Erin Plasse Advisors: Professor Hanson Professor Rudko
Introduction Experiment done in 1960’s by Kenneth Stevens and Dr. Sven Öhman in Sweden Used a cineradiograph x-ray to take lateral images of the vocal tract 31 utterances and 2 sentences were made Analyzed how articulators displace over time 45 frames/second
Movie Clip
Image Processing Perkell (1969)- Used manual methods to make tracings of the images
Typical Tracing Perkell (1969) used manual
Typical Analysis Perkell (1969) used manual measures
Goals & Parameters Design an algorithm in MATLAB to automate the tracings using edge detection methods Trace certain articulators, such as, lips, velum, epiglottis, hyoid bone, etc. Results should be similar to the original tracings Only 13 utterances were analyzed Obtain tracings for the 20 utterances not analyzed by Perkell (1969) Manual extraction is time consuming Smooth and continuous curves
Design Alternatives Snakes: Active Contour Models Matlab script written by Eric Debreuve Chan-Vese Region Based Segmentation Algorithm Matlab script written by Shawn Lankton EdgeTrak System for Ultrasound images VIMS Lab, University of Delaware Customize one of above to create own design for the data
Snakes: Active Contour Models Michael Kass Snake: Energy minimizing spline guided by external forces Image forces pull it toward lines and edges MATLAB code written by Eric Debreuve Only worked with binary images
Chan-Vese Algorithm Region based segmentation Use homogeneity of intensity in a region as the constraint Only applicable to closed contours Uses an initial mask region MATLAB script written by Shawn Lankton
Pharynx using Chan-Vese
EdgeTrak System Li, Kambhamettu, Stone Uses gradient image forces and intensity information in local regions Energy definition for snakes: E Total = α E int + β E ext Energy band gap External energy is redefined for EdgeTrak as: E′ ext (vi) = E band (vi) E ext (vi) Not effective for closed contours Good for tracking tongue in noisy images with high- contrast unrelated edges
Energy Minimization Band Main contribution of EdgeTrak method, finds the intensity of the regions. Energy band regions are found around each snake element Find mean intensity difference between regions Find new external energy using band energy Minimize total energy using dynamic programming
EdgeTrak Program
The Final Design Used methods from both the EdgeTrak System, Chan-Vese, and snake methods. Implemented using MATLAB Used only the image gradient to find edges Tongue is the articulator that is focused on
MATLAB Code User picks 5 points 33 snake elements found using spline interpolation Computes internal and external energy of initial snake elements Computes internal and external energies of points surrounding each initial point Finds the surrounding point with the lowest energy, this becomes new point New contour is graphed
MATLAB Code Demo %Edge_trak_demo %Coded by Erin Plasse
Final Results Results- o Energy of original snake = o Energy of new snake = o Percent change Snake energy = Alpha =.2, Beta =.8, Delta = 5
E_snake_orig = E_snake_new = Percent_change_Snake_energy =
Initial Points Final Points
Application to other articulators
Cont.
Future Work Apply the contour model to a sequence of consecutive frames Find more articulators Use the intensity method for external energy as described in the Edge Trak program
References Perkell, Joseph S.. Physiology of Speech Production: Results and Implications of a Quantitative Cineradiographic Study. Cambridge, MA: The MIT Press, Stevens, Kenneth and Öhman, Dr. Sven. (1963). “Cineradiographic Studies of speech:procedures and objectives.” J. Acoust. Soc. Am., 35, M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active Contour Models,” Int. J. Comput. Vis., vol. 1, pp , T.F. Chan, L.A. Vese. Active Contours Without Edges. IEEE Trans. On Img. Processing., vol. 10, pp , M. Li, C. Kambhametti, M. Stone. Automatic Contour Tracking in Ultrasound Images
Questions?