基於JPEG2000心電圖像之快速身份辨識系統

Abstract

本論文提出了一個快速的心電圖生物特徵辨識方法。在無線遠程醫療應用中，高效率的傳輸和儲存需求有賴於心電圖的資料壓縮處理，身份辨識必須執行解壓縮後，才能相容於現有運作在原始域的生物辨識技術。為了實現更迅速的病人照護，本論文提出了一種運作於壓縮域的心電圖生物特徵辨識方法，在JPEG2000架構上將身份辨識簡化成一項內涵式影像資訊檢索問題。首先，單一導程的一維心電圖訊號經過預處理程序轉變成二維心電圖影像，再進行JPEG2000影像編碼標準的壓縮處理。透過此機制心電圖的形態特徵轉換為輝階影像的紋理內容，我們利用此紋理特徵作為個人身份辨識的依據。由實驗結果顯示，本論文提出的壓縮域心電圖生物特徵辨識系統，在QT標準心電圖資料庫測試具有99.50%的辨識精準度。

In the wireless telecardiology application, compressed ECG packets are often required for efficient transmission and storage purposes. Compressed ECG data must be decompressed first before applying existing biometric techniques that work on the original signal. To achieve a faster patient care, we propose a new method to perform person identification in compressed domain using one-lead ECG signals. First, we apply a preprocessor which converts 1-D ECG signals to 2-D image matrices and compress them by JPEG2000 image coding standard. Feature relating to ECG morphology were then extracted for indexing person identity by texture content in a known enrollment database. Experiments on standard ECG databases demonstrate the validity of the proposed compressed- domain ECG biometric system with an accuracy of 99.50%.