Have you ever used myacm.org? If you are an ACM member, myacm.org includes a number of personalised services, for example e-mail forwarding, filtering, e-alerts, etc. It also lists the most popular articles in the ACM Digital library and also the most popular searches. According to their data, the most popular article is A feature-based algorithm for detecting and classifying scene breaks and was downloaded 2402 times. This paper describes an approach to detecting and classifying scene breaks. I think the work in this paper could be useful to people working on video accessibility.

A Feature-Based Algorithm for Detecting and Classifying Scene Breaks

We describe a new approach to the detection and classification of production effects in video sequences. Our method can detect and classify a variety of effects, including cuts, fades, dissolves, wipes and captions, even in sequences involving significant motion. We detect the appearance of intensity edges that are distant from edges in the previous frame. A global motion computation is used to handle camera or object motion. The algorithm we propose withstands JPEG and MPEG artifacts, even at high compression rates. Experimental evidence demonstrates that our method can detect and classify production effects that are difficult to detect with previous approaches.

Full Paper: http://doi.acm.org/10.1145/217279.215266
Full Proceedings: Proceedings of the third ACM international conference on Multimedia, San Francisco, California, 1995.

Labels: multimedia, myacm, video accessibility