Annotate And Visualize A Video With Pose Recognition And Text Gloss Ssg

Good interfaces should help us to decide what next? Hence, Interface design issues pertinent to this project include the integration of media, annotation, use of metaphors, standards and the goals of the multimedia system. Without control over facial appearance, screening perspective, illumination circumstances, occlusions, background, expression, hairstyles, in the video quality is exaggerated and image contains noise pixels and Face data in different angle cannot be recognized. So recognize an unimpeded pose and visualizing a video in multimedia environment with authoring is, still a thorny way. In this paper we present a dual course of action, at first annotate a video with excellent pretense extraction using Fuzzy Local Information C-Means (FLICM) Clustering Algorithm. This approach is used to fuzzy local gray level quantify resemblance, aiming to assure noise insensitiveness and image detail preservation. Subsequently we can generate sketches using sobel operator which finds the sharp intensity variation of an image and it obtains the edges of the objects contained on the image. At the jiffy phase we propose a text gloss scene structured graph to authorize a video.