Loading...

Unsupervised estimation of conceptual classes for semantic image annotation

Teimoori, F ; Sharif University of Technology | 2011

1111 Viewed
  1. Type of Document: Article
  2. Publisher: 2011
  3. Abstract:
  4. A probabilistic formulation for semantic image annotation and retrieval is proposed. Annotation and retrieval are posed as classification problems where each class is defined as the group of database images labeled with a common semantic label. It is shown that, by establishing this one-to-one correspondence between semantic labels and semantic classes, a minimum probability of error annotation and retrieval are feasible with algorithms that are 1) conceptually simple and 2) computationally efficient. In this article, a content-based image retrieval and annotation architecture is proposed. Its attitude is decreasing the semantic gap by partitioning the image to its semantic regions and using color and texture feature of these regions to build a feature database. The partiotioning is done by both Gaussian mixture model and self-organizing neural networks
  5. Keywords:
  6. Content-based image annotation ; Color and texture features ; Computationally efficient ; Content based image retrieval ; Database images ; Feature database ; Gaussian Mixture Model ; Image annotation ; Minimum probability of error ; Probabilistic formulation ; Self-organizing neural network ; Semantic class ; Semantic gap ; Semantic image annotation ; Semantic images ; Semantic labels ; Electrical engineering ; Image analysis ; Image retrieval ; Neural networks ; Object recognition ; Semantics ; Search engines
  7. Source: 2011 19th Iranian Conference on Electrical Engineering, ICEE 2011, 17 May 2011 through 19 May 2011 ; May , 2011 ; 9789644634284 (ISBN)
  8. URL: http://www.civilica.com/EnPaper--ICEE19_306.html