本論文提出一套智慧型行動裝置與手勢辨識結合的系統,此系統透過無線攝影機擷取即時影像資訊,並搭配手勢辨識演算法,讓使用者可手勢控制音響設備。 本論文的模擬情境設置於一般居家環境,在電腦端設計一個GUI 介面,使用者可藉此介面擷取即時影像並執行辨識演算法。其流程乃是在擷取手勢影像後,利用K_means方法進行膚色偵測及萃取得手勢特徵,辨識手勢姿態,然後將辨識後的結果加以編碼。另外,搭配Eclipse軟體撰寫Android智慧型手機音樂播放程式,此播放程式經由TCP/IP接收編碼後的手勢指令,進而實現音響設備的控制。 本文著重在影像演算法上進行改良,使其偵測人體膚色的方法更具強健性,並將演算法實現於智慧型行動裝置之控制,透過使用者的手勢來進行音樂播放控制,實現智慧居家的夢想。 This thesis presents a hand gesture recognition algorithm and integrates it with the smart mobile devices for controlling an audio equipment. Specifically, the resulting system adopts a non-contacting way for hand gesture recognition, which captures the live video image through a wireless camera, recognizes hand gestures via the proposed algorithm, and operates with a friendly interface. As a result this allows the users to perform remote control of audio equipments. The proposed hand gesture recognition algorithm consists of skin color detection and hand gesture recognition, in which the K-means clustering classifier is used. Experiment shows that the proposed skin color detection method is more robust than a well-known statistical method, and the verification rate is increased. In addition, a music player program is developed upon the Android platform under the help of Eclipse software. This makes the remote control of audio equipment by hand gesture come true.