1 / 11

Indexed Captioned Searchable Videos

Indexed Captioned Searchable Videos. Cecilia Y. Chen University of Houston July 11,2012. Introduction. Usage of video to deliver coursework online: commonplace Evidence for video usage: - MIT OpenCourseware , - Apple’s iTunes University - YouTube Edu.

barny
Télécharger la présentation

Indexed Captioned Searchable Videos

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Indexed Captioned Searchable Videos Cecilia Y. Chen University of Houston July 11,2012

  2. Introduction • Usage of video to deliver coursework online: commonplace • Evidence for video usage: - MIT OpenCourseware , - Apple’s iTunes University - YouTube Edu

  3. Classroom lecture videos widely used at University of Houston • Tablet PC recordings

  4. Survey focus group: • Video lectures : powerful and versatile resource • The biggest weakness of the video format : Inability to quickly access the content of interest

  5. ICS Videos • Indexing: Segmented videos • Search: Keyword search in video • Captioning: Scrolling text for audio • Integrated in ICS Video Player • Project Goal: Quick access to video content

  6. Indexing: Finding Transition Points • Indexing : dividing video into segments; • User can start playback from any index frame • Transition Point: is a frame that has changes significantly when compared to another frame.

  7. Image approach: comparing images by pixel to find transition points • Text approach: comparing images using text to find transition points using OCR(Optical Character Recognition)

  8. Image approach vs Text approach

  9. Preliminary Results • There are special cases that is a lot faster to use the text approach • When a video is processed with text comparison at the end the difference in time to process might not be that significant • Most of the time the text comparison will recognize transition points accurately

  10. Resources • Houston, University of. Indexed Captioned Searchable Videos for STEM Courseware. 2009. <http://icsvideos.cs.uh.edu/>. • Tuna T, Subhlok J, Barker L,Shah S, Varghese V, Johnson O. "Development and Evaluation of Indexed Captioned ." (n.d.). • Tuna T, Subhlok J, Shah S. "Indexing and Keyword Search to Ease Navigation ." (n.d.).

  11. Questions

More Related