Main Menu

Home
Coordination
Research & Integration
Dissemination
Community
News
Events
Links

Workpackages

WP2: Evaluation, Integration and Standards
WP3: Visual Content Indexing
WP4: Content Description for Audio, Speech and Text
WP5: Multimodal Processing and Interaction
WP6: Machine Learning and Computation Applied to Multimedia
WP7: Dissemination towards Industry


Logo IST
Home arrow Research & Integration arrow Overview arrow Choosing Features for CBIR and Automated Image Annotation

Choosing Features for CBIR and Automated Image Annotation

Contact person: Allan Hanbury (TU Vienna -PRIP)
Synopsis:
In this e-team, we will work on:

  • Feature extraction and selection for CBIR and image annotation.
  • CBIR using Baysian methods operating on well-chosen features. 
  • Automated image annotation. 
This E-team covers topics from a number of workpackages, namely:
  • WP5: Segmentation and feature extraction. 
  • WP8: Feature selection and learning based on the features extracted. 
  • WP3: Creation of ground truth to test the developed algorithms. 
  • WP7: Because some of the algorithms are certainly computationally intensive.

The aim is to unite people who have expertise in image segmentation and feature extraction with those with expertise in machine learning. As an initial task, we will be working on the recognition of animals in images.
Keywords:

  • CBIR, image annotation

Additonal info: E-Team's webpage