Open Access Open Access  Restricted Access Subscription or Fee Access

Video Shot Boundary detection using logarithmic intensity histogram for Video Retrieval

Kalpesh M Shah, Ramji M. Makwana


This paper presents automated shot boundary detection for video retrieval applications that exploits the logarithmic histogram of intensity to extract color features from video frames. The proposed algorithm has the main purpose of identifying appropriate boundaries between shots of a video. In the first step, logarithmic histogram of the video frame is obtained with mapping of intensity level to an appropriate level. This quantization process maps the image features into logarithmic histogram. To find shot boundaries between video frames, Video frames are compared sequentially using logarithmic histogram and absolute difference. Higher the difference value point outs extreme change between content of two frames. In lieu of statistical threshold frame rate is used for identifying shot boundaries. If detected Video shot having frames less than frame rate is ignore as a shot boundary and clubbed with previously detected shot. Videos from various categories like sports, news and cartoon are used o evaluate the performance of proposed technique. It shows significant detection of boundaries having sharp transition. Due to auto threshold it performs very well even in case of gradual shot boundaries. Method has also been evaluated on standard database TRECVID 2007.


Shot Boundary detection; Logarithmic histogram; Threshold selection; Difference vector

Full Text:


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.