Proceedings 15th International Conference on Pattern Recognition. ICPR-2000

3-7 Sept. 2000

Go

Filter Results

Displaying Results 1 - 25 of 205
  • Proceedings 15 Th International Conference On Pattern Recognition

    Publication Year: 2000, Page(s):1 - 18
    Request permission for reuse | PDF file iconPDF (707 KB)
    Freely Available from IEEE
  • Handwriting recognition-the last frontiers

    Publication Year: 2000, Page(s):1 - 10 vol.4
    Cited by:  Papers (10)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1049 KB)

    The last frontiers of handwriting recognition are considered to have started in the last decade of the second millennium. The paper summarizes (a) the nature of the problem of handwriting recognition, (b) the state of the art of handwriting recognition at the turn of the new millennium, and (c) the results of CENPARMI researchers in automatic recognition of handwritten digits, touching numerals, c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A methodology for special symbol recognitions

    Publication Year: 2000, Page(s):11 - 14 vol.4
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (389 KB)

    Presents a special symbol recognition system that incorporates the result of OCR to recognize the special symbols those nor handled by the current commercial OCR systems. Given a document image and the OCR output, we first refine the character coordinates produced by the OCR. Then, the special symbols are distinguished from the normal characters. Finally, we compute the features from the special s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic acquisition of context-based images templates for degraded character recognition in scene images

    Publication Year: 2000, Page(s):15 - 18 vol.4
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (518 KB)

    Proposes a method for adaptively acquiring templates for degraded characters in scene images. Characters in scene images are often degraded because of poor printing and viewing conditions. To cope with the degradation problem, we proposed the idea of "context-based image templates" which include neighboring characters of parts thereof and so represent more contextual information than single-letter... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Crisp and fuzzy evaluations and DP algorithms for dealing with extra ink in cursive handwriting recognition

    Publication Year: 2000, Page(s):19 - 22 vol.4
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (428 KB)

    In segmentation-by-recognition methods, words are recognised by searching for the aggregation of basic segments (strokes) that best matches one of the sequences of letters allowed by the lexicon. The presence of spurious strokes ("extra ink") impairs recognition, since they have to be associated anyway with some letter of the word. The paper describes how we solved this problem by properly definin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • IRIS an image recognition and interpretation system for the Dutch Postbank

    Publication Year: 2000, Page(s):23 - 26 vol.4
    Cited by:  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (355 KB)

    KPN Research has developed an all-purpose check recognition system for the Dutch Postbank. This image recognition and interpretation system (IRIS) is the result of more than thirty years of research and development and contains four major functionalities: (1) determination of the way a check is filled in; (2) recognition of the amount and account fields; (3) recognition of the postcode; and (4) si... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • OCR with no shape training

    Publication Year: 2000, Page(s):27 - 30 vol.4
    Cited by:  Papers (9)  |  Patents (8)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (423 KB)

    We present a document-specific OCR system and apply it to a corpus of fixed business letters. Unsupervised classification of the segmented character bitmaps on each page, using a "clump" metric, typically yields several hundred clusters with highly skewed populations. Letter identities are assigned to each cluster by maximizing matches with a lexicon of English words. We found that for 2/3 of the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Issues and directions in visual information retrieval

    Publication Year: 2000, Page(s):31 - 38 vol.4
    Cited by:  Papers (1)  |  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (835 KB)

    Visual information retrieval is attracting an increasing number of researchers from disparate fields, like image analysis, computer vision, databases, knowledge representation, artificial intelligence, man-machine interaction. Although a number of prototype systems have been made available, nevertheless this discipline has not yet reached a mature stage, and overall has not yet been credited as of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic video scene extraction by shot grouping

    Publication Year: 2000, Page(s):39 - 42 vol.4
    Cited by:  Papers (21)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (448 KB)

    For more efficient organizing, browsing, and retrieving digital video content, it is important to extract video structure information at both scene and shot levels. The paper presents an effective approach to video scene segmentation based on a pseudo-object-based shot correlation analysis. A measure of the semantic correlation of consecutive shots based on dominant color grouping and tracking is ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Locale-based visual object retrieval under illumination change

    Publication Year: 2000, Page(s):43 - 46 vol.4
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (704 KB)

    Providing a user with an effective image search engine has been a very active research area. A search by an object model is considered to be one of the most desirable and yet difficult tasks. An added difficulty is that objects can be photographed under different lighting conditions. We have developed a feature localization scheme that finds a set of locales in an image. We make use of a diagonal ... View full abstract»

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

    Publication Year: 2000, Page(s):47 - 50 vol.4
    Cited by:  Papers (7)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (551 KB)

    Color features are among the most important features used in image database retrieval, especially in cases where no additional semantic information is available. Due to its compact representation and low complexity, direct histogram comparison is the most commonly used technique in comparing color similarity of images. However, it has many serious drawbacks, including a high degree of dependency o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Processing pictorial queries with multiple instances using isomorphic subgraphs

    Publication Year: 2000, Page(s):51 - 54 vol.4
    Cited by:  Papers (3)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (390 KB)

    An algorithm is given for processing pictorial query specifications that consist of a query image and a similarity level that must hold between the query image and database images. The similarity level specifies the contextual similarity (how well the content of one image matches that of another) as well as the spatial similarity (the relative locations of the matching symbols in the two images). ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture similarity queries and relevance feedback for image retrieval

    Publication Year: 2000, Page(s):55 - 58 vol.4
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (660 KB)

    The measurement of perceptual similarities between textures is a difficult problem in applications such as image classification and image retrieval in large databases. Among the various texture analysis methods or models developed over the years, those based on a multi-scale multi-orientation paradigm seem to give more reliable results with respect to human visual judgement. This work introduces n... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On ridges and valleys [image registration]

    Publication Year: 2000, Page(s):59 - 66 vol.4
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1265 KB)

    Ridges and valleys are Earth's relief structures. They can have an imaging counterpart provided we model a digital image as a landscape by considering grey level values as height. These two dual entities have received comparatively little attention from the computer vision community with regard to other like edges or comets. In this paper, we first propose a taxonomy or classification of the sever... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient retrieval of deformed and occluded shapes

    Publication Year: 2000, Page(s):67 - 71 vol.4
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (432 KB)

    We propose an approach for matching deformed and occluded shapes using dynamic programming. Our algorithms handle noise and shape distortions by allowing matching of merged sequences of consecutive small segments in a shape, with larger segments of another shape, while being invariant to translation, scale and orientation transformations of shapes. We illustrate the effectiveness of our algorithms... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast tracking of ellipses using edge-projected integration of cues

    Publication Year: 2000, Page(s):72 - 75 vol.4
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (638 KB)

    Commercial applications of ellipse tracking require robustness and real-time capability. The method presented tracks ellipses at field rate using a Pentium PC. Robustness is obtained by integrating gradient and intensity values for the detection of contour edges and by using a RANSAC-like method to find the most likely ellipse. The method adapts to the appearance along the ellipse circumference an... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Features detection and navigation on neurovascular trees

    Publication Year: 2000, Page(s):76 - 79 vol.4
    Cited by:  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (444 KB)

    The 3D reconstruction of the cerebral vascular anatomy can greatly improve the diagnosis of vascular pathologies, such as embolisms and haemorrhages. This paper presents a new method for the automatic extraction of the blood vessels surface and the labelling of its features, specifically branching, aneurysms and stenoses. The method works with segmented magnetic resonance angiography images. It ex... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation of bone tumor in MR perfusion images using neural networks and multiscale pharmacokinetic features

    Publication Year: 2000, Page(s):80 - 83 vol.4
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (358 KB)

    The decrease in the volume of viable tumor is an indicator for the effect preoperative chemotherapy has on bone tumors. We develop an approach for segmenting dynamic perfusion MR-images into viable tumor, nonviable tumor and healthy tissue. Two cascaded feedforward neural networks are trained to perform the pixel-based segmentation. As features, we use the parameters obtained from a pharmacokineti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmenting at higher scales to classify at lower scales. A mathematical morphology based methodology applied to forest cover remote sensing images

    Publication Year: 2000, Page(s):84 - 87 vol.4
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (464 KB)

    A methodology based on mathematical morphology to classify forest cover types in remote sensing images is presented. The information automatically extracted at higher scales (aerial photographs) by morphological segmentation approaches is afterwards used to classify different forest cover types at lower scales (satellite images). In this methodology the spectral process is guided by the spatial pr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic recognition and reconstruction of the human heart

    Publication Year: 2000, Page(s):88 - 93 vol.4
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (704 KB)

    Medical imaging is constantly advancing due to technological improvements in both data gathering devices and data processing of their output. In this progress the heart presents special demands because of its incessant and brisk movement, and intrinsic characteristics. In this paper we briefly survey techniques that can be used to construct a three-dimensional model of a heart, and discuss our app... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D fundus pattern reconstruction and display from multiple fundus images

    Publication Year: 2000, Page(s):94 - 97 vol.4
    Cited by:  Papers (7)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (487 KB)

    This paper proposes a method to reconstruct and display 3D fundus (inner bottom of eye-ball) pattern from a set of multiple partial images of fundus. They were taken from several different view angles by shifting fundus camera. Since they are distorted by eye lens, a simple stereo technique does not work for the 3D reconstruction from any pair of images. Moreover, every fundus image's distortions ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A surveillance system integrating visual telepresence

    Publication Year: 2000, Page(s):98 - 101 vol.4
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (400 KB)

    We describe an indoor surveillance system which enables the control of a binocular active vision system by a remote operator wearing a head mounted display. Visual feedback to the head mounted display is obtained using the images captured by the active vision system. To maximize the 3D perception of the operator the system is able to adjust the vergence angle of the active vision system in order t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Production of video images by computer controlled camera operation based on distribution of spatiotemporal mutual information

    Publication Year: 2000, Page(s):102 - 105 vol.4
    Cited by:  Papers (8)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (539 KB)

    This paper defines a spatiotemporal mutual information on the pixels of a given video image on the basis of information theory (Shannon's communication theory), which can be interpreted as the theoretical estimation of interested features for human being. As an application of this spatiotemporal mutual information, we propose a method of producing a vivid video image of the distance learning by us... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Surface recovery from planar sectional contours

    Publication Year: 2000, Page(s):106 - 109 vol.4
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (462 KB)

    We propose an approach for surface recovery from planar sectional contours. The surface is reconstructed based on the so-called "equal importance criterion" which suggests that every point in the region contributes equally to the reconstruction process. The problem is then formulated in terms of a partial differential equation, and the solution is efficiently calculated from a distance transformat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • View synthesis from needle-maps

    Publication Year: 2000, Page(s):110 - 113 vol.4
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (426 KB)

    Investigates the use of shape from-shading for view synthesis. The aim of our study is to determine whether needle-maps delivered by a new shape-from-shading (SFS) algorithm can be used as a compact object representation. Specifically, we aim to show that the needle maps can be used to generate novel object views. To this end we conduct two sets of experiments. Firstly, we use the recovered needle... View full abstract»

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