An investigation on gradual shot boundary detection and modified object based video retrieval algorithm

Abstract

Rapid growth in the field of data capturing and storage along with the increase in the availability of multimedia content in the web, has resulted in many large personal and public digital video databases. The rapid development in the availability of the multimedia database is not accompanied by the technologies used for its efficient usage and retrieval. This is due to the fact that the content of multimedia database is not same as that of the text database which is easily accessible based on the keywords of the document. It is very important to segment and organize the video data to be accessed easily. Shot Boundary Detection (SBD) is the fundamental base for automatic video content analysis that is used in the field of video indexing, video compression and video access. The objective of the shot boundary detection is to detect the visual discontinuities along with the time domain. During this detection the extracted visual features measures the degree of similarity between frames in a given shot. The video is hierarchically organized structure of frames, shots, scenes and stories. A frame is the lowest level in the hierarchy; it is the basic unit in of a video, also it represents a still image. Shot boundary detection techniques are used to group the set of frames into shots. Shot designates a continues sequence of video frames recorded by an uninterrupted camera operation, a scene is a collection of shots that present different views of the same object newline