English  |  正體中文  |  简体中文  |  Items with full text/Total items : 28611/40649
Visitors : 643150      Online Users : 48
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/54113

Title: 結合人臉辨識與PPG之門禁系統實作
Imlementation of an Access control System Using Facial Recognition and PPG
Authors: Hu, Wen-Yang
胡文揚
Contributors: NTOU:Department of Electrical Engineering
國立臺灣海洋大學:電機工程學系
Keywords: 人工智慧;人臉辨識;卷積神經網路;PPG量測
Artificial Intelligence;Human Face Recognition;Convolutional Neural Networks;PPG Measurement
Date: 2019
Issue Date: 2020-07-09T03:02:04Z
Abstract: 最近幾年人工智慧一直是熱門話題,人工智慧是電腦科學的一個分支領域,在機器的自我解決問題,機器的自我學習,與機器的自我辨識,醫療影像處理領域,自駕車領域,圖像辨識領域等,應用廣泛,這些人工智慧的技術,可以分為監督式學習,與非監督式學習,監督式學習是有提供一個預估的資料供應其電腦學習,而非監督式學習則沒有提供一個預估的資料供其學習 本論文主要希望能實作一個門禁系統,使用人臉辨識與PPG波形辨識的結合,文中有三大部分,第一部分介紹opencv 的haar like分類器,能夠偵測人臉並且找出座標,第二部分介紹tensorflow所建立的卷積神經網路,能夠辨識人物,第三部分介紹arduino與pulse sensor 結合的PPG量測,第四部分實作這三個部分的組合,並且介紹這個系統的測試結果
In recent years, artificial intelligence (AI) has been becoming a popular topic. AI is a sub-field of computer science that may be widely applied to the fields of machine's automatic troubleshooting, machine's automated learning, machine's self-identification, and medical image processing, the field of self-driving cars, as well as the field of image identification. The above are all AI technologies, which can be divided into supervised learning and unsupervised learning. Supervised learning provides forecasting data for computers to learn, while unsupervised learning provides no forecasting data for computers to learn. The essay mainly wished to create an access control system that integrates the human face recognition function and the PPG waveform identification. The essay is comprised of three primary parts. The first part introduces the Haar-like classifier, which can detect human face and locate the coordinates. The second part presents the convolutional neural networks (CNN) established by TensorFlow, which can recognize human figures. The third part introduces the PPG measurement that combined Arduino and pulse sensor. The fourth part carries out experiments using combinations of the above three parts and presents the testing results of the system.
URI: http://ethesys.lib.ntou.edu.tw/cgi-bin/gs32/gsweb.cgi?o=dstdcdr&s=G0040543023.id
http://ntour.ntou.edu.tw:8080/ir/handle/987654321/54113
Appears in Collections:[電機工程學系] 博碩士論文

Files in This Item:

File SizeFormat
index.html0KbHTML12View/Open


All items in NTOUR are protected by copyright, with all rights reserved.

 


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback