Content based Indexing and Retrieval of Videos


There has been a tremendous increase in the generation and exchange of multimedia data in general and video databases in particular, resulting in an increased need for effective indexing and retrieval mechanisms.
Traditionally, video retrieval has been based on user-assigned tags and not on the actual content of the video. This project aims to develop a content-based video indexing and retrieval system.
Any caption text appearing in videos will be used as the primary index, while the audio content in these videos will serve as the secondary index. Indexing can be implemented either through recognition of text or using a word spotting-based technique. Either of these solutions could be developed to target a defined vocabulary of keywords.
Once the videos are indexed, the user may then retrieve all the frames of all the videos containing the text or/and spoken occurrences of the keyword by searching on a query keyword.

ThemeAI/Big DataTypeMultiple/