Download presentation
Presentation is loading. Please wait.
Published byLeslie Wilkins Modified over 9 years ago
1
D-BUG Turkish Sign Language Recognition Using Microsoft Kinect Sponsored by INNOVA
2
G ROUP M EMBERS
3
O UTLINE Problem & Solution Project Details Work Done So Far Project Demo Video Future Work References
4
O UTLINE Problem & Solution Project Details Work Done So Far Project Demo Video Future Work References
5
P ROBLEM & S OLUTION The main problem is communication problem between speech-impaired people and the others. Being unable to express himself/herself can be frustrating.
6
P ROBLEM & S OLUTION Our Solution: Our goal: To help alleviate the frustration that speech-impaired people face by using assistive technology. Final Product : Gets the sign language gestures and give the meaning of them in text format.
7
O UTLINE Problem & Solution Project Details Work Done So Far Project Demo Video Future Work References
8
P ROJECT D ETAILS Components of the System Environmental Assumptions Libraries & Tools
9
C OMPONENTS OF THE S YSTEM InputHandler InterfaceHandler HMM Recognizer
10
C OMPONENTS OF THE S YSTEM HMM InterfaceHandler InputHandler Recognizer Joint positions Scaled hand positions Video stream Matrix indices Observation sequence Probability Gesture name Figure 1 : Interaction of the Components
11
C OMPONENTS OF THE S YSTEM InputHandler Repeatedly arranges Kinect input Calculates hand positions on the screen Creates SpaceZoningMatrix
12
C OMPONENTS OF THE S YSTEM InputHandler Figure 2: Space Zoning Matrix
13
C OMPONENTS OF THE S YSTEM InterfaceHandler Manages the user interface Moves hand cursors Changes interface modes
14
C OMPONENTS OF THE S YSTEM What is an HMM? HMM (Hidden Markov Model) is a probabilistic model created with a state set and an observation set. Model is based on the assumption that a visible observation sequence is triggered by hidden states of the model.
15
C OMPONENTS OF THE S YSTEM HMM Figure 3: General Hidden Markov Model Retrieved from http://www.mental.sk/temp/ai/csr.html
16
C OMPONENTS OF THE S YSTEM An HMM is defined with: Initial state distribution matrix State transition matrix Observation matrix
17
C OMPONENTS OF THE S YSTEM Three problems: Problem 1: Given a model, and a sequence of observations O find the probability of observing O in this model.
18
C OMPONENTS OF THE S YSTEM Three problems: Problem 2: Given a model and an observation sequence O, determine the optimal state sequences that results in given observation sequence in the given model.
19
C OMPONENTS OF THE S YSTEM Three problems: Problem 3: Given an observation sequence O and the dimensions N and M, determine the model which maximizes the probability of observing O.
20
C OMPONENTS OF THE S YSTEM In TSL-Kinect 1. Use the solution to Problem 3 to train an HMM for each gesture. 2. Use the solution to Problem 1 to determine the gesture is more likely to be “X” or “Y” or neither.
21
C OMPONENTS OF THE S YSTEM Figure 4: Working principle of HMMs Retrieved from http://lh5.ggpht.com
22
C OMPONENTS OF THE S YSTEM Recognizer Creates observation sequence for both hand Release sequence stacks
23
E NVIRONMENTAL A SSUMPTIONS Set up Kinect properly Stand 1.8 - 2.4 meters away from the sensor No moving objects around!
24
L IBRARIES & T OOLS The Microsoft official SDK for Kinect Microsoft Visual Studio 2010 NUI library Coding4Fun Kinect Toolkit
25
O UTLINE Problem & Solution Project Details Work Done So Far Project Demo Video Future Work References
26
W ORK D ONE S O F AR Basic user interface User interface control Simple gesture recognition
27
O UTLINE Problem & Solution Project Details Work Done So Far Project Demo Video Future Work References
28
P ROJECT D EMO V IDEO
29
O UTLINE Problem & Solution Project Details Work Done So Far Project Demo Video Future Work References
30
F UTURE W ORK Improvement on user interface HMM implementation More gesture recognition
31
O UTLINE Problem & Solution Project Details Work Done So Far Project Demo Video Future Work References
32
R EFERENCES
33
T HANK Y OU F OR Y OUR A TTENTION ANY QUESTIONS
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.