Title: | Image Edge Detection in a Mimic Spiral Architecture |
Authors: | Wu, Quiang Hintz, Tom He, Xiangjian |
Citation: | WSCG '2001: Conference proceedings: The 9-th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision 2001: University of West Bohemia, Plzen, Czech Republic, February 5.-9., 2001, p. 320-327. |
Issue Date: | 2001 |
Publisher: | University of West Bohemia |
Document type: | konferenční příspěvek conferenceObject |
URI: | http://wscg.zcu.cz/wscg2001/Papers_2001/R129.ps.gz http://hdl.handle.net/11025/11285 |
ISBN: | 80-7082-713-0 |
ISSN: | 1213-6972 |
Keywords: | detekce hran;počítačové vidění;spirálová architektura;zpracování obrazu |
Keywords in different language: | edge detection;computer vision;spiral architecture;image processing |
Abstract: | Detection of edge points of 3-dimensional physical objects in a 2-dimensional image is one of the main research areas of computer vision. Object contour detection and object recognition rely heavily on edge detection. In this paper, we present an edge detection scheme using Gaussian Multi-resolution Theory based on a mimic Spiral Architecture. The Spiral Architecture has been described in many papers. Although it has many ad-vantages such as powerful computational features in image processing especially in image edge detection, there is no available image capture device yet to support this structure. Hence, we mimic the Spiral Architecture from the existing image structure. This mimic structure inherits all computational features of the Spiral Architecture. The Gaussian Multi-resolution Theory is used to reduce noise and unnecessary details of the image. |
Rights: | © University of West Bohemia |
Appears in Collections: | WSCG '2001: Conference proceedings |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Wu.pdf | Plný text | 1,24 MB | Adobe PDF | View/Open |
Wu.ps | Plný text | 3,06 MB | Postscript | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/11285
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.