Paper Info
Title
Spatial pyramid mining for logo detection in natural scenes
Abstract
This work introduces a novel data mining scheme, spatial pyramid mining, to discover association rules at multiple res- olutions in order to identify frequent spatial configurations of local features that correspond to classes of logos appearing in real world scenes. By indexing representative examples by the mined rules we can efficiently detect a variety of different lettering or design marks associated with a brand. Features in an image are marked by matching rules to representative examples selected via a weighted cosine similarity measure. Logos are localized in an image via density-based clustering of matched features. Precision vs. recall curves are presented for experiments on a dataset of web images of nearly 1,000 images containing seven popular logo types.
Year
DOI
Venue
2008
10.1109/ICME.2008.4607625
Hannover
Keywords
Field
DocType
mobile search,object detection,index terms— data mining,logo recognition,feature extraction,association rule,indexation,indexing terms,spatial resolution,data mining,indexing,association rules,image resolution
Computer vision,Object detection,Pattern recognition,Cosine similarity,Computer science,Search engine indexing,Logo,Feature extraction,Association rule learning,Artificial intelligence,Pyramid,Cluster analysis
Conference
ISBN
Citations 
PageRank 
978-1-4244-2571-6
37
1.42
References 
Authors
14
3
Name
Order
Citations
PageRank
Jim Kleban11989.81
Xing Xie29105527.49
Wei-ying Ma3145871003.11