Foundations of Multimedia Information Processing

Foundations of Multimedia Information Processing

Anindita Das Bhattacharjee (Swami Vivekananda Institute of Science and Technology, India)
Copyright: © 2017 |Pages: 31
DOI: 10.4018/978-1-5225-0498-6.ch001


It is easy to understand image and video stream by a human being but a computer can't understand them at all. For that reason there are several methods to make the computer to understand about the media it is being talked about. The following writing discusses about how to analyze a video or an image by using several methods like scene analysis, and shot boundary detection and analysis, frame analysis, hypermedia representation, segmentation of media. All of these are the representation of the whole media that have been fed as input and these representation outputs are used by computer by computer vision algorithm to process a video or image and give the expected results. The main focus of this writing is discussing how to use the above mentioned methods in any of the media video or image and extract the information required to represent the whole media under process.
Chapter Preview


Human beings can understand video and images better than any computer but computer can outperform a human in the means of computation. Say for instance from a live stream of video one specific face should be located and the person whose face is being tracked is also in motion is a crowd. It is almost impossible for a human being to detect that specific face in such a short time where the person is on the move and there are other people surrounding him. The computer if it has the proper algorithm written, can detect the face and track down the person with much higher probability of success than any human being. So the objective is not to make the computer understand a video stream or image better than human but to detect and separate objects better than any human being.

Complete Chapter List

Search this Book: