TAMU Homepage TAMU Libraries Homepage TAMU Digital Library Homepage

Acoustic Based Sketch Recognition

Show simple item record

dc.contributor.advisor Hammond, Tracy en_US
dc.creator Li, Wenzhe en_US
dc.date.accessioned 2012-10-19T15:31:11Z en_US
dc.date.accessioned 2012-10-22T18:05:17Z
dc.date.available 2014-11-03T19:49:15Z
dc.date.created 2012-08 en_US
dc.date.issued 2012-10-19 en_US
dc.date.submitted August 2012 en_US
dc.identifier.uri http://hdl.handle.net/1969.1/ETD-TAMU-2012-08-11880 en_US
dc.description.abstract Sketch recognition is an active research field, with the goal to automatically recognize hand-drawn diagrams by a computer. The technology enables people to freely interact with digital devices like tablet PCs, Wacoms, and multi-touch screens. These devices are easy to use and have become very popular in market. However, they are still quite costly and need more time to be integrated into existing systems. For example, handwriting recognition systems, while gaining in accuracy and capability, still must rely on users using tablet-PCs to sketch on. As computers get smaller, and smart-phones become more common, our vision is to allow people to sketch using normal pencil and paper and to provide a simple microphone, such as one from their smart-phone, to interpret their writings. Since the only device we need is a single simple microphone, the scope of our work is not limited to common mobile devices, but also can be integrated into many other small devices, such as a ring. In this thesis, we thoroughly investigate this new area, which we call acoustic based sketch recognition, and evaluate the possibilities of using it as a new interaction technique. We focus specifically on building a recognition engine for acoustic sketch recognition. We first propose a dynamic time wrapping algorithm for recognizing isolated sketch sounds using MFCC(Mel-Frequency Cesptral Coefficients). After analyzing its performance limitations, we propose improved dynamic time wrapping algorithms which work on a hybrid basis, using both MFCC and four global features including skewness, kurtosis, curviness and peak location. The proposed approaches provide both robustness and decreased computational cost. Finally, we evaluate our algorithms using acoustic data collected by the participants using a device's built-in microphone. Using our improved algorithm we were able to achieve an accuracy of 90% for a 10 digit gesture set, 87% accuracy for the 26 English characters and over 95% accuracy for a set of seven commonly used gestures. en_US
dc.format.mimetype application/pdf en_US
dc.language.iso en_US en_US
dc.subject Pattern Recognition en_US
dc.subject Signal Processing en_US
dc.subject Sketch Recognition en_US
dc.subject Machine Learning en_US
dc.title Acoustic Based Sketch Recognition en_US
dc.type Thesis en
thesis.degree.department Computer Science and Engineering en_US
thesis.degree.discipline Computer Science en_US
thesis.degree.grantor Texas A&M University en_US
thesis.degree.name Master of Science en_US
thesis.degree.level Masters en_US
dc.contributor.committeeMember Ieorger, Thomas en_US
dc.contributor.committeeMember Cahill, Tony en_US
dc.type.genre thesis en_US
dc.type.material text en_US
local.embargo.terms 2014-10-22 en_US

Files in this item

Files Size Format View
LI-THESIS.pdf 2.165Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record