隨著網際網路技術的蓬勃發展，檔案數位化已成為這幾年來的趨勢，多媒體資訊在網際網路上傳輸已相當簡單且容易，而資料的隱密性相對的也變得日漸重要。因此數位影片的智慧財產權（intellectual property, IP）已成為數位化時代中的重要課題之一。
本研究中，提出一個能減少嵌入影像浮水印所需的龐大時間，且達到省時快速又不失去浮水印演算法強健性的技術。此技術著重於這幾年相當熱門的圖形處理器（graphic processing unit, GPU） 與統一計算架構（computer unified device architecture, CUDA）並配合強健的浮水印演算法，將與一般中央處理器（central processing unit, CPU）所執行之嵌入浮水印演算法做效能比較。並且藉由本實驗所產生之數據，驗證兩種不同設備之運算方式的效能高低。

With the rapid development of the Internet technology, digital archives have become the trend for the past few years, and transmission of multimedia data over the Internet has become simple and easy. Therefore, the confidentiality of information has become increasingly important, and study of intellectual property rights of digital videos has turned into a hot issue in the digital age today.
In this paper, we propose a fast algorithm to reduce the time required to embed watermarks for large images, and retain robustness of watermarks as well. The proposed technique focuses on combining graphic processing unit (GPU) and computer unified device architecture (CUDA) with a robust watermarking algorithm. Finally, we conduct performance comparison of embedding watermarks on videos using GPU or central processing unit (CPU) to investigate the effectiveness of these two different computing approaches.