Francesco Setti
ABSTRACT
Several branches of computer vision heavily rely (but we could even say depend) on the availability of large datasets of labelled images. While such labeling is usually done by hand, a powerful help can be obtained from Internet and its related tools. In this paper we address the problem of automatically generating a set of images representing an object class, given the name of the class. We exploit semantic technologies, such as lexical resources and ontologies, in order to improve the search performances by using a standard web search engine. We will also discuss an application to the automatic building of a training set for a classification framework. Preliminary experiments are provided for 10 classes from the public CalTech256 dataset and results show an average increment in classification accuracy of about 10%.
- K. Barnard, P. Duygulu, D. Forsyth, N. de Freitas, D. M. Blei, and M. I. Jordan. Matching words and pictures. Journal of Machine Learning Research, 3:1107--1135, 2003. Google Scholar
Digital Library
- T. L. Berg and D. A. Forsyth. Animals on the web. In CVPR, volume 2, pages 1463--1470, Washington, DC, USA, 2006. IEEE Computer Society. Google ScholarDigital Library
- R. C. Bunescu and R. J. Mooney. Multiple instance learning for sparse positive bags. In ICML, pages 105--112, New York, NY, USA, 2007. ACM. Google ScholarDigital Library
- P. Carbonetto, N. de Freitas, and K. Barnard. A statistical model for general contextual object recognition. In ECCV, volume 3021 of Lecture Notes in Computer Science, pages 350--362. Springer Berlin Heidelberg, 2004.Google Scholar
- Y. Chen, X. S. Zhou, and T. Huang. One-class svm for learning in image retrieval. In ICIP, volume 1, pages 34--37, 2001.Google Scholar
- B. Collins, J. Deng, K. Li, and L. Fei-Fei. Towards scalable dataset construction: An active learning approach. In ECCV, pages 86--98, Berlin, Heidelberg, 2008. Springer-Verlag. Google ScholarDigital Library
- G. Csurka, C. R. Dance, L. Fan, J. Willamowski, and C. A. Bray. Visual categorization with bags of keypoints. In ECCV workshop, pages 1--22, 2004.Google Scholar
- C. Fellbaum. WordNet: An Electronic Lexical Database (Language, Speech, and Communication). The MIT Press, 1998.Google Scholar
- C. Fellbaum. Wordnet and wordnets. In K. Brown, editor, Encyclopedia of Language and Linguistics, pages 665--670, Oxford, 2005. Elsevier.Google Scholar
- R. Fergus, L. Fei-Fei, P. Perona, and A. Zisserman. Learning object categories from internet image searches. Internet Vision, 98(8):1453--1466, 2010.Google Scholar
- G. Griffin, A. Holub, and P. Perona. Caltech-256 object category dataset. Technical Report CNS-TR-2007-001, California Institute of Technology, 2007.Google Scholar
- N. Guarino and C. Welty. An overview of ontoclean. In S. Staab and R. Studer, editors, Handbook on Ontologies, International Handbooks on Information Systems, pages 201--220. Springer Berlin Heidelberg, 2009.Google Scholar
- S. Helmer, D. Meger, P. Viswanathan, S. McCann, M. Dockrey, P. Fazli, T. Southey, M. Muja, M. Joya, L. Jim, D. G. Lowe, and A. K. Mackworth. Semantic robot vision challenge: Current state and future directions. In IJCAI workshop, 2009.Google Scholar
- L.-J. Li and L. Fei-Fei. Optimol: Automatic online picture collection via incremental model learning. Int. J. Comput. Vis., 88(2):147--168, 2010. Google ScholarDigital Library
- D. G. Lowe. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis., 60(2):91--110, 2004. Google ScholarDigital Library
- C. Masolo, S. Borgo, A. Gangemi, N. Guarino, and A. Oltramari. Wonderweb deliverable d18. Technical report, CNR, 2003.Google Scholar
- Princeton University. Wordnet online. http://wordnet.princeton.edu/, May 2010.Google Scholar
- F. Schroff, A. Criminisi, and A. Zisserman. Harvesting image databases from the web. In ICCV, 2007.Google ScholarCross Ref
- A. T. Setz and C. G. M. Snoek. Can social tagged images aid concept-based video search? In ICME, pages 1460--1463, Piscataway, NJ, USA, 2009. IEEE Press. Google ScholarDigital Library
- A. Ulges, C. Schulze, M. Koch, and T. M. Breuel. Learning automatic concept detectors from online video. Comput. Vis. Image Underst., 114(4):429--438, 2010. Google ScholarDigital Library
- S. Vijayanarasimhan and K. Grauman. Keywords to visual categories: Multiple-instance learning forweakly supervised object categorization. In CVPR, 2008.Google ScholarCross Ref
Index Terms
- "Tell me more": how semantic technologies can help refining internet image search
Recommendations
Towards Foundational SemanticsOntological Semantics Revisited
Proceedings of the 2006 conference on Formal Ontology in Information Systems: Proceedings of the Fourth International Conference (FOIS 2006)In line with Nirenburg and Raskin's paradigm of ontological semantics, we adhere to the basic tenet that natural language semantics needs to be captured with respect to an explicitly formalized ontology. Many researchers in computational semantics, ...
Using SPARQL to query bioportal ontologies and metadata
ISWC'12: Proceedings of the 11th international conference on The Semantic Web - Volume Part IIBioPortal is a repository of biomedical ontologies--the largest such repository, with more than 300 ontologies to date. This set includes ontologies that were developed in OWL, OBO and other languages, as well as a large number of medical terminologies ...
A web-centric semantic mediation approach for spatial information systems
Semantics-related issues are at the heart of web-centric information systems and emerging spatial applications that require an integrated access to collections of heterogeneous data sources. We present an ontology-based semantic mediation approach and ...
Comments