Using Relevance Feedback in Retrieving Auroral Images

M.T. Syrjäsuo and E.F. Donovan (Canada)


Geosciences, pattern recognition, machine vision, content based image retrieval


In modern space physics research, digital imagers are widely utilised in studies of the near-Earth space envir onment. The physical process being directly observed is the aurora, and millions of auroral images are acquired an nually. These data sets provide a wealth of opportunities for developing and testing content-based image retrieval (CBIR) techniques with the irregular natural shapes occur ring in auroral displays. Our CBIR implementation with relevance feedback was used in searching for one rare au roral form (”North-South structure”) that is a manifesta tion of an important physical process of general interest to space physics researchers today. We finish with a brief dis cussion of important benefits of anticipated application of this technique to multi-terabyte multi-million auroral im age data sets.

Important Links:

Go Back