithm. In order to learn the distribution of the topographic surface, the parametric expectation-maximization (EM) algorithm is employed. Cluster validation is performed to determine how many nuclei are overlapped. Our segmentation approach incorporates a priori knowledge about the regular shape of clumped nuclei to yield more accurate segmentation results. Experimental results show that the proposed method yields superior segmentation performance, compared to those produced by conventional schemes.

Markov Random Field Surface Reconstruction

Abstract: A method for implicit surface reconstruction is proposed. The novelty in this paper is the adaption of Markov Random Field regularization of a distance field. The Markov Random Field formulation allows us to integrate both knowledge about the type of surface we wish to reconstruct (the prior) and knowledge about data (the observation model) in an orthogonal fashion. Local models that account for both scene-specific knowledge and physical properties of the scanning device are described. Furthermore, how the optimal distance field can be computed is demonstrated using conjugate gradients, sparse Cholesky factorization, and a multiscale iterative optimization scheme. The method is demonstrated on a set of scanned human heads and, both in terms of accuracy and the ability to close holes, the proposed method is shown to have similar or superior performance when compared to current state-of-the-art algorithms.

Image-to-class distance metric learning for image classification

Abstract: Image-To-Class (I2C) distance is first used in Naive-Bayes Nearest-Neighbor (NBNN) classifier for image classification and has successfully handled datasets with large intra-class variances. However, the performance of this distance relies heavily on the large number of local features in the training set and test image, which need heavy computation cost for nearest-neighbor (NN) search in the testing phase. If using small number of local features for accelerating the NN search, the performance will be poor. In this paper, we propose a large margin framework to improve the discrimination of I2C distance especially for small number of local features by learning Per-Class Mahalanobis metrics. Our I2C distance is adaptive to different class by combining with the learned metric for each class. These multiple Per-Class metrics are learned simultaneously by forming a convex optimization problem with the constraints that the I2C distance from each training image to its belonging class should be less than the distance to other classes by a large margin. A gradient descent method is applied to efficiently solve this optimization problem. For efficiency and performance improved, we also adopt the idea of spatial pyramid restriction and learning I2C distance function to improve this I2C distance. We show in experiments that the proposed method can significantly outperform the original NBNN in several prevalent image datasets, and our best results can achieve state-of-the-art performance on most datasets.

Image processing apparatus and c0mputer program

Abstract: The present invention relates to an image processing apparatus for compressing image data used in an image generating apparatus for generating a free-viewpoint image. According to the invention, the apparatus has a selecting unit that selects one image as a first image, and defines other images as second images, a projective transformation unit that generates a projected depth map of a second image from a depth map of the first image, a subtracting unit that creates a difference map of the second image, and a storage unit that stores the depth map of the first image and the difference map of the second image. Here, the difference map is a difference between a depth map of the second image and the projected depth map of the second image, and the depth map indicates a depth value of each pixel of a corresponding image.

Precise Hausdorff distance computation for planar freeform curves using biarcs and depth buffer

Abstract: We present a real-time algorithm for computing the precise Hausdorff Distance (HD) between two planar freeform curves. The algorithm is based on an effective technique that approximates each curve with a sequence of G 1 biarcs within an arbitrary error bound. The distance map for the union of arcs is then given as the lower envelope of trimmed truncated circular cones, which can be rendered efficiently to the graphics hardware depth buffer. By sampling the distance map along the other curve, we can estimate a lower bound for the HD and eliminate many redundant curve segments using the lower bound. For the remaining curve segments, we read the distance map and detect the pixel(s) with the maximum distance. Checking a small neighborhood of the maximum-distance pixel, we can reduce the computation to considerably smaller subproblems, where we employ a multivariate equation solver for an accurate solution to the original problem. We demonstrate the effectiveness of the proposed approach using several experimental results.

Finite volume distance field and its application to medial axis transforms

Abstract: Accurate and efficient computation of the nearest wall distance d (or level set) is important for many areas of computational science/engineering. Differential equation-based distance/level set algorithms, such as the hyperbolic-natured Eikonal equation, have demonstrated valuable computational efficiency. Here, in the context, as an ‘auxiliary’ equation to the main flow equations, the Eikonal equation is solved efficiently with two different finite volume approaches (the cell-vertex and cell-centered). The application of the distance solution is studied for various geometries. Moreover, a procedure using the differential field to obtain the medial axis transform (MAT) for different geometries is presented. The latter provides a skeleton representation of geometric models that has many useful analysis properties. As an alternative to other methods, the current d-MAT procedure bypasses difficulties that are usually encountered by pure geometric methods (e.g. the Voronoi approach), especially in three dimensions, and provides better accuracy than pure thinning methods. It is also shown that the d-MAT approach provides the potential to sculpt/control the MAT form for specialized solution purposes.

An efficient graph-based deformable 2D/3D registration algorithm with applications for abdominal aortic aneurysm interventions

Abstract: 2D/3D registration is in general a challenging task due to its ill-posed nature. It becomes even more difficult when deformation between the 3D volume and 2D images needs to be recovered. This paper presents an automatic, accurate and efficient deformable 2D/3D registration method that is formulated on a 3D graph and applied for abdominal aortic aneurysm (AAA) interventions. The proposed method takes the 3D graph generated from a segmentation of the CT volume and the 2D distance map calculated from the 2D X-ray image as the input. The similarity measure consists of a difference measure, a length preservation term and a smoothness regularization term, all of which are defined and efficiently calculated on the graph. A hierarchical registration scheme is further designed specific to the anatomy of abdominal aorta and typical deformations observed during AAA cases. The method was validated using both phantom and clinical datasets, and achieved an average error of > 1mm within 0.1s. The proposed method is of general form and has the potential to be applied for a wide range of applications requiring efficient 2D/3D registration of vascular structures.

Catheter rf ablation using segmentation-based 2d-3d registration

Abstract: A method for registering a two-dimensional image of a cardiocirculatory structure and a three-dimensional image of the cardiocirculatory structure includes acquiring a three-dimensional image including the cardiocirculatory structure using a first imaging modality. The acquired three-dimensional image is projected into two-dimensions to produce a two-dimensional projection image of the cardiocirculatory structure. A structure of interest is segmented either from the three-dimensional image prior to projection or from the projection image subsequent to projection. A two-dimensional image of the cardiocirculatory structure is acquired using a second imaging modality. The structure of interest is segmented from the acquired two-dimensional image. A first distance map is generated based on the two-dimensional projection image and a second distance map is generated based on the acquired two-dimensional image. A registration of the three-dimensional image and the two-dimensional image is performed by minimizing a difference between the first and second distance maps.

Stereo camera apparatus

Abstract: A stereo camera apparatus which carries out distance measuring stably and with high accuracy by making measuring distance resolution variable according to a distance to an object is provided. A stereo camera apparatus 1 takes in two images, changes resolution of a partial area of each image that is taken in, and calculates a distance from a vehicle to an object that is imaged in the partial area, based on disparity of the partial area of each image in which resolution is changed. Thus, even when the object exists at a long distance and is small in size, distance measuring processing can be carried out stably.

Surface Reconstruction Based on Hierarchical Floating Radial Basis Functions

Abstract: In this paper we address the problem of optimal centre placement for scattered data approximation using radial basis functions (RBFs) by introducing the concept of floating centres. Given an initial least-squares solution, we optimize the positions and the weights of the RBF centres by minimizing a non-linear error function. By optimizing the centre positions, we obtain better approximations with a lower number of centres, which improves the numerical stability of the fitting procedure. We combine the non-linear RBF fitting with a hierarchical domain decomposition technique. This provides a powerful tool for surface reconstruction from oriented point samples. By directly incorporating point normal vectors into the optimization process, we avoid the use of off-surface points which results in less computational overhead and reduces undesired surface artefacts. We demonstrate that the proposed surface reconstruction technique is as robust as recent methods, which compute the indicator function of the solid described by the point samples. In contrast to indicator function based methods, our method computes a global distance field that can directly be used for shape registration.

ODSIM: An Object-Distance Simulation Method for Conditioning Complex Natural Structures

Abstract: Stochastic simulation of categorical objects is traditionally achieved either with object-based or pixel-based methods. Whereas object-based modeling provides realistic results but raises data conditioning problems, pixel-based modeling provides exact data conditioning but may lose some features of the simulated objects such as connectivity. We suggest a hybrid dual-scale approach to combine both shape realism and strict data conditioning. The procedure combines the distance transform to a skeleton object representing coarse-scale structures, plus a classical pixel-based random field and threshold representing fine-scale features. This object-distance simulation method (ODSIM) uses a perturbed distance to objects and is particularly appropriate for modeling structures related to faults or fractures such as karsts, late dolomitized rocks, and mineralized veins. We demonstrate this method to simulate dolomite geometry and discuss strategies to apply this method more generally to simulate binary shapes.

An Approach to the Parameterization of Structure for Fast Categorization

Abstract: A decomposition is described, which parameterizes the geometry and appearance of contours and regions of gray-scale images with the goal of fast categorization. To express the contour geometry, a contour is transformed into a local/global space, from which parameters are derived classifying its global geometry (arc, inflexion or alternating) and describing its local aspects (degree of curvature, edginess, symmetry). Regions are parameterized based on their symmetric axes, which are evolved with a wave-propagation process enabling to generate the distance map for fragmented contour images. The methodology is evaluated on three image sets, the Caltech 101 set and two sets drawn from the Corel collection. The performance nearly reaches the one of other categorization systems for unsupervised learning.

Rapid surface reconstruction from a point cloud using the least-squares projection

Abstract: A new approach for the rapid and robust surface reconstruction from a point cloud is presented based on the distance field and the least-squares projection (LSP) algorithm. This novel approach works directly on the point cloud without any explicit or implicit surface reconstruction procedure. First, a coarse base polygonal model was created directly from the distance field for the given point cloud through the iso-surface extraction. After acquiring a rough base polygonal model, we obtain a quality polygonal model through the iterative refinement and least-squares projection which projects current working polygonal model onto the point cloud in a least-squares sense. The main contribution of this work is the robust and fast surface reconstruction from randomly scattered 3D points only without any further information. We demonstrate the validity and efficiency of this new approach through a number of application examples.

Two-dimensional images in frequency-time representation: direction images and resolution map

Abstract: We discuss the concept of the direction image multiresolution, which is derived as a property of the 2-D discrete Fourier transform, when it splits by 1-D transforms. The N×N image, where N is a power of 2, is considered as a unique set of splitting-signals in paired representation, which is the unitary 2-D frequency and 1-D time representation. The number of splitting-signals is 3N−2, and they have different durations, carry the spectral information of the image in disjoint subsets of frequency points, and can be calculated from the projection data along one of 3N/2 angles. The paired representation leads to the image composition by a set of 3N−2 direction images, which defines the directed multiresolution and contains periodic components of the image. We also introduce the concept of the resolution map, as a result of uniting all direction images into log2 N series. In the resolution map, all different periodic components (or structures) of the image are packed into a N×N matrix, which can be used for image processing in enhancement, filtration, and compression

Imaging device and image input device

Abstract: PROBLEM TO BE SOLVED: To provide an imaging device and an image input device capable of obtaining information on a distance to a subject and a color image signal by once photographing though the constitution is simple.SOLUTION: It is possible to obtain a distance image signal and a color image signal from an identical imaging element and to obtain a color image free from deviation of pixel positions for a distance image. Furthermore, a distance image independent of the shape of the subject can be obtained by measuring a distance pixel by pixel. Even a speedily moving subject can be photographed at real time without need of plural times of photographing.

Deformable 2D-3D registration of structure

Abstract: A method for performing deformable non-rigid registration of 2D and 3D images of a vascular structure for assistance in surgical intervention includes acquiring 3D image data. An abdominal aorta is segmented from the 3D image data using graph-cut based segmentation to produce a segmentation mask. Centerlines are generated from the segmentation mask using a sequential topological thinning process. 3D graphs are generated from the centerlines. 2D image data is acquired. The 2D image data is segmented to produce a distance map. An energy function is defined based on the 3D graphs and the distance map. The energy function is minimized to perform non-rigid registration between the 3D image data and the 2D image data. The registration may be optimized.

Image processing system having an additional piece of scale information to be processed together with the image information

Abstract: The invention relates to an image processing system, containing an optical digital camera (1) having means (4) that produce information representative of a specified geometric distance within the image by means of optical protection using laser light in the detection range of the optical digital camera (1), said information representative of the specified geometric distance being processed together with the image information. Separating means (8) are arranged downstream of the digital camera, said separating means separating the information representative of the specified geometric distance from the image information. Subsequent evaluating means produce a distance value therefrom. Image storage means (9) additionally arranged downstream of the separating means are used to store the recorded image information. Adjustment means (14) automatically change the image size on a screen in the form of a digital zoom for the purpose of setting the reproduction size according to a specified scale factor in such a way that an object contained in the image content, the physical dimension of which object corresponds to the specified geometric distance, is reproduced in a corresponding dimension that is multiplied by the specified scale factor.

Competitive image colorization

Abstract: This paper presents a new method for image colorization based on manually added scribbles. We determine color propagation paths in the image by minimizing the geodesic distance from the scribbles using Dijkstra algorithm. After that, chrominance blending is performed to colorize the image. Our contribution lies in proposing the competitive approach for selecting an appropriate type of the path cost. Moreover, we introduce a modified chrominance distance calculated along each path. Benefits of these improvements are explained and justified. The experiments confirmed that the proposed algorithm yields better results compared with other well-established methods.

Image-assisted modeling from sketches

Abstract: In this paper, we propose a method for creating freeform surfaces from sketch-annotated images. Beginning from an image, the user sketches object boundaries, features, and holes. Sketching is made easier by a magnetic pen that follows strong edges in the image. To create a surface from the sketch, a planar mesh is constructed such that its geometry aligns with the boundary and interior features. We then inflate to 3D using a discrete distance transform filtered through a cross-sectional mapping function. Finally, the input image is applied as a texture to the surface. The benefits of our framework are demonstrated with examples in modeling both freeform and manufactured objects.

Image registration based on Hausdorff distance

Abstract: As for the RST transform in image registration, corresponding formula of box distance transform is deduced. Compared with traditional formula of general affine Hausdorff box distance, search range of distance is reduced. The paper proposes regional Voronoi surface combining comparison of sliding windows when computing Hausdorff distance, characterized by reducing calculating-cost for Voronoi surface. It also has the advantages of eliminating trivial edges and preserving longer edges for calculating. Experimental results show that calculation speed of image registration based on Huasdorff distance is improved.

Methods for evaluating distances in a scene and apparatus and machine readable medium using the same

Abstract: A distance evaluation method for evaluating distances from an observation point to objects within an arbitrary detectable range in a scene is disclosed. The method includes the following steps. First, a focus distance is set to correspond to a lower or higher limit of a chosen detection range. Next, an image is then captured with an image acquisition system, wherein transfer function of the image acquisition system depends on the focus distance. The captured image of the scene is segmented. A blur metric is computed for each image segment of the captured image. The blur metric is associated with the distance of the objects from the observation point in each image segment.

An Inshore Ship Detection Method Based on Contour Matching

Abstract: Inshore ship detection has significant practical meaning,especially for the target change detection.However,it is difficult to realize the inshore ship detection utilizing the traditional area-based method because of the complex background.A partial Hausdorff distance measurement based on image contour matching method is proposed,which is fit for the inshore ship search and location.The main characteristics of the proposed method are,1) a fast distance transform and pyramid decomposition are used to speedup the Hausdorff distance matching;2) a pyramid is constructed from the original image to avoid the over-sample of contour.Experiments with images of satellite are carried out to validate and analyze the proposed method.

Extraction of Human Body Skeleton Based on Silhouette Images

Abstract: Skeleton extraction is essential for general shape representation. A typical skeletonization algorithm should obtain the ability to preserve original object’s topological and hierarchical properties. However, most of current methods are high memory cost, computationally intensive, and also require complex data structures. In this paper, we propose an efficient and accurate skeletonization method for the skeleton feature points extracted from human body based on silhouette images. First, the gradient of distance transform is used to detect critical points inside the foreground. Then, we converge and simplify critical points in order to generate the most important and elegant skeleton feature points. Finally, we present an algorithm which connects the skeleton feature points and estimates the position of skeleton joints.

Method and apparatus for image alignment

Abstract: A first image captured by a first camera can be aligned with at least a segment of a second image captured with a second camera, where the images have an overlapping field of view. Image characteristic values indicative of image characteristics at positions within the overlapping field of view of the first and second images are respectively determined. A difference in position between corresponding image characteristic values in the overlapping field of view in the first image and the overlapping field of view in the second image is determined. A transform is applied to the first image, adjusting an orientation of the first image relative to the second image. The first and second image can be aligned when the difference in position between corresponding image characteristic values in the first and second image is a predetermined amount.