Please use this identifier to cite or link to this item:
Title: Curve description by histograms of tangent directions
Authors: Köksal, Ali
Özuysal, Mustafa
Keywords: Image classification
Feature extraction
Gradient methods
Textural cues
Embedded vision applications
Nearest neighbour classification
Issue Date: 2019
Publisher: Institution of Engineering and Technology
Abstract: The authors propose a novel approach for the description of objects based on contours in their images using real-valued feature vectors. The approach is particularly suitable when objects of interest have high contrast and texture-free images or when the texture variations are high so textural cues are nuisance factors for classification. The proposed descriptor is suitable for nearest neighbour classification still popular in embedded vision applications when the power considerations outweigh the performance requirements. They describe object outlines purely based on the histograms of contour tangent directions mimicking many of the design heuristics of texture-based descriptors such as scale-invariant feature transform (SIFT). However, unlike SIFT and its variants, the proposed approach is directly designed to work with contour data and it is robust to variations inside and outside the object outline as well as the sampling of the contour itself. They show that relying on tangent direction estimation as opposed to gradient computation yields a more robust description and higher nearest neighbour classification rates in a variety of classification problems.
ISSN: 1751-9632
Appears in Collections:Computer Engineering / Bilgisayar Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Files in This Item:
File SizeFormat 
IET Computer Vision.pdf2.21 MBAdobe PDFView/Open
Show full item record

CORE Recommender

Google ScholarTM



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