Proceedings 11th International Conference on Image Analysis and Processing

26-28 Sept. 2001

Filter Results

Displaying Results 1 - 25 of 103
  • Proceedings 11th International Conference on Image Analysis and Processing

    Publication Year: 2001
    Request permission for commercial reuse | PDF file iconPDF (388 KB)
    Freely Available from IEEE
  • Automatic character location and segmentation in color scene images

    Publication Year: 2001, Page(s):2 - 7
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (675 KB) | HTML iconHTML

    This paper describes a connected component (CC)-based approach to automatic text location and segmentation in natural scene images. A multi-group decomposition scheme is used to deal with the complexity of the color background. Connected component extraction is implemented using the block adjacency graph (BAG) algorithm after noise filtering and runlength smearing (RLS) operation. Some heuristic f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Lip detection and tracking

    Publication Year: 2001, Page(s):8 - 13
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (778 KB) | HTML iconHTML

    Seeing the talker's lips in addition to audition can improve speech understanding which is rather based on lip shape temporal evolution than on absolute mouth shape. We propose a totally automatic algorithm which can extract lip shape over an image sequence. The algorithm does not require any make-up or markers and works under natural lighting conditions. The lip detection algorithm uses an active... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition of shape-changing hand gestures based on switching linear model

    Publication Year: 2001, Page(s):14 - 19
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (762 KB) | HTML iconHTML

    We present a method to track and recognise shape-changing hand gestures simultaneously. The switching linear model using the active contour model corresponds well to temporal shapes and motions of hands. Inference in the switching linear model is computationally intractable and therefore the learning process cannot be performed via the exact EM (expectation maximization) algorithm. However, we pre... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 2D shape recognition by hidden Markov models

    Publication Year: 2001, Page(s):20 - 24
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (404 KB) | HTML iconHTML

    In computer vision, two-dimensional shape classification is a complex and well-studied topic, often basic for three-dimensional object recognition. Object contours are a widely chosen feature for representing objects, useful in many respects for classification problems. We address the use of hidden Markov models (HMM) for shape analysis, based on chain code representation of object contours. HMM r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian face recognition with deformable image models

    Publication Year: 2001, Page(s):26 - 35
    Cited by:  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1119 KB) | HTML iconHTML

    We propose a novel representation for characterizing image differences using a deformable technique for obtaining pixel-wise correspondences. This representation, which is based on a deformable 3D mesh in XYI-space, is then experimentally compared with two related correspondence methods: optical flow and intensity differences. Furthermore, we make use of a probabilistic similarity measure for dire... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spatial clustering of pixels in the mouth area of face images

    Publication Year: 2001, Page(s):36 - 41
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (605 KB) | HTML iconHTML

    We propose a method of image segmentation using a Gaussian mixture model of the colour image histogram. The model construction is based on the model validation philosophy of architecture selection (Kittler et al., 2001). In contrast with the k-means clustering approach, the number of segments in the proposed scheme is determined completely automatically. We show that the modelling method can be st... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Eigenspace-based recognition of faces: comparisons and a new approach

    Publication Year: 2001, Page(s):42 - 47
    Cited by:  Papers (10)  |  Patents (44)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (521 KB) | HTML iconHTML

    Different eigenspace-based approaches have been proposed for the recognition of faces. They differ mostly in the kind of projection method used and in the similarity matching criterion employed. A first goal of this paper is to present a comparison between some of these different approaches. A second goal is to outline an adaptive, neural-based security access control system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integrated 2D and 3D images for face recognition

    Publication Year: 2001, Page(s):48 - 53
    Cited by:  Papers (6)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (616 KB) | HTML iconHTML

    This paper presents a feature-based face recognition system based on both 3D range data as well as 2D gray-level facial images. Ten 2D feature points and four 3D feature points are designed to be robust against changes of facial expressions and viewpoints and are described by Gabor filter responses in the 2D domain and point signature in the 3D domain. Localizing feature points in a new facial ima... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature based merging of application specific regions

    Publication Year: 2001, Page(s):56 - 62
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (699 KB) | HTML iconHTML

    Over-segmentation is a common problem for all kinds of segmentation tasks. Automated segmentation of natural scenes is no exception. This paper proposes a solution to the over-segmentation problem, with the emphasis on satellite images of farmland. In many cases, an agricultural field can be considered as a flat region having a rather large area, a compact shape, and straight region boundaries bec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Maximum likelihood motion segmentation using eigendecomposition

    Publication Year: 2001, Page(s):63 - 68
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (630 KB) | HTML iconHTML

    This paper presents an iterative maximum likelihood framework for motion segmentation. Our representation of the segmentation problem is based on a similarity matrix for the motion vectors for pairs of pixel blocks. By applying eigendecomposition to the similarity matrix, we develop a maximum likelihood method for grouping the pixel blocks into objects which share a common motion vector. We experi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Wavelet-based texture segmentation of remotely sensed images

    Publication Year: 2001, Page(s):69 - 74
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1190 KB) | HTML iconHTML

    A texture feature extraction scheme based on M-band wavelet packet frames is investigated. The features so extracted are used for segmentation of satellite images which usually have complex and overlapping boundaries. The underlying principle is based on the fact that different image regions exhibit different textures. Since most significant information of a texture often lies in the intermediate ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion detection with non-stationary background

    Publication Year: 2001, Page(s):78 - 83
    Cited by:  Papers (7)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (544 KB) | HTML iconHTML

    This paper proposes a new method for moving object (foreground) detection with non-stationary background using background subtraction. While background subtraction has traditionally worked well for stationary backgrounds, the same cannot be implied for a nonstationary viewing sensor. To a limited extent, motion compensation for non-stationary backgrounds can be applied, but in practice, it is diff... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysing and simplifying histograms using scale-trees

    Publication Year: 2001, Page(s):84 - 89
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (760 KB) | HTML iconHTML

    A new method for analysing image histograms is introduced. The technique decomposes a histogram into probability level sets. The relationships between these level sets are encoded using a tree. The tree has fewer nodes than the histogram and so is a compressed feature. When used in image retrieval experiments the tree is shown to have a performance that is superior to many methods and no worse tha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vanishing point detection: representation analysis and new approaches

    Publication Year: 2001, Page(s):90 - 94
    Cited by:  Papers (39)  |  Patents (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (659 KB) | HTML iconHTML

    We introduce two different representation approaches and propose two techniques to estimate the position of vanishing points in an image, one bused on a probabilistic strategy and the other focused on a deterministic analysis. Unlike most of the methods so far developed, which exploit the Gaussian sphere, the new techniques operate in the (/spl rho/, /spl theta/) polar parameter space and in the (... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fast recursive algorithm for the computation of axial moments

    Publication Year: 2001, Page(s):95 - 100
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (661 KB) | HTML iconHTML

    This paper describes a fast algorithm to compute local axial moments used for the detection of objects of interest in images. The basic idea is grounded on the elimination of redundant operations while computing axial moments for two neighboring angles of orientation. The main result is that the complexity of recursive computation of axial moments becomes independent of the total number of compute... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A modified fuzzy ART for image segmentation

    Publication Year: 2001, Page(s):102 - 107
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (688 KB) | HTML iconHTML

    This paper presents a clustering approach for image segmentation based on a modified fuzzy ART model. The goal of the proposed approach is to find a simple model able to instance a prototype for each cluster in order to avoid complex post-processing phases. Some results and comparisons with other models present in the literature, like SOM and original fuzzy ART are presented. Qualitative and quant... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time tracking and reproduction of 3D human body motion

    Publication Year: 2001, Page(s):108 - 112
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (522 KB) | HTML iconHTML

    Non-intrusive human body tracking is a key issue in advanced human-computer interaction, with key applications ranging from virtual reality to videoconferencing and telepresence. This paper describes a system for vision-based tracking of body posture. The system is explicitly designed to provide a robust yet simple and inexpensive solution to real-time body tracking through a careful choice of vis... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image segmentation for appearance-based self-localisation

    Publication Year: 2001, Page(s):113 - 118
    Cited by:  Papers (1)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1031 KB) | HTML iconHTML

    The paper describes a segmentation technique that well fits to an appearance-based self-localisation. In an appearance-based approach robot positioning is performed without using explicit object models. The choice of the representation of image appearances is fundamental. We use image-domain features, as opposed to interpreted characteristics of the scene, and we adopt feature vectors including bo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Circle detection based on orientation matching

    Publication Year: 2001, Page(s):119 - 124
    Cited by:  Papers (6)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (674 KB) | HTML iconHTML

    The paper reports a correlation-based method for the detection of circular objects which is capable of overcoming well-known problems arising by the use of gradient-based voting schemes. Specifically, the method is: (a) capable of detecting circular objects on the basis of both magnitude and direction of the image gradient; and (b) of dealing with three-dimensional spherical objects by considering... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Concurrent edge/region detection from a Peano scan

    Publication Year: 2001, Page(s):125 - 130
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (596 KB) | HTML iconHTML

    This paper deals with an adaptive sub-sampling process that is an example of a more general class of data processing. Our approach consists of spanning a Z-tree over the image. The Z-tree is the bin-tree built from the 1D pixel sequence obtained through a peculiar scan called the Peano traversal. A conditional rotation operator, defined to manipulate the Z-tree, supports the Peano scan adaption. I... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Increasing efficiency of Hausdorff approach for tracking real scenes with complex environments

    Publication Year: 2001, Page(s):131 - 136
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (696 KB) | HTML iconHTML

    Tracking moving objects based on a Hausdorff approach can be formulated in terms of a matching process between two sets of edge points extracted from the object model to be localized and the corresponding frame of the image sequence. However, no information about the global measures of the object feature positions has been considered to carry out the matching process through a search strategy. Thi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Remote sensed images segmentation through shape refinement

    Publication Year: 2001, Page(s):137 - 144
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (790 KB) | HTML iconHTML

    A novel approach to the automatic classification of remotely sensed images is proposed. This approach is based on a three-phase procedure: first pixels which belong to the areas of interest with large likelihood are selected as seeds; second the seeds are refined into connected shapes using two well-known image processing techniques; third the results of the shape refinement algorithms are merged ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Temporal filtering of disparity measurements

    Publication Year: 2001, Page(s):145 - 150
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (746 KB) | HTML iconHTML

    The paper proposes a temporal filtering technique for the disparity measurements generated by area-based stereo-matching algorithms. The technique improves temporal consistency of disparity measurements by reducing the matching errors due to noise affecting the imaging system. Moreover, the technique is capable of increasing the number of correct matches by locating uncertain measurements with a c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Clustering context properties of wavelet coefficients in automatic modelling and image coding

    Publication Year: 2001, Page(s):151 - 155
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (477 KB) | HTML iconHTML

    An algorithm for automatic modelling of wavelet coefficients from context properties is presented. The algorithm is used to implement an image coder, in order to demonstrate its image coding efficiency. The modelling of wavelet co-efficients is performed by partitioning the weighted context property space to regions. Each of the regions has a dynamic probability distribution stating the prediction... View full abstract»

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