基於區域二值化紋理之人臉認證在 行動裝置遠端監控系統之應用

Abstract

本論文旨在開發可讓使用者針對特定區域經由無線網路進行監視與控制之遠端監控系統(MRSS)，主要目標是設計出使用在Android行動裝置上的應用程式，用來連結運算伺服器，利用伺服器快速的運算能力及大量的資料存取空間，來達到遠端監控之功能，包括影像傳輸、使用者資料存取、人臉偵測與認證、遙控網路攝影機。為了提升網路之個人隱私及資訊安全層級，使用者在觀看監控影像前，除了帳號密碼認證外，還需通過人臉認證，本論文開發了基於區域二值化紋理的類神經網路人臉認證系統，最後，運用SAMSUNG Galaxy SII智慧型手機和Acer ICONIA平板電腦來執行並驗證遠端監控之應用軟體，根據實驗結果，行動裝置至伺服器的傳輸速率為每秒15張影像，人臉辨識的準確率為95.77%，已達即時監控之功能。

This thesis develops a mobile remote surveillance system (MRSS) for users to watch a specific location via the wireless Internet. The aim is to design an App running on Android mobile devices to connect an operational server. The proposed MRSS adopts a PC-based operational server with fast calculating ability and large data capacity to fulfill the functions in remote surveillance and control, such as multimedia transmission through TCP protocol, access of user’s data, human face detection and verification and remote control of IP camera. To promote the level of personal privacy and information security, besides the password it is required to execute face verifications before the user watches the desired images. To increase the accuracy of face verification, this thesis develops an NN-Based face verification system which adopts the LBP operation to extract the face features. To demonstrate the performance of the MRSS system, the proposed Apps are executed on a SAMSUNG Galaxy SII phone and an Acer ICONIA Tab. Under the frame rate of 15 frames per second, the accuracy of human face verification is up to 95.77%.