A modified shifted means-based segmentation approach to detect active regions and coronal holes in the solar dynamics observatory images

Solar images taken at different wavelengths enable scientists to visualize and analyze the suns activities. The Solar Dynamics Observatory (SDO) provides high-resolution images of the sun, with cadence in seconds, taken at varying wavelengths, resulting in finely detailed, almost continuous data for researcher’s examination. We propose an approach to find active regions and coronal holes that involves shifted means based segmentation, and voting based edge linking to link fragments combined with Moore’s neighbor tracing algorithm to highlight the regions of interest. This approach is illustrated by using the images taken by the AIA telescopes onboard of the SDO mission. We obtain a segmented image that clearly isolates the active regions. Moreover this method is comparatively faster than the commonly used fuzzy logic based methods. This method is capable of forming a foundation for the analysis of various other features of the sun like detection of prominences.