UT Arlington project aims to make American Sign Language learning
\neasier<\/p>\n
Monday, February 4, 2008 <\/p>\n
UT Arlington project aims to make American Sign Language learning
\neasier <\/p>\n
By Pegasus News wire <\/p>\n
A UT Arlington assistant professor\u0019s research project will develop
\nmethods to aid in learning American Sign Language (ASL) by both deaf
\nand hearing individuals through $900,000 in National Science
\nFoundation funding during the next three years. <\/p>\n
Vassilis Athitsos \u0013 who is in the UT Arlington Computer Science and
\nEngineering Department, and will work with Drs. Stan Sclaroff and
\nCarol Neidle of Boston University\u0019s Computer Science Department \u0013
\nwill create tools and methods to aid in the learning process for ASL.<\/p>\n
Unlike a spoken or written language, ASL is not a literal
\nrepresentation of each word, so a complete sentence can be presented
\nvery rapidly. This often makes it difficult for students of ASL to
\ngrasp the quickly changing hand positions and gestures. The project
\nwill involve two significant developments. <\/p>\n
The first is the creation of search technologies for looking up the
\nmeaning of an unknown sign. Currently available sign\/meaning
\ndictionaries organize entries in alphabetical order. The team\u0019s
\nproposed methods can be incorporated into any existing dictionary to
\nallow sign-based look up, a capability that no dictionary currently
\nhas. <\/p>\n
Developed through the use of computer vision, data mining and machine
\nlearning applications, the dictionary will contain approximately 4,000
\ncommonly-used signs and should be deployable within three years. This
\nwill allow non-ASL users to more easily match gestures with meanings
\nand study visual patterns. <\/p>\n
The second goal is the development of a visual database and an
\nautomatic search tool for identifying occurrences of signs in large
\nvideo databases of ASL content \u0013 sort of a visual equivalent of
\nGOOGLE. It will allow users to search databases for occurrences of
\nthousands of signs. <\/p>\n
This would involve large-scale machine learning integrating methods
\nfor accurate sign recognition with methods for efficient indexing. <\/p>\n
\u001cThese applications would be of potential use to everyone
\ncommunicating with ASL,\u001d Dr. Athitsos said. \u001cChildren, parents,
\nteachers, doctors; they could all potentially benefit from the sign
\nlookup and search methods we are developing. For example, it should
\nbe very useful for a parent to be able to look up the meaning of a
\nsign that their deaf child has just performed, or perhaps for a
\ndoctor to understand signs used by a deaf patient.\u001d <\/p>\n
Source: UTA<\/p>\n
Link:
\nhttp:\/\/www.pegasusnews.com\/news\/2008\/feb\/04\/ut-arlington-project-aims-make-american-sign-langu\/?print<\/p>\n
—<\/p>\n
BETTER IP RELAY – EVERYWHERE! i711.com makes all your relay calls better.
\nBetter web calls. Better wireless calls. Better AIM calls. Why settle for
\nordinary IP relay? Go beyond! Try http:\/\/www.i711.com for free today!<\/p>\n
NEW! Try out our Deaf Network of Texas Calendar! Go to
\nhttp:\/\/calendar.deafnetwork.com <\/p>\n
NOTE: deafnetwork.com does not endorse any of the products, vendors,
\nconsultants, or documentation referenced in this message or. Any mention of
\nvendors, products, or services is for informational purposes only.<\/p>\n
Powered by http:\/\/www.CrazyWebHosting.com<\/p>\n
If you do not want to receive any more newsletters,
\nhttp:\/\/deafnetwork.com\/list\/?p=unsubscribe&uid=23e6b0ac27edebd2b6f52f1354859234<\/p>\n
To update your preferences and to unsubscribe visit
\nhttp:\/\/deafnetwork.com\/list\/?p=preferences&uid=23e6b0ac27edebd2b6f52f1354859234
\nForward a Message to Someone
\nhttp:\/\/deafnetwork.com\/list\/?p=forward&uid=23e6b0ac27edebd2b6f52f1354859234&mid=1046<\/p>\n
—
\nPowered by PHPlist, www.phplist.com —<\/p>\n","protected":false},"excerpt":{"rendered":"
UT Arlington project aims to make American Sign Language learning easier Monday, February 4, 2008 UT Arlington project aims to make American Sign Language learning easier By Pegasus News wire A UT Arlington assistant professor\u0019s research project will develop methods…<\/p>\n