Automated removing stripe interference in full-disk solar image

Abstract The full-disk solar Hα image quality is significantly degraded by the stripe interference. In this paper, to improve the analysis of morphological evolution, a robust solution for stripe interference removal in the partial full-disk solar Hα image is proposed. The full-disk solar image is decomposed into a set of support value images in different scales by convolving the image with the sequence of multi-scale support value filters, which are calculated from the mapped least-squares support vector machines (LS-SVM). To match the resolution of the support value images, the scale-adaptive LS-SVM regres-sion model is used to remove the stripe interference from the support value images. We demonstrated the advantages of our method on the solar Hα images taken in 2001-2002 by Huairou Solar Observing Station. Experimental results show that our method can well remove the stripe interference in the solar Hα images and the restored image can be used in morphology researches