Title: An Image Matching Using Critical-Point Filters and Level Set Analysis
Authors: Thanasoontornlerk, Kittipong
Kanongchaiyos, Pizzanu
Citation: WSCG '2007: Short Communications Proceedings: The 15th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision 2007 in co-operation with EUROGRAPHICS: University of West Bohemia, Plzen, Czech Republic, January 29 – February 1, 2007, p. 191-198.
Issue Date: 2007
Publisher: Václav Skala - UNION Agency
Document type: konferenční příspěvek
URI: http://wscg.zcu.cz/wscg2007/Papers_2007/short/!WSCG2007_Short_Proceedings_Final-Part_2.zip
ISBN: 978-80-86943-02-2
Keywords: morfování obrazu;měření funkce;úrovňový set;filter kritických bodů
Keywords in different language: image morphing;feature measurement;level set;critical-point filter
Abstract: Critical-Point Filters (CPFs) are nonlinear filters which preserve intensity and location of each critical point in the image and reduce the resolution without any prior knowledge. Although CPFs can avoid blurred intensity and ambiguous location problem of previous linear filters, its computational cost is still expensive due to its complexity. We propose an enhancement of the CPFs algorithm for image matching using level set analysis. An image is analyzed and transformed to hierarchical level sets of pixel having same intensity. Connectivity of the level sets represents the image contrast invariant features. Between the corresponding level sets of the input images, two pixels are mapped based on their energy and bijectivity conditions. Finally, less computational time with precise mapping is shown in the experimental result.
Rights: © Václav Skala - UNION Agency
Appears in Collections:WSCG '2007: Short Communications Proceedings

Files in This Item:
File Description SizeFormat 
Thanasoontornlerk.pdfPlný text522,84 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/11179

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.