CVGIP: Graphical Models and Image Processing最新文献

A digitized image that consists of text strings and uniformly distributed background symbols must be segmented if the characters in the text string are to be recognized. This paper describes the development and implementation of a morphological approach to character string extraction from overlapping text/background images that minimizes the shape distortion of characters. The effectiveness of this algorithm is demonstrated on several test images.

Previous solutions to the problem of obtaining a least squares fit to a circular arc are discussed. The existence of severe bias in closed form solutions and non-convergence in iterative solutions for shallow arcs is noted. A straightforward and economical iterative procedure is developed which is shown to be stable and have rapid convergence to an unbiased least squares fit on a wide range of synthetic data. The random error in the parameters of these fits is measured and compared with theoretical predictions. The procedure is shown to operate up to the limit of the validity of circular arc fitting. The term well-defined is introduced to describe arcs within this limit. Example applications to image data show the utility of the method, and the inadequacy of previous solutions, in real image analysis tasks.

It is demonstrated by example that non-uniform scaling of polygons prior to reconstruction from slices can lead to illegal intersections when the scaling is retracted. But uniform scaling does not suffer from this potential defect.

In many applications of tomography, the fundamental quantities of interest in an image are geometric ones. In these instances, pixel-based signal processing and reconstruction is at best inefficient, and, at worst, nonrobust in its use of the available tomographic data. Classical reconstruction techniques such as filtered back-projection tend to produce spurious features when data is sparse and noisy; these "ghosts" further complicate the process of extracting what is often a limited number of rather simple geometric features. In this paper, we present a framework that, in its most general form, is a statistically optimal technique for the extraction of specific geometric features of objects directly from the noisy projection data. We focus on the tomographic reconstruction of binary polygonal objects from sparse and noisy data. In our setting, the tomographic reconstruction problem is essentially formulated as a (finite-dimensional) parameter estimation problem. In particular, the vertices of binary polygons are used as their defining parameters. Under the assumption that the projection data are corrupted by Gaussian white noise, we use the maximum likelihood (ML) criterion, when the number of parameters is assumed known, and the minimum description length (MDL) criterion for reconstruction when the number of parameters is not known. The resulting optimization problems are nonlinear and thus are plagued by numerous extraneous local extrema, making their solution far from trivial. In particular, proper initialization of any iterative technique is essential for good performance. To this end, we provide a novel method to construct a reliable yet simple initial guess for the solution. This procedure is based on the estimated moments of the object, which may be conveniently obtained directly from the noisy projection data.

A new algorithm for ray tracing generalized cylinders whose axis is an arbitrary three-dimensional space curve and whose cross-sectional contour can be varied according to a general sweeping rule is presented. The main restriction placed on the class of generalized cylinders that can be ray-traced is that the sweeping rule of the generalized cylinder must be invertible. This algorithm handles a broader class of generalized cylinders than any other reported ray tracer. It has been integrated into a general geometric modeling system that can render objects utilizing visible light as well as simulated X rays. Generalized cylinders are often used in modeling systems because they compactly represent objects. Many commonly occurring objects including snakes, horses, airplanes, flower vases, and organs of the human abdomen such as the stomach and liver can be described naturally and conveniently in terms of one or more generalized cylinder primitives. By extending the class of generalized cylinders that can be conveniently modeled, the presented algorithm enhances the utility of modeling systems based on generalized cylinders. X-ray images of the internal bone structure of a knee joint and a visible light image of a fan blade assembly are presented.

In many imaging applications, boundaries of objects need to be identified in multidimensional digital image data for the visualization and analysis of object information captured in the images. This article addresses the question of how to define boundaries in multidimensional digital spaces so that they are "closed" and connected, and so that they partition the digital space into an interior set that is connected and an exterior set that is connected. Using adjacency relations defined on the elements of the digital space and on boundary elements, we prove some basic results relating to these properties of boundaries. We examine in detail some specific boundary element adjacency relations and present efficient algorithms that track boundaries defined in binary images of any (finite) diinensionality. We conclude with two conjectures relating to the connectedness of boundaries.

We simplify the red/blue segment intersection algorithm of Chazelle et al. (Technical Report UIUC DCS-R-90-1578, Department of Computer Science, University of Illinois at Urbana, 1990). Given sets of n disjoint red and n disjoint blue segments, we count red/blue intersections in O(n log n) time using O(n) space or report them in additional time proportional to their number. Our algorithm uses a plane sweep to presort the segments; then it operates on a list of slabs that efficiently stores a single level of a segment tree. With no dynamic memory allocation, low pointer overhead, and mostly sequential memory reference, our algorithm performs well even with inadequate physical memory.

A very efficient algorithm for the restoration of an image was developed by Chang and Leu. We implemented the algorithm and experimented on numerous variant types of images. When some images with an in-contour were dealt with, four problems were observed. In this article we present the problems by a counterexample and propose simple improvements to modify the results so that the improved algorithm will make possible robust, flexible, and correct region filling and complete reconstruction of an image.

This paper proposes a method for identifying the existence of bar codes in compressed images without any decompression. The compressed images considered here are produced by the CCITT Group 4 (or 2-D coding in Group 3) facsimile compression standard. The proposed method is tested against forms, with Code 39 bar codes, and the results of our experiments show the method is very effective and robust against different form types and for scanning imperfection.

This paper investigates resampling techniques on a pseudohexagonal grid. Hexagonal grids are known to be advantageous in many respects for sampling and representing digital images in various computer vision and graphics applications. Currently, a real hexagonal grid device is still difficult to find. A good alternative for obtaining the advantages of a hexagonal grid is to construct a pseudohexagonal grid on a regular rectangular grid device. In this paper we first describe the options and procedures for constructing such a pseudo-hexagonal grid and then demonstrate techniques of resampling digital images on the pseudohexagonal grid. Four distinct resampling kernels are tested, and their results are illustrated and compared.