Bradford Scholars -how to deposit your paper Overview Copyright check• Check if your publisher allows submission to a repository.• Use the Sherpa RoMEO database if you are not sure about your publisher's position or email openaccess@bradford.ac.uk.

Despite several decades of research and development in the field of pattern recognition, the general problem of recognizing complex patterns with arbitrary orientations, locations, and scales remains unsolved and normally is applied using iterative manual evaluation of the detection results. This problem is becoming increasingly important with the growing number of massive archives of solar images produced by instruments located at ground-based observatories and aboard current satellites such as YOHKOH, SOHO and TRACE, with future satellites such as SOLAR B, SDO and STEREO in prospect. The size of expected archives requires a new automated approach to digital image processing and data extraction with robust and efficient pattern recognition techniques to be developed and implemented. This review evaluates techniques for the standardisation in shape and intensity of solar images and summarises the existing manual and semi-automated feature recognition techniques applied to a representative range of solar features, including sunspots, filaments, active regions, flares, coronal mass ejections and magnetic neutral lines. The review also surveys the most recent fully-automated detection techniques developed for the creation of Solar Feature Catalogues of sunspots, active regions and filaments for the European Grid of Solar Observations. The survey is aimed to help researchers and students to learn about the recognition techniques applied to astrophysical images with different levels of noise and distortions and to work effectively with the Solar Feature Catalogue.

No abstract

We describe the automated extraction of active regions (ARs) or plages from the European Grid of Solar Observations (EGSO) Solar Feature Catalogue using a region-growing technique. In this work, Hα and Ca II K3 solar images from the Meudon Observatory and EUV solar images from the SOHO/EIT instrument were used. For better detection accuracy, the statistical properties of each quarter of a full disk solar image are used to define local intensity thresholds for an initial segmentation that helps to define AR seeds. Median filtering and morphological operations are applied to the resulting binary image in order to remove noise and to merge broken regions. The centroids of each labelled region are used as seeds, from which a region-growing procedure starts. Statistics-based local thresholding is also applied to compute upper-and lower-threshold intensity values defining the spatial extents of the regions. The detection results obtained with the resulting automated thresholding and region-growing (ATRG) procedure are compared day-by-day with the synoptic maps manually generated by the Meudon Observatory and NOAA for 2 months in 2002 and more coarsely over a 5-year period. The moderate correlation found between our detection results and those produced manually on the other data sets reveals a need for a unified active region definition. As an application of the SFC for ARs we present the tracking of the active region AR NOAA 10484 during its appearance on the solar disk from 19-26 October 2003 and compare its intensity variations for Hα and Fe XII 195Å wavelengths.

No abstract