Point pattern matching using convex hull edges

Goshtasby, A. Ardeshir; Stockman, George C.

doi:10.1109/tsmc.1985.6313439

Cited by 109 publications

(51 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These range from relaxation-based methods [19,4], to cluster detection in transformation space (by computing point-to-point correspondences [20][21][22], to hierarchical decomposition of transformation space coupled with the application of a robust similarity measure [2,11,23,24]. Most of the techniques presented in these papers are computationally intensive (in a worst-case theoretical sense), or take long times to run in practice.…”

Section: Prior Workmentioning

confidence: 99%

“…Thus, by sampling a number of triples of points (or even pairs or singletons, depending on the number of degrees of freedom in the transformation space), and enumerating all possible matching triples in the other point set, one is likely to encounter a good match. This is the basis of many matching algorithms, including those of Goshtasby and others [20][21][22] and Goodrich et al [17]. and also of methods based on geometric hashing [25,26].…”

Section: Prior Workmentioning

confidence: 99%

See 1 more Smart Citation

Efficient algorithms for robust feature matching

Mount

Netanyahu

Moigne

1999

Pattern Recognition

135

103

View full text Add to dashboard Cite

One of the basic building blocks in any point-based registration scheme involves matching feature points that are extracted from a sensed image to their counterparts in a reference image. This leads to the fundamental problem of point matching: Given two sets of points, find the (affine) transformation that transforms one point set so that its distance from the other point set is minimized. Because of measurement errors and the presence of outlying data points, it is important that the distance measure between the two point sets be robust to these effects. We measure distances using the partial Hausdorff distance. Point matching can be a computationally intensive task, and a number of theoretical and applied approaches have been proposed for solving this problem. In this paper, we present two algorithmic approaches to the point matching problem, in an attempt to reduce its computational complexity, while still providing a guarantee of the quality of the final match. Our first method is an approximation algorithm, which is loosely based on a branch-andbound approach due to Huttenlocher and Rucklidge, (Technical Report 1321, Dept. of Computer Science, Cornell University, Ithaca, 1992; Proc. IEEE Conf. on Computer vision and Pattern Recognition, New York, 1993, pp. 705-706). We show that by varying the approximation error bounds, it is possible to achieve a tradeoff between the quality of the match and the running time of the algorithm. Our second method involves a Monte Carlo method for accelerating the search process used in the first algorithm. This algorithm operates within the framework of a branch-and-bound procedure, but employs point-to-point alignments to accelerate the search. We show that this combination retains many of the strengths of branch-and-bound search, but provides significantly faster search times by exploiting alignments. With high probability, this method succeeds in finding an approximately optimal match. We demonstrate the algorithms' performances on both synthetically generated data points and actual satellite images.

show abstract

Section: Prior Workmentioning

confidence: 99%

Section: Prior Workmentioning

confidence: 99%

Efficient algorithms for robust feature matching

Mount

Netanyahu

Moigne

1999

Pattern Recognition

135

103

View full text Add to dashboard Cite

show abstract

“…As the dimension of GLðnÞ depends quadratically on n, direct generalizations of these methods to higher dimensions would require too much memory to be practical. In another direction, the edges of the point set's convex hull can serve as important features for point matching, as was first noted in [20] for similarity transforms, and the vertices of the convex hull were later used for affine point-set matching in [56], [19]. In [28], affine invariant representations of point sets are obtained by using distance ratios defined by quadruples of feature points, and the convex hull of each point-set is utilized to select some reference points.…”

Section: Previous Workmentioning

confidence: 96%

Higher-Dimensional Affine Registration and Vision Applications

Nejhum

Chi

et al. 2011

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Abstract-Affine registration has a long and venerable history in computer vision literature, and in particular, extensive work has been done for affine registration in IR 2 and IR 3 . This paper studies affine registration in IR m with m typically ranging from 4 to 12. To justify breaking of this dimension barrier, the first part of the paper describes three novel matching problems that can be formulated and solved as affine point-set registration problems in dimensions greater than three: stereo correspondence under motion, image set matching, and covariant point-set matching, problems that are not only interesting in their own right but also have potential for important vision applications. Unfortunately, most of the existing affine registration algorithms do not generalize easily to higher dimensions due to their inefficiency. Therefore, the second part of this paper develops a novel algorithm for estimating the affine transform between two point sets in IR m . Specifically, the algorithm follows the common approach of iteratively solving the correspondences and transform. The initial correspondences are determined using the novel notion of local spectral features, features constructed from local distance matrices. Unlike many correspondence-based methods, the proposed algorithm is capable of registering point sets of different size, and the use of local features provides some degree of robustness against noise and outliers. The proposed algorithm is validated on a variety of synthetic point sets in different dimensions with varying degrees of deformation and noise, and the paper also shows experimentally that several instances of the aforementioned three matching problems can indeed be solved satisfactorily using the proposed affine registration algorithm.

show abstract

“…Image registration methods can be further categorized into feature-and area-based approaches. Feature-based methods (26,27,31,34) generally extract sets of feature points (e.g. end points, center of lines, and center of regions) from reference and target images, and then find the correspondences using their spatial relationships or other correlations.…”

mentioning

confidence: 99%

3D image stack reconstruction in live cell microscopy of Drosophila muscles and its validation

Wasser

2009

Cytometry Pt A

View full text Add to dashboard Cite

Rapid movements of live tissues during the acquisition of 3D image stacks can result in misalignments between successive image slices. The remodeling of the muscles in Drosophila metamorphosis is an example where sporadic motion during image acquisition impede image analysis and volume visualization. Most of the image stack registration algorithms applied in microscopy are aimed at the linear alignment of fixed histological sections. However, live muscles are nonrigid objects and their contractions and relaxations represent nonlinear transformations that cannot be properly rectified by applying purely linear registration methods. We developed a fully automated area-based nonrigid stack registration (NSR) method that minimizes the mean square error of intensities between successive image slices. The mapping function is formulated using the thin plate spline (TPS). A hierarchical linear to nonlinear, coarse to fine matching strategy is applied to ensure stability and fast convergence. Topological structure is preserved by constraining the step size of the nonlinear transformation. To assess the accuracy of 3D reconstruction, we propose a new benchmarking method that measures geometrical features of restored nuclei. We tested our algorithm on image stacks generated by laser scanning confocal microscopy that show live muscles during the prepupal stage of Drosophila metamorphosis. Our registration algorithm is able to restore image stacks that are distorted by periodic contraction of muscles. Quantitative assessment of registration performance agrees well with qualitative visual inspection. Our NSR method is able to restore image stacks for the purpose of visualization and quantitative analysis of Drosophila metamorphosis and, potentially, various other processes in developmental biology studied by 3D live cell microscopy. ' International Society for Advancement of CytometryKey terms live cell imaging; confocal microscopy; 3D reconstruction; nonrigid registration; thin plate spline; Drosophila; muscle development; metamorphosis IN the areas of developmental and cell biology, multidimensional imaging of living tissues has gained increasing popularity as a tool to study and visualize the diversity of cellular functions and behaviors. The progress in live cell imaging is driven by two principal technologies: the development of fluorescent proteins and improvement in instrumentation. Ever since the discovery of the green fluorescent protein (GFP) from the jellyfish Aequorea (1), various studies have demonstrated that GFP, its variants and many other fluorophores from other (mostly marine) animals can be functionally tagged to almost any other protein (2,3). Through genetic engineering it is possible to control multiple aspects of reporter gene expression, including cell type, sub-cellular localization, time and strength, and the color of the fluorophore.Confocal laser scanning microscopy (CLSM) is the most common imaging modality to visualize fluorescently labeled cells in animal models, such as zebrafish, Caen...

show abstract

Point pattern matching using convex hull edges

Cited by 109 publications

References 0 publications

Efficient algorithms for robust feature matching

Efficient algorithms for robust feature matching

Higher-Dimensional Affine Registration and Vision Applications

3D image stack reconstruction in live cell microscopy of Drosophila muscles and its validation

Contact Info

Product

Resources

About