Jump to content

Video search engine: Difference between revisions

From Wikipedia, the free encyclopedia
Content deleted Content added
Line 26: Line 26:
* '''Vedeo.tv''' Spanish site, but allows search in English and shows results from many video sites, including local news websites.
* '''Vedeo.tv''' Spanish site, but allows search in English and shows results from many video sites, including local news websites.
* '''[[yovisto]]''' is an academic video search engine for lecture recordings and scientific conference talks based on speech processing, [[Optical_character_recognition|OCR]], and user annotation.
* '''[[yovisto]]''' is an academic video search engine for lecture recordings and scientific conference talks based on speech processing, [[Optical_character_recognition|OCR]], and user annotation.
* [http://zapom.com ZaPom] Video Search Engine provides video search results from over 101 video content providers.


==== Non-agnostic search ====
==== Non-agnostic search ====

Revision as of 02:01, 14 September 2010

A video search engine is a web-based search engine which crawls the web for video content. Some video search engines parse externally hosted content while others allow content to be uploaded and hosted on their own servers. Some engines also allow users to search by video format type and by length of the clip. Search results are usually accompanied by a thumbnail view of the video.

Design and algorithms

Video search has evolved slowly through several basic search formats which exist today and all use keywords. The keywords for each search can be found in the title of the media, any text attached to the media and content linked web pages, also defined by authors and users of video hosted resources.

Some video search is performed using human powered search, others create technological systems that work automatically to detect what is in the video and match the searchers needs. Many efforts to improve video search including both human powered search as well as writing algorithm that recognize what's inside the video have meant complete redevelopment of search efforts.

It is generally acknowledged that speech to text is possible, though recently Thomas Wilde, the new CEO of EveryZing, acknowledged that Everyzing works 70% of the time when there is music, ambient noise or more than one person speaking. If newscast style speaking (one person, speaking clearly, no ambient noise) is available, that can rise to 93%. (From the Web Video Summit, San Jose, CA, June 27, 2007).

Around 40 phonemes exist in every language with about 400 in all spoken languages. Rather than applying a text search algorithm after speech-to-text processing is completed, some engines use a phonetic search algorithm to find results within the spoken word. Others work by literally listening to the entire podcast and creating a text transcription using a sophisticated speech-to-text process. Once the text file is created, the website lets you search the file for any number of search words and phrases.

It is generally acknowledged that visual search into video does not work well and that no company is using it publicly. Researchers at UC San Diego and Carnegie Melon University have been working on the visual search problem for more than 15 years, and admitted at a "Future of Search" conference at UC Berkeley in the Spring of 2007 that it was years away from being viable even in simple search.

Search that is not affected by the hosting of video, where results are agnostic no matter where the video is located:

  • AltaVista Video Search had one of the first video search engines with easy accessible use. Is found on a direct link called "Video" off the main page above the text block.[Since 2 February 2009 this feature has not been available from Altavista.com]
  • blinkx was launched in 2004 and uses speech recognition and visual analysis to process spidered video rather than rely on metadata alone. blinkx claims to have the largest archive of video on the web and puts its collection at around 26,000,000 hours of content.
  • CastTV is a Web-wide video search engine that was founded in 2006 and funded by Draper Fisher Jurvetson, Ron Conway, and Marc Andreessen.
  • Clipta is a deep crawling video search engine that indexes millions of videos from across the Internet. Clipta was founded and launched in 2008.
  • Munax released their first version all-content search engine in 2005 and powers both nation-wide and worldwide search engines with video search.
  • Picsearch Video Search has been licensed to search portals since 2006. Picsearch is a search technology provider who powers image, video and audio search for over 100 major search engines around the world.
  • ScienceStage is an integrated universal search engine for science-oriented video (lectures, conferences, documentaries, webinars, tutorials, demonstrations, grand rounds, etc.). All videos are also semantically matched to millions of research documents from open-access databases.
  • Truveo is a Web-wide video search engine that was founded in 2004 and launched in September 2005. Truveo claims to index over 100 million videos from thousands of sources across the Web.
  • Vedeo.tv Spanish site, but allows search in English and shows results from many video sites, including local news websites.
  • yovisto is an academic video search engine for lecture recordings and scientific conference talks based on speech processing, OCR, and user annotation.
  • ZaPom Video Search Engine provides video search results from over 101 video content providers.

Search results are modified, or suspect, due to the large hosted video being given preferential treatment in search results:

  • AOL Video offers a leading video search engine that can be used to find video located on popular video destinations across the web. In December 2005, AOL acquired Truveo Video Search.
  • Google Video is a popular video search engine which used to permit its visitors to upload videos. It searches its own hosted content, Youtube and many other video hosting sites.
  • Yahoo! Video Search Yahoo!'s search engine examines video files on the internet using its Media RSS standard. Is found on a direct link called "Video" off the main page above the text block.