Paper Info
Title
Joining feature-based and similarity-based pattern description paradigms for object detection.
Abstract
In pattern recognition, two of the main paradigms for describing objects are the feature-based and the (dis)similarity-based one. The former aims at encoding tangible features that characterize the object per-se. The latter gives a relational description of the object, considering the similarities with other reference entities. In this paper, we propose the marriage between these two philosophies: this is possible by considering an object as described by its local parts. Actually, object parts can be described by features, and structural information can be extracted considering the similarities between parts. We cast our intuition in an object detection framework, where we select HOG as feature and simple euclidean distances for the similarity computation. The results show how this hybrid representation outperforms the single paradigms, demonstrating their complementarity.
Year
Venue
Keywords
2012
ICPR
feature extraction,image coding,object detection,Euclidean distances,HOG,feature-based pattern description paradigms,local parts,object detection,object parts,pattern recognition,similarity computation,similarity-based pattern description paradigms,structural information extraction,tangible feature encoding
Field
DocType
ISSN
Complementarity (molecular biology),Object detection,Computer vision,Viola–Jones object detection framework,3D single-object recognition,Pattern recognition,Feature (computer vision),Computer science,Object model,Feature extraction,Artificial intelligence,Euclidean geometry
Conference
1051-4651
Citations 
PageRank 
References 
3
0.41
0
Authors
5
Name
Order
Citations
PageRank
Samuele Martelli1314.77
M. Cristani21928109.03
Loris Bazzani3140452.36
Diego Tosato41656.58
Vittorio Murino53277207.20