12th International Conference on Image Analysis and Processing, 2003.Proceedings.

17-19 Sept. 2003

Filter Results

Displaying Results 1 - 25 of 113
  • 3DMODS: 3D moving obstacle detection system

    Publication Year: 2003, Page(s):618 - 623
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (803 KB) | HTML iconHTML

    The proposed system is aimed at detecting and classifying 3D moving objects for security control of unmanned automatic railway stations. Most common approaches are based on active sensors like optical barriers or laser scanning devices. The proposed approach, named 3DMODS, is based on stereo vision technology, using a prediction-verification paradigm. Adaptive change detection is performed at the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The mantis head camera (why the praying mantis is so good at catching its prey)

    Publication Year: 2003, Page(s):612 - 617
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (415 KB) | HTML iconHTML

    Inspired by the abilities of the praying mantis to judge the distance to its prey before striking by use of motion-based visually mediated odometry, we create a miniature model for depth estimation that is similar to the head movements of the praying mantis. We develop mathematical models of the praying mantis behavior and describe our implementations and experimental environment. We investigate t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robustness to noise of stereo matching

    Publication Year: 2003, Page(s):606 - 611
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (372 KB) | HTML iconHTML

    We have measured the performance of several area-based stereo matching algorithms with noise added to synthetic images. Dense disparity maps were computed and compared with the ground truth using three metrics: the fraction of correctly computed disparities, the mean and the standard deviation of the disparity error distribution. For a noise-free image, S. Birchfield and C. Tomasi's pixel-to-pixel... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation approach by learning: different image applications

    Publication Year: 2003, Page(s):600 - 604
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (742 KB) | HTML iconHTML

    We present a new segmentation approach by thresholding based on learning strategy. This strategy is based only on one image and its ideal thresholded version. A decision matrix is generated from each pixel and each gray level. At the moment of new image segmentation, the best solution for each pixel is evaluated by means of K nearest neighbors in the decision matrix. Comparative tests were perform... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Highlight extraction in soccer videos

    Publication Year: 2003, Page(s):498 - 503
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (422 KB) | HTML iconHTML

    Live logging and posterity logging are the two basic applications for video databases. The former aims at providing effective annotation of video in quasi-real time and supports extraction of meaningful clips from the live stream; the latter provides annotation for later reuse of video material and is the prerequisite for retrieval by content from video digital libraries. Both require that informa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A statistical rationalisation of Hartley's normalised eight-point algorithm

    Publication Year: 2003, Page(s):334 - 339
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (343 KB) | HTML iconHTML

    The eight-point algorithm of Hartley occupies an important place in computer vision, notably as a means of providing an initial value of the fundamental matrix for use in iterative estimation methods. In this paper, a novel explanation is given for the improvement in performance of the eight-point algorithm that results from using normalised data. A first step is singling out a cost function that ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An empirical performance evaluation technique for discrete second derivative edge detectors

    Publication Year: 2003, Page(s):594 - 599
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (334 KB) | HTML iconHTML

    The problem of edge evaluation in relation to image gradient-based edge detectors has been widely studied, and there exist a range of edge evaluation techniques that are appropriate to such edge detectors. Although discrete second derivative operators often form the basis of edge detection methods, whereby zero-crossings are used to locate edge pixels, rather less attention has been paid to the de... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Content-based video summarization and adaptation for ubiquitous media access

    Publication Year: 2003, Page(s):494 - 496
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (202 KB) | HTML iconHTML

    Today's mobile and wireless users access multimedia content from different types of networks and terminals. Content analysis plays a critical role in developing effective solutions in meeting unique resource constraints and user preferences in such usage environments. Specifically, content analysis is central to automatic discovery of syntactic-level summaries and generation of concise semantic-le... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical matching of panoramic images

    Publication Year: 2003, Page(s):328 - 333
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (356 KB) | HTML iconHTML

    When matching regions from "similar" images, one typically has the problem of missing counterparts due to local or even global variations of segmentation fineness. Matching segmentation hierarchies, however, not only increases the chances of finding counterparts, but also allows us to exploit the manifold constraints coming from the topological relations between the regions in a hierarchy. In this... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture analysis based on local semicovers

    Publication Year: 2003, Page(s):588 - 593
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1312 KB) | HTML iconHTML

    The paper presents a new efficient approach to texture analysis based on distributions of simple spatial and tonal relationships. The texture description proposed makes use of a semicover concept over binary planes derived from grey images. A measure of the local semicover tendency based on joint occurrences of elementary semicover patterns is described, and a computation simplification method is ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Depth-first k-nearest neighbor finding using the MaxNearestDist estimator

    Publication Year: 2003, Page(s):486 - 491
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (300 KB) | HTML iconHTML

    Similarity searching is an important task when trying to find patterns in applications which involve mining different types of data such as images, video, time series, text documents, DNA sequences, etc. Similarity searching often reduces to finding the k nearest neighbors to a query object. A description is given of how to use an estimate of the maximum possible distance at which a nearest neighb... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A graphics hardware implementation of the generalized Hough transform for fast object recognition, scale, and 3D pose detection

    Publication Year: 2003, Page(s):188 - 193
    Cited by:  Papers (25)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (480 KB) | HTML iconHTML

    The generalized Hough transform constitutes a wellknown approach to object recognition and pose detection. To attain reliable detection results, however, a very large number of candidate object poses and scale factors need to be considered. We employ an inexpensive, consumer-market graphics-card as the "poor man's" parallel processing system. We describe the implementation of a fast and enhanced v... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An efficient algorithm for exhaustive template matching based on normalized cross correlation

    Publication Year: 2003, Page(s):322 - 327
    Cited by:  Papers (18)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (340 KB) | HTML iconHTML

    This work proposes a novel technique aimed at improving the performance of exhaustive template matching based on the normalized cross correlation (NCC). An effective sufficient condition, capable of rapidly pruning those match candidates that could not provide a better cross correlation score with respect to the current best candidate, can be obtained exploiting an upper bound of the NCC function.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Class-oriented recognizer design by weighting local decisions

    Publication Year: 2003, Page(s):676 - 681
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (553 KB) | HTML iconHTML

    The paper presents a new technique for the design of class-oriented recognizer. For each recognizer, a generic technique is used to determine, in an optimal way, the weights to balance the local decisions obtained from the analysis by parts of the patterns of the specific class. The experimental results, that have been obtained in the field of handwritten numeral and character recognition, demonst... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical modeling via optimal context quantization

    Publication Year: 2003, Page(s):380 - 384
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (236 KB) | HTML iconHTML

    Optimal context quantization with respect to the minimum conditional entropy (MCECQ) is proven to be an efficient way for high order statistical modeling and model complexity reduction in data compression systems. The MCECQ merges together contexts that have similar statistics to reduce the size of the original model. In this technique, the number of output clusters (the model size) must be set be... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Classification with reject option in text categorisation systems

    Publication Year: 2003, Page(s):582 - 587
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (239 KB) | HTML iconHTML

    The aim of this paper is to evaluate the potential usefulness of the reject option for text categorisation (TC) tasks. The reject option is a technique used in statistical pattern recognition for improving classification reliability. Our work is motivated by the fact that, although the reject option proved to be useful in several pattern recognition problems, it has not yet been considered for TC ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pattern spaces from graph polynomials

    Publication Year: 2003, Page(s):480 - 485
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (561 KB) | HTML iconHTML

    Although graph structures have proved useful in high level vision for object recognition and matching, they can prove computationally cumbersome because of the need to establish reliable correspondences between nodes. Hence, standard pattern recognition techniques cannot be easily applied to graphs since feature vectors are not easily constructed. To overcome this problem, we turn to the spectral ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Hough transform-based method for radial lens distortion correction

    Publication Year: 2003, Page(s):182 - 187
    Cited by:  Papers (12)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (755 KB) | HTML iconHTML

    The paper presents an approach for a robust (semi-)automatic correction of radial lens distortion in images and videos. This method, based on the Hough transform, has the characteristics to be applicable also on videos from unknown cameras that, consequently, can not be a priori calibrated. We approximated the lens distortion by considering only the lower-order term of the radial distortion. Thus,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Revisiting image splitting

    Publication Year: 2003, Page(s):314 - 319
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (437 KB) | HTML iconHTML

    The paper presents a modified version of the classical split and merge algorithm (Horowitz, S. and Pavlidis, T., 1976). Instead of performing a regular decomposition of the image, it relies on a split at an optimal position that makes a good interregion separation. The implementation of the algorithm uses an initial image preprocessing to speed-up computation. Experimental results show that the nu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Complementary features combined in an HMM-based system to recognize handwritten digits

    Publication Year: 2003, Page(s):670 - 675
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (246 KB) | HTML iconHTML

    We combine complementary features based on foreground and background information in an HMM-based classifier to recognize handwritten digits. A zoning scheme based on column and row models provides a way of dividing the digit into zones without making the features size variant. This strategy allows us to avoid the digit normalization, while it provides a way of having information from specific zone... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Camera calibration and 3D reconstruction using interval analysis

    Publication Year: 2003, Page(s):374 - 379
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (300 KB) | HTML iconHTML

    The paper deals with the problem of error estimation in 3D reconstruction. It shows how interval analysis can be used in this way for 3D vision applications. The description of an image point by an interval assumes an unknown but bounded localization. We present a new method based on interval analysis tools to propagate this bounded uncertainty. This way of computation can produce guaranteed resul... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A complete and stable set of affine-invariant Fourier descriptors

    Publication Year: 2003, Page(s):578 - 581
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (660 KB) | HTML iconHTML

    We propose here a study of a new affine-invariant Fourier descriptors (Ghorbel (1998)) which are computed on the projection of a given curve that is assumed to be evolving on three dimensional space and supposed to be far enough from the camera. This set of descriptors is compared to the well known affine curvature. These invariants satisfy the completeness and stability properties. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Resolution conversion of gray-level images by discrete geometry

    Publication Year: 2003, Page(s):542 - 547
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1209 KB) | HTML iconHTML

    We propose a superresolution process for gray-level images based on a resolution-conversion method for discrete terrain in a space. With our resolution-conversion method, sampling a terrain and expressing it as a discrete surface allows us to estimate an original surface from a low-resolution one applying the resolution-conversion method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Face recognition committee machines: dynamic vs. static structures

    Publication Year: 2003, Page(s):121 - 126
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3420 KB) | HTML iconHTML

    We propose a dynamic face recognition committee machine (DFRCM) consisting of five well-known state-of-the-art algorithms in this paper. In previous work, we have developed a static committee machine which outperforms all the individual algorithms in the experiments. However, the weight for each expert in the committee is fixed and cannot be changed once the system is trained. We propose a dynamic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An eigenvector method for shape-from-shading

    Publication Year: 2003, Page(s):474 - 479
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1682 KB) | HTML iconHTML

    We explore how spectral methods for graph seriation can be used to develop a new shape-from-shading algorithm. We characterise the field of surface normals using a transition matrix whose elements are computed from the sectional curvature between different image locations. We use a graph seriation method to define a curvature minimising surface integration path for the purposes of height reconstru... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.