Yan, Wei QiLi, Ricky2017-10-232017-10-23201720172017https://hdl.handle.net/10292/10892The Morse code is one of the earliest means of telecommunications; however, it is rarely used nowadays due to viral mobile communications. Although a person can tap Morse codes using his fingers easily, perhaps nobody is aware of this kind of finger gestures anymore. In this thesis, we will develop a prototype combined the principle of old Morse code with finger gesture recognition in machine learning together. A camera is used to capture a sequence of video frames, the prototype will recognize the finger gestures from these frames and convert the corresponding Morse codes to readable ASCII letters, characters or emotional symbols. The significant work could be applied to those special communications or dialogues, not allowed to speak loudly and explicitly. The contributions of this thesis are the finger gesture recognition based on empirical approaches for Morse code input; the highest recognition rate is up to 93%.enGesture recognitionMorse codeFingertip trackingSVM (support vector machine)Gaussian pyramidBPNNThesisOpenAccess2017-10-20