近幾年來人機互動領域的相關研究越來越頻繁地出現在我們生活周遭，這些相關的應用與研究不但帶給我們生活上的便利也提高使用者的工作效率，使用這些相關應用可以降低成本開銷，同時也讓使用者透過不同類型的人機互動方式以更自然、更迅速且更直觀的操控向電腦傳達需求，隨著科技進步與精密設備的推出現今電腦能夠替使用者完成的工作越來越多元，例如我們隨手可得的智慧型手機只需要輕觸面板就可以執行手機內的應用程式，或是透過攝影機如手機鏡頭 、 Kinect 、 Leap Motion 、 Google Glass …等等設備辨識影像進一步向電腦傳達指令，當電腦接收到指令後替使用者完成指定的工作，近幾年透過新穎人機互動技術與電腦互動的相關研究逐漸變得純熟，而這些相關研究突破傳統與電腦互動及溝通的方式，這也使得人機互動逐漸成為現代人生活的一部分。 在這篇論文將會介紹使用Leap Motion實作虛擬樂器的方法，同時搭配MIDI軟體讓虛擬樂器可以演奏的音色更多，然後我們會先透過幾個手部的特徵資訊訓練類神經網路，再將訓練完的類神經網路加入系統進一步辨別預定好的手勢觸發指定的功能，加入類神經網路後系統依然可以保持即時執行。;Research in the field of Human-Computer Interaction (HCI) has become more and more frequently in our life. These related applications not only make our lives more convenient and efficiency, but also reduce the overhead costs. Users can more naturally, quickly and intuitively convey commands through different types of HCI applications to computer. With advances in computer technology and precision equipment, computers can complete multivariate works for users. For example, the use of smartphones just touching the panel, then the alarm clock, navigation, photograph applications will be executed. And even the use of camera devices like Kinect , Leap Motion , Creative Sen3d , etc. Through recognizing the images obtained from camera devices convey commands to the computer. And the computer complete the assigned work for users when receives commands. In recent years, the researches about innovative technology and human-computer interaction become skillful. These studies break the traditional way of interacting with a computer also makes HCI becoming a part of life. Leap Motion was used to captured the hand information of users in this paper. Further recognize the hand gesture of users to reduce the burden of operating virtual instrument. We train a neural network to analyze the information captured from the Leap Motion, then convey commands that we predefined to computer. Finally, this paper will show that our system could maintain in real time and stable state.
