Loading...

Design of Sensory Gove for Recognition of Persian Sign Language

Sarsharzaedh, Mohammad Mahdi | 2011

480 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 42362 (08)
  4. University: Sharif University of Technology
  5. Department: Mechanical Engineering
  6. Advisor(s): Vossoughi, Gholamreza; Parnianpour, Mohammad
  7. Abstract:
  8. Sign language is recognized by considering the combination of the hand gesture, orientation, location and patterns of hand and arm movement. These complex interactions make the character and word recognition very challenging. In this paper, with the aid of sensory gloves and multiple inertial measurement units (IMUs) we measure the shoulder and elbow joint trajectories and hand gesture to train the discriminant functions to recognize the words intended and represented by sign language. For recognition of hand gesture, the Naive Baysian classifier was used while for Eulerian angles a new time series similarity measures were computed. Different aggregation method was used to integrate temporal similarity measure of hand movement and spatial similarity measures of hand gesture. This hybrid approach improved the classifiers performance. Based on the 55 words that have been investigated in Persian sign language, we were able to recognize 98 percent of words correctly. The developed system that is being evaluated is a portable device and is independent of any external device for capturing and classifying the words being performed by the Persian sign language. We are currently engaged in expanding the vocabulary of learned words
  9. Keywords:
  10. Pattern Recognition ; Time Series ; Sign Language ; Bayesian Method ; Aggregation Method

 Digital Object List

 Bookmark

No TOC