台灣正逐漸面臨著高齡化社會，老年人口比例逐年提高，又社會普遍對機構照顧接受度不高，獨居的老人日益增加。因此政府積極的推動長照2.0，希望盡早準備銀髮族的照顧與需求。現今社會對銀髮族的研究議題主要著重在銀髮族的健康、醫療、生活照護等等的輔助上，鮮少著重在銀髮族長者獨自在家的居家安全上，然而這一點在未來的長照2.0中的居家照護上是非常重要，因為沒有居家安全何來居家照護。在高齡化社會年長者獨自生活，生理上的疾病甚至宵小闖空門，就不能保障年長者的生活安全。本研究將以銀髮族為對象，設計他們專屬的居家安全系統。透過物聯網技術與人臉辨識技術的結合，提供獨居銀髮族長者居家環境監控，長者在家可以透過系統門窗有無關妥，當系統偵測到獨居長者環境訊息不對勁，系統會即時的通知家屬及相關單位。對門外的訪客資訊也會做智能型的紀錄與過濾，在門外來了訪客時，系統會通知獨居長者，協助建議是否給予放行，並且記錄來客拜訪資訊追蹤訪客的時間，透過統計數據協助辨識訪客來訪時間是否有異常，阻絕陌生人入侵的危險並將資訊通知相關安全單位與家屬，在危險發生前確保他們的安全，建立一個智能的安全的居家環境。

Taiwan is gradually stepping into the aging society. The proportion of senior citizens grows year by year. In Taiwan, living in the care facilities is not popularly accepted by the senior citizens. Therefore, the number of living alone senior citizens grows quickly. Nowadays, the research topics on the senior citizens mainly focus on health monitoring, medical care, and life support, but fewer of them care about the home security. However, in the aging society, home security is an important issue before all the other issues. For the living alone senior citizens, we need to monitor the accidents occur in the home, the physical diseases of the senior citizens, and intruders to guarantee the safety of the senior citizens. By combining the technology of Internet of Things (IoT) and face recognition, we designed a Home Security System for senior citizens. The environmental information around the home, and the visitor's information are monitored. When the designed system detects the abnormal status of the senior citizens, the families and the related institutions will be notified immediately. When strangers appear in front of the door, the designed system will help the elders to determine whether the visitors can enter the house or not. The system will record related visiting information about the visitors and use statistics for helping the families of the senior citizens to detect the abnormal states of the visitors.

摘要............................................................i
Abstract.......................................................ii
誌謝..........................................................iii
目錄...........................................................iv
表目錄..........................................................v
圖目錄.........................................................vi
符號說明.....................................................viii
第1章 簡介....................................................1
1.1 研究背景................................................1
1.2 研究動機................................................3
1.3 研究目的................................................4
1.4 論文架構................................................4
第2章 相關文獻探討與技術分析...................................5
2.1 文獻探討................................................5
2.2 人臉辨識技術............................................12
2.2.1 主要成分分析(Principal Components Analysis，PCA)........12
2.2.2 線性判別分析(Linear Discriminant Analysis，LDA).........13
2.2.3 局部二值模式 (Local Binary Patterns，LBP)...............15
第3章 系統設計與方法..........................................17
3.1 系統架構...............................................17
3.2 系統流程...............................................22
3.3 系統方法...............................................25
第4章 實驗結果...............................................32
4.1 核心人臉辨識演算法驗證..................................32
4.1.1 混和特殊化與一般化特徵的主要成分分析......................32
4.1.2 局部二值模式............................................36
4.1.3 結合遮罩局部二值模式.....................................38
4.2 系統實作數據與驗證.......................................40
4.2.1 統計數據分析............................................40
4.2.2 智能感知物聯網系統.......................................44
第5章 結論與未來展望..........................................47
參考文獻........................................................48
Extended Abstract...............................................51

[1]內政部戶政司 (2018, January 28). 人口統計 [Online].Available：http://www.ris.gov.tw/
[2]內政部警政署 (2018, February 13).刑案發生統計[Online]. Available：https://www.npa.gov.tw/NPAGip/wSite/mp?mp=1
[3]蘇怡璇 (2017, December 18). 男強盜民宅 [Online].Available：http://www.setn.com/News.aspx?NewsID=326754
[4]鐘武達 (2017, June 21) 老闆行竊失風，竟毒打獨居老人 [Online].Available：http://www.chinatimes.com/newspapers/20170621000665-260107
[5]August (2016, November 06) Smart Lock [Online].Available：http://august.com
[6]ASUS (2016, June 16) Smart Door Lock [Online].Available：https://www.asus.com/tw/
[7]ZKTeco (2015, September 29) 指紋辨識門鎖 [Online].Available：http://www.zkteco.com
[8]Yale(2016, June 20) 電子鎖 YMF40 指紋鎖 密碼鎖 [Online].Available：https://www.yale.com.hk/zh-hk/yale/yale-hk/
[9]Samsung(2016, October 4)電子鎖SHP-DP728 [Online].Available：https://samsungsmarthome.cyberbiz.co/
[10]壹讀 (2016, February 03) 這樣簡單幾步就能破解指紋手機？一起來驗證 [Online].Available：https://read01.com/zh-tw/AGnAL.html#.WhrFVUqWaHs
[11]Ettoday新聞雲 (2018 January 29) 破解手機指紋辨識只需一塊「橘子皮」！ [Online].Available：https://www.ettoday.net/news/20180129/1102849.htm
[12]SCG (2010, March 14) RFID感應鎖[Online].Available：http://www.scglock.com/big5
[13]卿榮波 (2015, February 09) 電子市場5秒就能複製一張 [Online].Available：http://m.news.sina.com.tw/article/20150209/13820713.html
[14]Beseye (2017, June. 14) Beseye Pro雲端智慧攝影機 [Online].Available：https://www.beseye.com/tw/home
[15]小米公司 (2015, June 25) 小蟻智慧攝影機 [Online].Available：http://www.mi.com/tw/
[16]G. Sowjanya, and S. Nagaraju, “Design and implementation of door access control and security system based on IOT” in proceedings of International Conference on Inventive Computation Technologies (ICICT), Coimbatore, India, 26-27 Aug. 2016, pp.1-4.
[17]R. Ibrahim, and Z. M. Zin, “Study of automated face recognition system for office door access control application”, in proceedings of International Conference on Communication Software and Networks (ICCSN), Xi'an, China, 27-29 May 2011, pp.132-136
[18]M. Sahani, C. Nanda, and A. K. Sahu, “Web-based online embedded door access control and home security system based on face recognition,” in proceedings of International Conference on Circuit, Power and Computing Technologies (ICCPCT), Nagercoil, India, 19-20 March 2015, pp. 1-6.
[19]A. B. Dorothy, S. B. R. Kumar, and J. J. Sharmila, “IoT Based Home Security through Digital Image Processing Algorithms,” in proceedings of World Congress on Computing and Communication Technologies (WCCCT), Tiruchirappalli, India, 2-4 Feb. 2017, pp. 20-23.
[20]L. Zhengzheng, L. Lianrong, and W. Yong, “Development of face recognition system based on PCA and LBP for intelligent anti-theft doors,” in proceedings of International Conference on Computer and Communications (ICCC), Chengdu, China, 14-17 Oct. 2016, pp. 341-346.
[21]R. Endluri, M. Kathait, and K. C. Ray, “Face recognition using PCA on FPGA based embedded platform,” in proceedings of International Conference on Control, Automation, Robotics and Embedded Systems (CARE), Jabalpur, India, 16-18 Dec. 2013, pp. 1-4.
[22]S. N. Borade, R. R. Deshmukh, and S. Ramu, “Face recognition using fusion of PCA and LDA: Borda count approach,” in proceedings of Mediterranean Conference on Control and Automation (MED), Athens, Greece, 21-24 June 2016, pp. 1164-1167.
[23]N. S. Tummala, and P. C. Sekhar, “Face recognition using PCA and geometric approach,” in proceedings of International Conference on Computing Methodologies and Communication (ICCMC), Erode, India, 18-19 July 2017, pp. 562-565.
[24]E. U. Haq, X. Huarong, and M. I. Khattak, “Face Recognition by SVM Using Local Binary Patterns,” in proceedings of Conference on Web Information Systems and Applications (WISA), Liuzhou, Guangxi Province, China, 11-12 Nov. 2017, pp. 172-175.
[25]W. Yiding, X. Wei, and Y. Xiaojie, “An automatic physical access control system based on hand vein biometric identification,” in proceedings of IEEE Transactions on Consumer Electronics, IEEE Consumer Electronics Society,15 October 2015, pp. 320-327.
[26]N. R. Borkar, and S. Kuwelkar, “Real-time implementation of face recognition system,” in proceedings of International Conference on Computing Methodologies and Communication (ICCMC), Erode, India, 18-19 July 2017, pp. 249-255.
[27]C. Zijun, S. Tianwei, and C. Wenhua, “3D face recognition based on kinect depth data,” in proceedings of International Conference on Systems and Informatics (ICSAI), Hangzhou, China, 11-13 Nov. 2017, pp. 555-559.
[28]Q. Akariman, A. N. Jati, and A. Novianty, “Face recognition based on the Android device using LBP algorithm,” in proceedings of International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC), Bandung, Indonesia, Indonesia, 27-29 Aug. 2015, pp. 166-170.
[29]N. A. Hussein, and I. A. Mansoori, “Smart Door System for Home Security Using Raspberry pi3,” in proceedings of International Conference on Computer and Applications (ICCA), Doha, United Arab Emirates, 6-7 Sept. 2017, pp. 395-399.
[30]B. Vaidya, A. Patel, A. Panchal, R. Mehta, K. Mehta, and P. Vaghasiya, “Smart home automation with a unique door monitoring system for old age people using Python, OpenCV, Android and Raspberry pi,” in proceedings of International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, 15-16 June 2017, pp. 82-86.
[31]C. Yong-Ping, C. Qi-Hui, and C. Kuan-Yu, “Low-cost face recognition system based on extended local binary pattern, ” in proceedings of International Automatic Control Conference (CACS), Taichung, Taiwan, 9-11 Nov. 2016, pp. 13-18.
[32]黃韋瀚，“結合五官特徵與深度資訊之人臉辨識系統”， 大同大學資訊工程研究所，碩士論文，2012。
[33]Pearson, K., “LIII. On Lines and Planes of Closest Fit to Systems of Points in Space,” Philosophical Magazine., 1 Nov. 1901, 2(6), pp. 559–572
[34]R.A., Fisher, “The use of multiple measurements in taxonomic problems, ” Annual Eugenics, 7: 179-188, 1936
[35]T. Ojala, M. Pietikäinen, and D. Harwood, “T. Ojala, M. Pietikäinen, and D. Harwood, ” in Proceedings of 12th International Conference on Pattern Recognition(ICPR), Jerusalem, Israel, Israel, 9-13 Oct. 1994, pp. 582-585.
[36]B. Hatipoglu and C. Köse, “Gender recognition from face images using PCA and LBP, ” in Proceedings of 9th International Conference on Electrical and Electronics Engineering (ELECO), Bursa, Turkey, 26-28 Nov. 2015, pp. 1258-1262.
[37]A. A. M. Hagar ,M. A. M. Alshewimy, and M. T. F. Saidahmed, “A new object recognition framework based on PCA, LDA, and K-NN, ” in Proceedings of 11th International Conference on Computer Engineering & Systems (ICCES), Cairo, Egypt, 20-21 Dec. 2016, pp. 141-146.
[38]Raspberry Pi (2016, February 29) raspberry pi 3 [Online].Available：https://www.raspberrypi.org/
[39]Arduino (2008, May 15) Arduino nano [Online].Available：https://www.arduino.cc/