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. 

• 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