I am working on content based video retrieval system as my mtech project. Please send me required matlab code in moon.kgec[at]gmail.com, so that I can modify and reuse it.
I am working on content based video retrieval system as my mtech project. Please send me required matlab code in mustaqeemicp[at]gmail.com/mustaqeem306[at]yahoo.com, so that I can modify and reuse it. i shall be very obliged for this kind of act.
Content Based Video Indexing and Retrieval (CBVIR), in the application of the image recovery problem, ie the problem of finding digital videos in large databases. "Content Based" means that the search will analyze the actual content of the video. The term "Content" in this context may refer to colors, shapes, textures. Without the ability to browse video content, searches must be based on user-supplied images. Although the term "search engine" is often used indiscriminately to describe search engines based on crawlers, directories for human use and everything else, they are not all the same. Each type of "search engine" gathers and sorts lists in radically different ways. Search engines based on crawlers, like Google, compile your ads automatically. They "crawl" or "spider" the web, and people search through your ads. These listings are those that make up the index or the catalog of the search engine. One can think of the index as a massive electronic filing cabinet containing a copy of every web page that the spider finds. Because spiders scan the web on a regular basis, any changes that are made to a website can affect the ranking of the search engines. It is also important to remember that it may take a while for a spidered page to be added to the index. Until that happens, it is not available to those who search with the search engine.
Content-Based Video Retrieval (CBVR) has been increasingly used to describe the process of retrieving desired videos from a large collection based on the characteristics that are extracted from the videos. The extracted features are used to index, sort and retrieve the desired and relevant videos while filtering unwanted ones. Videos can be represented by their audio, texts, faces and objects in their frames. An individual video has unique motion characteristics, colour histograms, motion histograms, text features, audio characteristics, features extracted from faces and objects in its frames. Videos that contain useful information and that occupy significant space in the databases are underused unless CBVR systems able to retrieve the desired videos by selecting sharply relevant while filtering unwanted videos exist. The results have shown improved performance (greater accuracy and recall values) when the characteristics appropriate for certain types of videos are used wisely. Various combinations of these characteristics may also be used to achieve the desired performance. In this work, a complex and wide area of CBVR and CBVR systems has been presented in an exhaustive and simple way.