Semantic knowledge construction from annotated image collections
- 25 June 2003
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 205-208
- https://doi.org/10.1109/icme.2002.1035549
Abstract
This paper presents new methods for extracting semantic knowledge from collections of annotated images. The proposed methods include novel automatic techniques for extracting semantic concepts by disambiguating the senses of words in the annotations using the lexical database WordNet, and both the images and their annotations, and for discovering semantic relations among the detected concepts based on WordNet. Another contribution of this paper is the evaluation of several techniques for visual feature descriptor extraction and data clustering in the extraction of semantic concepts. Experiments show the potential of integrating the analysis of both images and annotations for improving the performance of the word-sense disambiguation process. In particular, the accuracy improves 4- 15% with respect to the baselines systems for nature images.Keywords
This publication has 9 references indexed in Scilit:
- Perceptual knowledge construction from annotated image collectionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- IMKAPublished by Association for Computing Machinery (ACM) ,2001
- Data clusteringACM Computing Surveys, 1999
- A method for word sense disambiguation of unrestricted textPublished by Association for Computational Linguistics (ACL) ,1999
- General Word Sense Disambiguation Method Based on a Full Sentential ContextJournal of Natural Language Processing, 1998
- WordNetCommunications of the ACM, 1995
- Unsupervised word sense disambiguation rivaling supervised methodsPublished by Association for Computational Linguistics (ACL) ,1995
- Improving the retrieval of information from external sourcesBehavior Research Methods, Instruments & Computers, 1991
- Indexing by latent semantic analysisJournal of the American Society for Information Science, 1990