| Summary: | 碩士 === 國立臺灣科技大學 === 機械工程系 === 104 === In this thesis hand images were applied to perform sign language recognition through an RGB-D camera in general environments. Unlike many available methods focusing on number (from zero to nine) recognition in sign language, we proposed a method to perform Taiwanese sign language recognition, both for single vocabulary and sentences.
For practical use, users first put their hands in front of the RGB-D camera with a distance between 40 cm and 70 cm. The depth information extracted from RGB-D camera was then used to construct the hand images and perform Taiwanese sign language vocabulary recognition using Haar feature-based cascade classifiers. The recognition can be classified into two parts. The first part is static Taiwanese sign language recognition for a sentence. The second part is recognizing dynamic Taiwanese sign language vocabularies as a sentence. Because hands are moving during dynamic sign language vocabulary recognition, we applied the optical flow method to recognize the hand orientation. Using the methods above, we have successfully performed Taiwanese sign language recognition. Finally, we also developed a Taiwanese sign language recognition module, which can be treated as a key technology for Taiwanese sign language translation. The recognition includes static and dynamic Taiwanese sign language vocabularies. These results may be useful for future real-time Taiwanese sign language recognition researches.
|
|---|
