Spatial Pyramid Mining For Logo Detection in Natural Scenes

Jim Kleban (1), Xing Xie (2), Wei-Ying Ma (2)

(1) University of California, Santa Barbara
ECE Department
kleban [at]

(2) Microsoft Research Asia
No. 49 Zhichun Road, Haidian District
Beijing, 100080, P. R. China
xingx, wyma [at]


This work introduces a novel data mining scheme, spatial pyramid mining, to discover association rules at multiple resolutions 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.
[PDF] [BibTex]
Jim Kleban, Xing Xie, Wei-Ying Ma,
Proc. IEEE International Conference on Multimedia and Expo (ICME), Hannover, Germany, Jun. 2008.
Node ID: 509 , DB ID: 316 , Lab: VRL , Target: Conference
Subject: [Multimedia Database Mining] « Look up more