Event extraction & image retrieval for story board generation using GLCM

Data mining is the process of extracting information or knowledge from a wide database. In addition, to provide a visually appealing storyboard, each event is mapped with a set of relevant images arranged along a timeline. In order to retrieve features of similar types of image shapes and texture, a feature called Weighted Euclidean distance is used. Image mining is the association of image data and extraction of hidden data. Image mining makes use of texture, color factors and size of an image. Traditional websites were driven by human-edited events which lead to huge web search traffic. This work suggests an automatic system to detect events from search log data and generate storyboards where the events are arranged along a timeline. Smooth Nonnegative Matrix Factorization framework (SNMF) based event discovery from log data is used. In addition, to provide a visually appealing storyboard, each event is mapped with a set of relevant images arranged along a timeline. Image texture is determined by a feature called Gray Level Co-occurrence Matrix (GLCM). In this case image retrieval feature will be sharp.