Paper Info
Title
Object matching based on partition information
Abstract
This paper presents a new technique for object matching that exploits the information about transitions in the image obtained by means of a segmentation approach. Object matching is performed by comparing a transformed version of an object shape model (reference contour) to the contours in the image partition. The comparison is based on a distance map that measures the Euclidean distance between any point in the image to the partition contours. Examples using parametric and non-parametric reference contours are provided to assess the quality of the proposed technique.
Year
DOI
Venue
2002
10.1109/ICIP.2002.1040079
Image Processing. 2002. Proceedings. 2002 International Conference  
Keywords
Field
DocType
edge detection,image matching,image segmentation,object recognition,Euclidean distance,distance map,image partition,image segmentation,image transitions,nonparametric reference contours,object matching,object shape model,parametric reference contours,partition contours,partition information,reference contour
Computer vision,Object detection,Pattern recognition,Segmentation,Computer science,Edge detection,Euclidean distance,Image processing,Image segmentation,Distance transform,Artificial intelligence,Cognitive neuroscience of visual object recognition
Conference
Volume
ISSN
Citations 
2
1522-4880
2
PageRank 
References 
Authors
0.58
4
3
Name
Order
Citations
PageRank
Ferran Marqués173867.44
Montse Pardàs234335.03
Ramon Morros3282.87