適用於各種企業應用之高擴充性混合式指紋辨識系統

Abstract

近年來，由於企業規模的迅速成長，在企業應用上能夠整合具有高安全性、低成本且可以快速認證使用者身份的方法顯得更加重要及需要。身份認證的目的在於個體的識別，除了傳統的密碼比對方法外，指紋辨識在市場上是一個普遍且可靠的生物辨識技術。為了符合企業應用的不同需求，我們提出一種混合式的指紋辨識系統，簡稱 HFIS。對於強調方便使用的企業應用，我們提出HFIS-HTTP來滿足使用者在任何平台、任何地方，只要透過網頁瀏覽器就可以經由認證使用公司內部資源；而對於強調能在短時間內處理大量需求的應用，我們所提出的HFIS-TCP可以滿足企業內部網路高安全性及快速反應的需求。在本論文中，我們以傳送指紋特徵 (feature-based)，而非指紋圖像 (image-based) 來降低指紋辨識所需的傳送資料量及傳遞時間。由於在指紋辨識系統內，指紋特徵抽取是其中最耗時的工作項目，我們將該項目程序由原本在指紋伺服器執行，改為分散到各個客戶端的終端機執行，以降低指紋伺服器的工作負載。在反應時間不超過兩秒的條件下，與其他以傳送指紋圖像的方法比較，在可支援的客戶端數量方面，HFIS-HTTP在截止期限錯失率2%時，比Liu的方法增加了41.92%；在截止期限錯失率5%時，比Wang的方法增加了84.06%。HFIS-TCP在截止期限錯失率3%時，比Chang的方法增加了45.28%。至於平均反應時間則分別減少23.66%、28.89%及14.58%。總而言之，除了HFIS-TCP在較低的截止期錯失率 (0%和1%) 情況下，我們提出的HFIS-HTTP和HFIS-TCP兩種方法，在其他所有情況下都比相關方法有較短的平均反應時間。因此，本論文所提出的混合式指紋辨識系統非常適用於需要高安全性、低成本、快速反應時間，以及高擴充性且有不同需求的企業應用。

In recent years, the scale of enterprises is getting larger and the integration of identity authentication with higher security, lower cost, and shorter response time to enterprise applications becomes more important and desirable. The purpose of an identity authentication is to identify individuals. Besides the traditional password verification, the fingerprint identification is a popular and reliable biometric identity authentication technique in the market. To meet different characteristics of enterprise applications, we propose a hybrid fingerprint identification system (HFIS). For applications with emphasis on easy access, HFIS-HTTP is proposed to meet the requirement for users to access internal resources through web browsers from any platform, any place in Internet; for applications with emphasis on handling massive requests coming in a very short time, HFIS-TCP is proposed to meet high security and fast response time requirements in intranets. In our approach, we reduce the amount and time of data transmissions by transferring fingerprint features (feature-based) instead of fingerprint images (image-based). Since feature extraction is the most time-consuming task in fingerprint identification systems, we offload this task to each client to reduce the loading of the fingerprint server. Compared to other image-based approaches, under 2 seconds response time threshold, the proposed HFIS-HTTP increases the number of clients supported by 41.92% (reduces average response time by 23.66%) compared to Liu’s at 2% deadline miss ratio and by 84.06% (reduces average response time by 28.89%) compared to Wang’s at 5% deadline miss ratio. In addition, the proposed HFIS-TCP increases the number of clients supported by 45.28% (reduces average response time by 14.58%) compared to Chang’s s at 3% deadline miss ratio. In summary, the proposed HFIS-HTTP and HFIS-TCP have shorter average response time than related work for all cases, except HFIS-TCP with Embedded-based Clients at lower deadline miss ratios (0% and 1%). Therefore, the proposed HFIS is well suited for various enterprise applications which may require different combinations of high security, low cost, low response time, and high scalability.