Доступ предоставлен для: Guest
Портал Begell Электронная Бибилиотека e-Книги Журналы Справочники и Сборники статей Коллекции
Telecommunications and Radio Engineering
SJR: 0.202 SNIP: 0.2 CiteScore™: 0.23

ISSN Печать: 0040-2508
ISSN Онлайн: 1943-6009

Том 78, 2019 Том 77, 2018 Том 76, 2017 Том 75, 2016 Том 74, 2015 Том 73, 2014 Том 72, 2013 Том 71, 2012 Том 70, 2011 Том 69, 2010 Том 68, 2009 Том 67, 2008 Том 66, 2007 Том 65, 2006 Том 64, 2005 Том 63, 2005 Том 62, 2004 Том 61, 2004 Том 60, 2003 Том 59, 2003 Том 58, 2002 Том 57, 2002 Том 56, 2001 Том 55, 2001 Том 54, 2000 Том 53, 1999 Том 52, 1998 Том 51, 1997

Telecommunications and Radio Engineering

DOI: 10.1615/TelecomRadEng.v71.i17.50
pages 1575-1588


K. Perez-Daniel
National Polytechnic Institute, IPN, Mexico City
E. Escamilla Hernandez
National Polytechnic Institute, IPN, Mexico City
Mariko Nakano-Miyatake
National Polytechnic Institute, IPN, Mexico City
Hector Manuel Perez-Meana
National Polytechnic Institute of Mexico

Краткое описание

Most computer vision applications base their operation on the interest point detection. Therefore accurate interest point detection is essential for them. The detected interest points must be invariant to rotation, zoom, blur, illumination, changes of viewpoints, etc. This paper presents a novel image interest point detector, called Harris Atomic detector, which is based on the conventional Harris detector, but the Gaussian Function used in was replaced by an Atomic Function (AF) to improve the detection accuracy. In order to know which Atomic Function provides better results under different imaging conditions, a performance evaluation was done using several AFs. The main criterion used for the comparison was the invariance, in position and number, among the interest points detected in the first and the subsequent frames of a known image sequence. Evaluation results show that, although in general any atomic function improves the performance of conventional Harris detector, the up(x) AF provides best performance, with an improvement of about 10% on the interest point detection accuracy under rotation, blur, zoom and view point changes.

Ключевые слова: image point, Harris detector, atomic function