ABSTRACT
We present a scalable logo recognition technique based on feature bundling. Individual local features are aggregated with features from their spatial neighborhood into bundles. These bundles carry more information about the image content than single visual words. The recognition of logos in novel images is then performed by querying a database of reference images.
We further propose a novel WGC-constrained RANSAC and a technique that boosts recall for object retrieval by synthesizing images from original query or reference images. We demonstrate the benefits of these techniques for both small object retrieval and logo recognition. Our logo recognition system clearly outperforms the current state-of-the-art with a recall of 83% at a precision of 99%.
- R. Arandjelovic and A. Zisserman. Multiple queries for large scale specific object retrieval. In BMVC, 2012.Google ScholarCross Ref
- R. Arandjelovic and A. Zisserman. Three things everyone should know to improve object retrieval. In CVPR, 2012. Google ScholarDigital Library
- Y. Cao, C. Wang, Z. Li, and L. Zhang. Spatial-bag-of-features. In CVPR, 2010.Google ScholarCross Ref
- O. Chum, M. Perdoch, and J. Matas. Geometric min-Hashing: Finding a (thick) needle in a haystack. In CVPR, 2009.Google ScholarCross Ref
- O. Chum, J. Philbin, and A. Zisserman. Near duplicate image detection: min-hash and tf-idf weighting. In BMVC, 2008.Google ScholarCross Ref
- H. Jégou, M. Douze, and C. Schmid. Improving Bag\allowbreak-of-Features for Large Scale Image Search. IJCV, 2009.Google Scholar
- H. Jegou, M. Douze, and C. Schmid. On the burstiness of visual elements. In CVPR, 2009.Google ScholarCross Ref
- H. Jegou, M. Douze, and C. Schmid. Packing bag-of-features. In ICCV, 2009.Google ScholarCross Ref
- K. Lebeda, J. Matas, and O. Chum. Fixing the Locally Optimized RANSAC. In BMVC, 2012.Google ScholarCross Ref
- D. Lee, Q. Ke, and M. Isard. Partition Min-Hash for Partial Duplicate Image Discovery. ECCV, 2010. Google ScholarDigital Library
- J. Morel and G. Yu. ASIFT: A New Framework for Fully Affine Invariant Image Comparison. SIAM, 2009. Google ScholarDigital Library
- M. Muja and D. Lowe. Fast approximate nearest neighbors with automatic algorithm configuration. In VISAPP, 2009.Google Scholar
- J. Philbin, O. Chum, M. Isard, J. Sivic, and A. Zisserman. Object retrieval with large vocabularies and fast spatial matching. In CVPR, 2007.Google ScholarCross Ref
- J. Revaud, C. Schmid, M. Douze, and C. Schmid. Correlation-Based Burstiness for Logo Retrieval. In ACM MM, 2012. Google ScholarDigital Library
- S. Romberg, M. August, C. X. Ries, and R. Lienhart. Robust Feature Bundling. In LNCS, 2012. Google ScholarDigital Library
- S. Romberg, L. Garcia Pueyo, R. Lienhart, and R. van Zwol. Scalable Logo Recognition in Real-World Images. In ICMR, 2011. Google ScholarDigital Library
- J. Sivic and A. Zisserman. alebox.85{1.0}Video Google: a text retrieval approach to object matching in videos. ICCV, 2003. Google ScholarDigital Library
- Z. Wu, Q. Ke, M. Isard, and J. Sun. Bundling features for large scale partial-duplicate web image search. In CVPR, 2009.Google Scholar
Index Terms
- Bundle min-hashing for logo recognition
Recommendations
Scalable logo recognition in real-world images
ICMR '11: Proceedings of the 1st ACM International Conference on Multimedia RetrievalIn this paper we propose a highly effective and scalable framework for recognizing logos in images. At the core of our approach lays a method for encoding and indexing the relative spatial layout of local features detected in the logo images. Based on ...
A Fast Logo Recognition Algorithm in Noisy Document Images
ICBMI '11: Proceedings of the 2011 International Conference on Intelligent Computation and Bio-Medical InstrumentationLogo recognition is one of the applied aspects of graphic recognition domain. In most of document images, some diverse conditions such as noise existence, occlusion, and different scale/orientation may affect logo recognition process. In this paper, a ...
A Complete Logo Detection/Recognition System for Document Images
SBES '13: Proceedings of the 2013 27th Brazilian Symposium on Software EngineeringIn this paper, a complete logo detection/ recognition system for document images is proposed. In the proposed system, first, a logo detection method is employed to detect a few regions of interest (logo-patches), which likely contain the logo(s), in a ...
Comments