PUMA
Istituto di Scienza e Tecnologie dell'Informazione     
Yang S., Li Y., Kuruoglu E. E. Scale invariant feature detection for object recognition in colour images. Technical report, 2012.
 
 
Abstract
(English)
This paper presents a method for extracting features from color images that can be used to perform reliable matching between different views of an object or scene. We extend the concept of the feature vector given in Lowe's method to color images by defining new gradient operator or giving new feature descriptor, which result in different algorithms with different optimality in the sense of information utilization of the original color image. Generally, better algorithm optimality is coupled with higher computation complexity, which is the case in this paper. Thus, the 4 methods proposed in this paper lead to a multi-optimality and multi-complexity scheme. In practice, people can choose which method to use according to their needs and computation abilities.
Subject Feature detection
Color image
SIFT (shift invariant feature transform)
I.5.4 PATTERN RECOGNITION. Applications
I.4.8 Scene Analysis. Object recognition
62H35 Image analysis


Icona documento 1) Download Document PDF


Icona documento Open access Icona documento Restricted Icona documento Private

 


Per ulteriori informazioni, contattare: Librarian http://puma.isti.cnr.it

Valid HTML 4.0 Transitional