J. de la Calleja, O. Fuentes, and A. López-López (Mexico)
image analysis, principal component analysis, information retrieval
We describe an approach to perform content-based retrieval on a database of astronomical images. The method first employs image processing to normalize the images, elimi nating the effects of orientation and scale, then it performs principal component analysis to reduce the dimensionality of the data, and finally, retrieval is done using the near est neighbors algorithm. The approach has been tested on a collection of 309 images of galaxies of different types, with varying intensities, positions and orientations, yield ing very good results.
Important Links:
Go Back
