Automatic Detection of sunspot activities using advanced detection model

Sunspots are dark areas on the photosphere, from which sun emit light. Sunspots are regions located on active regions of the sun and have intense magnetic field (1). Sunspots appear dark and bright areas in magnetograms representing opposite polarities. Despite several research and development in the field of pattern recognition with specific application like sunspots , the general problem of recognizing complex patterns remain difficult. A new technique was developed for automated detection of sunspots on full disk white light solar images obtained from SOHO/MDI and SDO/HMI instruments. Hurdles in the sun spot detection are the irregularities in the shape, contrast with the surrounding and uneven intensity make the sun spot detection difficult. In this paper we present a hybrid method to detect and extract features. The input is a sequence of MDI images and the output is categorization of solar events. We perform basic image processing techniques like normalization, noise removal and segmentation. Finally we compare the solar indices like wolf sunspot number with our method against with the synoptic maps and different reference observatory data source. The proposed method presented can lead to automatic monitoring and characterization of solar events and yield an optimum performance.