Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.14365/3823
Title: SymPaD: Symbolic patch descriptor
Authors: Aslan S.
Akgül C.B.
Sankur B.
Tunalı, Turhan
Keywords: Image feature
Image understanding
Model-driven visual dictionary
Object recognition
Primitive structures of natural images
Image understanding
Mathematical transformations
Object recognition
Geometrical shapes
Image features
Local image descriptors
Natural images
Probability vector
Rotation invariant
Transformation types
Visual dictionaries
Pixels
Publisher: SciTePress
Abstract: We propose a new local image descriptor named SymPaD for image understanding. SymPaD is a probability vector associated with a given image pixel and represents the attachment of the pixel to a previously designed shape repertoire. As such the approach is model-driven. The SymPad descriptor is illumination and rotation invariant, and extremely flexible on extending the repertoire with any parametrically generated geometrical shapes and any desired additional transformation types. Copyright © 2015 SCITEPRESS - Science and Technology Publications All rights reserved.
Description: Institute for Systems and Technologies of Information, Control and Communication (INSTICC)
10th International Conference on Computer Vision Theory and Applications, VISAPP 2015 -- 11 March 2015 through 14 March 2015 -- 112690
URI: https://doi.org/10.5220/0005361802660271
https://hdl.handle.net/20.500.14365/3823
ISBN: 9.7899E+12
Appears in Collections:Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Files in This Item:
File SizeFormat 
2906.pdf398.03 kBAdobe PDFView/Open
Show full item record



CORE Recommender

SCOPUSTM   
Citations

3
checked on Nov 20, 2024

Page view(s)

72
checked on Nov 25, 2024

Download(s)

22
checked on Nov 25, 2024

Google ScholarTM

Check




Altmetric


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