Completion Energies and Scale.

Dept. of Comput. Sci. & Appl. Math., Weizmann Inst. of Sci., Rehovot, Israel
IEEE Transactions on Pattern Analysis and Machine Intelligence (Impact Factor: 5.69). 11/2000; 22:1117-1131. DOI: 10.1109/34.879792
Source: DBLP

ABSTRACT Abstract The detection of smooth curves in images and their completion over gaps are two important problems,in perceptual grouping. In this paper we examine,the notion of completion energy and introduce a fast method,to compute,the most likely completions in images. Specifically, we develop two novel analytic approximations,to the curve of least energy. In addition, we introduce a fast numerical method to compute the curve of least energy, and show that our approximations are obtained at early stages of this numerical computation. We then use our newly developed energies to find the most likely completions in images through a generalized summation,of induction fields. Since in practice edge elements are obtained by applying filters of certain widths and lengths to the image, we adjust our computation to take these parameters into account. Finally, we show that, due to the smoothness of the kernel of summation, the process of summing,induction fields can be run in time that is linear in the number of different edge elements in the image, or in log where is the number of pixels in the image, using multigrid methods.

  • [Show abstract] [Hide abstract]
    ABSTRACT: This report will present a summary of views presented during a discussion at the 1999 Workshop on Perceptual Organization in Computer Vision. Our goal is to present diverse views, informally expressed on principles and algorithms of perceptual organization. Naturally, such a discussion must be somewhat limited both by the time available and by the specific set of researchers who could be present. Still, we hope to describe some interesting ideas expressed and to note the number of areas of apparent consensus among a fairly broad group. In particular, we will describe views on the state of the art in perceptual grouping, and what seem to be key open questions and promising directions for addressing them.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Contour Completion plays an important role in visual perception, where the goal is to group fragmented low-level edge elements into perceptually coherent and salient contours. This process is often considered as guided by some middle-level Gestalt principles. Most existing methods for contour completion have focused on utilizing rather local Gestalt laws such as good-continuity and proximity. In contrast, much fewer methods have addressed the global contour closure effect, despite that many psychological evidences have shown the usefulness of closure in perceptual grouping. This paper proposes a novel higher-order CRF model to address the contour closure effect, through local connectedness approximation. This leads to a simplified problem structure, where the higher-order inference can be formulated as an integer linear program (ILP) and solved by an efficient cutting-plane variant. Tested on the BSDS benchmark, our method achieves a comparable precision-recall performance, a superior contour grouping ability (measured by Rand index), and more visually pleasing results, compared with existing methods.
    Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on; 01/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a novel method that fuses, through a graph matching, segmentation of the blood vessels in contrast-enhanced images with segmentation of the guide-wires in the fluoroscopic images. This is achieved through a bottom up approach that first extracts local geometric primitives of interest in both images. Fusion between two graphs built with these primitives is performed through spectral matching and allows the definition of an improved criterion of ordering of the wire primitives. Given such criterion, local ordering is used towards reconstruction of multiple curvilinear structures that inherit visual support from both images. An evaluation performed on a broad variety of clinical situations validates the effectiveness of our approach.
    Proceedings / IEEE International Symposium on Biomedical Imaging: from nano to macro. IEEE International Symposium on Biomedical Imaging 01/2012;

Full-text (5 Sources)

Available from
May 21, 2014