A Framework for Measuring Video Similarity and Its Application to Video Query by Example

The usefulness of a video database relies on whether the video of interest can be easily located. To allow exploring, browsing, and retrieving videos according to their visual content, efJicient techniquesfor evaluating the visual similarity between diyerent video clips are necessary. Wepresent aframework for measuring video similarity across different resolutions - both spatial and temporal. In particular; the video clips to be compared can be properly aligned through the use of suitable weightingfunctions and alignment constraints. Dynamicprogramming techniquesare employed to obtain the video similarity measure with a reasonable computational cost. An application to searching MPEG compressed video by example is presented to demonstrate the potential use of the proposed video similarity measure.

• Type: Conference
• Year: 1999
• Where: ICIP
• Authors: Yap-Peng Tan, Sanjeev R. Kulkarni, Peter J. Ramadge
• Keywords: Diyerent Video Clips, ICIP 1999, Image Processing, MPEG Compressed Video, Video Similarity Measure