Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Thesis Final Defense Presentation

No description
by

Neil Anthony Rosales

on 27 February 2013

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Thesis Final Defense Presentation

A Framework for a Customizable Sign Language to Text Transcriber Prototype What's the problem? There is a scarcity of an adaptable and learning algorithm that will address the lack of
interpreters both in the local and global scale. Lack of Interpreters Dominance of the hearing community (Non-signers) poses difficulties for Signers. General Objective To be able to create a prototype that is customizable and is able to capture and interpret sign language gestures. Specific Objectives To capture, process and understand basic sign language gestures, regardless of the language. Verify if produced text is accurate based on its knowledge base. Interpret the gestures into its equivalent text from a stored data bank of gestures chosen by the user. How did we accomplish these? Scopes and Limitations Will use ASL and Custom FSL Only recorded words will be available for translation Only sign language gestures that involve the lip and the eye brows in terms of facial expression will be interpreted. The user must be in the approximate distance needed by the software in order to capture the data needed as inputs. Interpreted sign language into its equivalent text will not be altered in any way. Skeletal Tracking
Depth Mapping
Color Image Inputs
Facial Tracking [LANG2012] 2.5
[HUANG2011] 2.4
[ZHOU2011] 2.7 [ZHOU2011] 2.7 Signing Space [PDRC2004] 2.11 Posttest Only CGD. Agile Software Development Significance? The prototype to be produced by the research can be later used as a reference in implementing a compact and portable version of the prototype. Successful production of the prototype may also lead to a software which sign language teachers can make use of in aiding him/her on teaching sign language to the deaf people. The prototype may spark the creation of a software used in households that has a family member/s who is deaf. 1 out of 1000 in any community is deaf. (Parkhurst) 90% of born deaf have Non-signers as parents (Mitchel) Out of 1 million Filipino's with disabilities, only 0.159% are deaf (PNSO) Very difficult to learn spoken/written language (Garcia) Most deaf worldwide grow up without any formal way of communicating (Hurlbut) On average, a country only has 0.0000167% qualified and trained interpreters (Haualand). Euclidean Distance Depth Data Minimum distances from each interior point to every contour point, and from these distance we select the maximum. The point that corresponds to that distance is the center of the hand. k-curvature algorithm Finding Fingertips k=22 and a = 40. if a < 40 = A Fingertip [CEREZO2012] j48 algorithm Hit Miss Trajectory of "Halika" gesture Trajectory of "Good Evening" gesture
Full transcript