1 / 1

IEEE NOVA Seminar: 7 PM, Wednesday, May 29, 2013

IEEE NOVA Seminar: 7 PM, Wednesday, May 29, 2013 Hand Gesture Recognition Using Hidden Markov Models Joseph Picone, Shuang Lu and Amir Harati Institute for Signal and Information Processing, Temple University. Abstract:

shana
Download Presentation

IEEE NOVA Seminar: 7 PM, Wednesday, May 29, 2013

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. IEEE NOVA Seminar: 7 PM, Wednesday, May 29, 2013 Hand Gesture Recognition Using Hidden Markov Models Joseph Picone, Shuang Lu and Amir HaratiInstitute for Signal and Information Processing, Temple University Abstract: Advanced gaming interfaces such as Microsoft's Kinect have generated renewed interest in hand gesture recognition as an ideal interface for human computer interaction. In this talk, we will discuss a specific application of gesture recognition - fingerspelling in American Sign Language. Fingerspelling is widely used for communication amongst signers. Signer-independent (SI) fingerspelling alphabet recognition is a very challenging task due to a number of factors including the large number of similar gestures, hand orientation and cluttered background. We propose a novel framework that uses a two-level hidden Markov model (HMM) that can recognize each gesture as a sequence of sub-units and performs integrated segmentation and recognition. We present results on signer-dependent (SD) and signer-independent (SI) tasks for the ASL Fingerspelling Dataset: error rates of 2.0% and 46.8% respectively. The SI results improved the best previously published results by 18.2% absolute (28.0% relative). A live demo will also be presented. Biography: Joseph Picone received his Ph.D. in Electrical Engineering in 1983 from the Illinois Institute of Technology. He is currently a Professor in the Department of Electrical and Computer Engineering at Temple University. His primary research interests are currently machine learning approaches to acoustic modeling in speech recognition. His research group   is known for producing many innovative open source materials for signal processing including a public domain speech recognition system. He is a Senior Member of the IEEE and has been active in several professional societies related to human language technology. He has authored numerous papers on the subject and holds several patents in this field. LOCATION: Integrity Applications Incorporated (IAI), 15020 Conference Center Drive, Suite 100, Chantilly, VA 20151 Check-in:  IAI 1st Floor Suite 100 Reception Desk  Location:  IAI 4th Floor Suite 400 (Room number 4156)

More Related