Texture frame curves and regions of attention using adaptive non-cartesian networks

J. R.Serra Alvarez, J. Brian Subirana-Vilanova

    Research output: Contribution to journalArticleResearchpeer-review

    7 Citations (Scopus)

    Abstract

    This paper addresses the problem of locating and extracting frame curves in images with complex backgrounds. Frame curves are virtual image curves which lie along "the center" of texture boundaries. They can be used to carry out other visual tasks or to lead to subsequent processing such as recognition, indexing or image retrieval. We present an approach based on dynamic programming and adaptive non-cartesian networks (Script A sign script N script C sign script N). Script A sign script N script C sign script N are based on line placement using a distribution function adapted to the image texture. We present a computational scheme to extract frame curves directly from the image and we provide the results of several experiments on real images. © 1999 Published by Elsevier Science Ltd on behalf of the Pattern Recognition Society. All rights reserved.
    Original languageEnglish
    Pages (from-to)503-515
    JournalPattern Recognition
    Volume32
    Issue number3
    DOIs
    Publication statusPublished - 1 Jan 1999

    Keywords

    • Dynamic programming
    • Non-cartesian networks
    • Object detection
    • Region of attention
    • Texture-based segmentation
    • Young filters

    Fingerprint Dive into the research topics of 'Texture frame curves and regions of attention using adaptive non-cartesian networks'. Together they form a unique fingerprint.

    Cite this