臺灣博碩士論文加值系統

本研究的目的在於探討如何利用現今熱門的數位影像處理技術，給予復健者在起立復健的療程中，提供一個安全性上的即時監控，並且能夠給予復健師分析復健者復健進度的系統。
本文中我們提出一個想法，將目前大部分僅提供監看與錄影功能的監視系統，導入了人臉偵測與色彩辨識的功能，並對監控系統訂定了一套規則，系統如果偵測到可能發生危險時夠主動發出預警，將此應用在起立復健的療程上。
首先利用CCD來監控復健者的復健過程，並且在復健患者的膝蓋各貼上一個容易辨識的紅色特徵點，利用數位影像處理的技術，偵測這兩個特徵點並計算出兩點的連線，將此作為起立動作的重心轉移參考線；同時偵測復健者的頭髮顏色，並將此假定為復健者上半身的重心點，配合參考線的位置資訊做計算並且紀錄。
當復健者的重心點超過參考線的位置時，復健者可以較容易的達成起立復健的動作，相對的超過參考線位置太多，反而容易使的復健者失去平衡而跌倒。在此時監控系統的工作便是計算一個預警機制，計算復健者的復健動作是否會失去平衡而跌倒，提供給在旁的復健師以減少意外的產生。
此外，透過紀錄復健者重心移動的距離、移動到參考線的成功次數、以及成功站立的次數，更能讓復健師較容易進行復健進度的評估工作。

關鍵字：起立復健、監控系統、色彩辨識

The purpose of this study, Is to explore how to make use of today's popular digital image processing technology, in Standing rehabilitation of Treatment process, To provide a secure real-time monitoring, And Given to rehabilitation and analyzes the progress of the rehabilitation system.
In this paper, we propose an idea, Most of the current monitor is only available with the video surveillance system function, Into the face detection and color recognition function, Joined the human face detection and color recognition function, And a set of rules set out, If the system detects a potentially dangerous enough to take the initiative to issue a warning when, Be used in the course of rehabilitation to stand on, Used in the process of rehabilitation standing.
First, the use of CCD to monitor the rehabilitation process, And pastes on the red characteristic point which in the patient knee easy to recognize, The use of digital image processing technology, Detects these two characteristic points and calculates two spots the segment, As the focus shifted to stand and move the reference line; Rehabilitation at the same time detect the hair color, And this hypothesis for recovery upper part's center of gravity spot, With reference to the location of information line to do the calculation and record.
When the center of gravity spot surpasses the reference line the position, Make it easier for patients to achieve the rehabilitation of the action to stand up, The relative position of much more than the reference line, It is easy for patients losing their balance. At this time, Monitoring system is the calculation of the work of an early-warning mechanism, Calculation of rehabilitation patients will move out of balance and fall, To rehabilitation in the next division in order to reduce accidents arising from.
Besides, Rehabilitation through the records of persons moving from the center of gravity, Moved to the success of the number of reference lines, The number of standing and successful, Rehabilitation division allow easier assessment of the progress of rehabilitation work

Keyword：standing rehabilitation, monitoring system, color identification

誌 謝 iv
摘 要 v
英文摘要 vi
目　錄 viii
圖　目　錄 x
表　目　錄 xii
第一章 概論 1
1.1研究背景 1
1.2 研究動機 1
1.3 研究目的 1
1.4 研究方法 2
1.5 文獻探討 2
1.6 論文架構 4
第二章 生理學探討 5
2.1 起立動作 5
2.2 腦中風 6
2.2.1 腦中風的症狀 8
2.2.2 腦中風的治療與復健 8
第三章 系統架構設計與影像處理 10
3.1 系統架構 10
3.2 色彩空間 10
3.2.1 Normalized RGB色彩空間 11
3.2.2 HSV色彩空間 13
3.2.3 YCbCr色彩空間 14
3.3影像二值化 15
3.3.1單一閥值 16
3.3.2雙重閥值 16
3.4 影像形態學 17
3.4.1 膨脹 17
3.4.2 侵蝕 19
3.4.3 開啟 21
3.4.4 關閉 22
第四章 演算法設計與實驗 24
4.1 CCD1演算法流程 24
4.1.1 紅點偵測 26
4.1.2 髮色偵測 27
4.2 CCD2演算法流程 30
4.2.1 人臉偵測 30
4.2.2 移動高度偵測 34
4.3 實驗結果 35
第五章 結論 37
參考文獻 38
作者資料 40

[1]Yu-Hua Yu, Guan-Chung Yen, Yu-Jen Lee “ A surveillance system of standing rehabilitation”2009 International Conference on Gerontic Technology and Service Management, May 19-21, 2009
[2]賴郁芬 2000 「肌電回饋引發功能性電刺激對慢性中風病人上肢運動及功能恢復之效果」中山醫學院醫學研究所碩士論文。
[3]陳昭仁 2005 「供偏癱患者平衡訓練之功能性電刺激回饋控制系統設計與臨床評估」中原大學醫學工程學系碩士論文。
[4]陳羿辰 2003 「供偏癱患者平衡訓練之重心迴饋控制電刺激系統」國立台灣大學電機工程學研究所碩士論文。
[5]劉冠佑 視覺回饋之坐姿及站姿矯正訓練教導系統。
[6]陳叔煌 2006 「醫院候診區座椅高度對於老年人起身與坐下行為之影響」明治科技大學工程管理研究所碩士論文。
[7]洪維憲 2009 「高齡者輔助起身坐下座椅設計研究」台北科技大學創新設計研究所碩士論文。
[8]中華民國行政院衛生署 http://www.doh.gov.tw/cht2006/index_populace.aspx
[9]Hu HH, Chu FL, Chiang BL, et al. Prevalence of stroke in Taiwan. Stroke 1989；20:858-63.
[10]張淑鳳、蘇哲能、洪祖培。臺灣地區腦血管疾病流行病學之研究現況。臺灣醫誌 1993；92：S112-20。
[11]ERIC P. WIDMAIER 人體生理學 美商麥格羅希爾國際股份有限公司 2005。
[12]Bohannon RW. Muscle strength changes in hemiplegic stroke patients during　inpatient rehabilitation. J Neurolo Rehabil 1998;2:163-165..
[13]許鵬飛 2002 「供中風患者步行訓練之膝關節控制器設計」中原大學醫學工程學系碩士論文
[14] 繆紹綱　譯　數位影像處理：運用MATLAB 東華書局股份有限公司 2005
[15] ALASDAIR MCANDREW 數位影像處理 THOMSON 2005
[16]M. Soriano, S. Huovinen, B. Martinkauppi, and M. Laaksonen, “Using the Skin Locus to Cope with Changing Illumination Conditions in Color-Base Face Tracking”, Proc. of IEEE Nordic Signal Processing Symposium, pp. 383-386,2000.
[17]陳文俊 2003 「人臉辨識及其在家用機器人與人互動之研究」國立交通大學電機與控制學系碩士論文。
[18]楊明峰 2008 「基於銀髮族照顧之智慧型監視系統」南開科技大學福祉科技與服務管理所。
[19]Meng-Fung Yang “Implement a Smart Digital Surveillance System Based on Caring for the Elder.” Nan Kai University of Technology in for the Degree of Master in Graduate School of Gerontic Technology and Service Management June 2008.
[20]林維謙、吳瑞堯，「植基於支援向量機之人臉偵測與人臉辨識」，世新大學管理學院資訊管理學系碩士學位論文，2007。
[21]Gracia C., and G. Tziritas, “Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis”, Proc. of IEEE Transactions on Multimedia,Vol 1,NO 3,1999.
[22]Garcia C., G. Zikos, and G. Tziritas, “Face Detection in Color Images using Wavelet Packet Analysis, Multimedia Computing and Systems”, Proc. of IEEE International Conference,Vol 1,pp. 703- 708,1999.
[23]Najafi, B., Aminian, K., Loew, F., Blanc, Y. and Robert, P.A., 2002.“Measurement of stand-sit and sit-stand transitions using a miniature gyroscope and its application in fall risk evaluation in the elderly.” IEEE Transactions on Biomedical Engineering, Vol.49, p.843-851.
[24]Rein-Lien Hsu, “Face Detection in Color Image.” IEEE Transactions on pattern analysis and machine intelligence Vol. 24,No 5,May 2002;p696-706.
[25]Wen-Jun Chen. “Face Recognition and Its Applications to Human-Robot Interaction.” National Chiao Tung University in for the Degree of Master in Electrical and Control Engineering June 2003;p.11-12.
[26]L. G. Shapiro, G. C. Stockman, Computer Vision, pp.65-68, Prentice –Hall,NJ,2001.
[27]Rudra N. Hota, Vijendran Venkoparao and Saad Bedros” Face Detection by using Skin Color Model based on One Class Classi'er” 9th International Conference on Information Technology (ICIT'06) 2006.
[28]V. Vezhnevets, V Sazonov, and A. Andreeva, ”A Survey on Pixel Based Skin clor Detection Techniques”,Proc Graphicon, pp. 85-92, Moscow, Russia, Sept2003.
[29]Paul Viola and Michael Jones,”Robust real-time object detection”, International Journal of Computer Vision,2001.
[30]L. Mostafa and S Abdelazeem,”Face Detection Based on Skin Color Using Neural Networks”, GVIP 05 Conference, 19-21, Dec 2005.
[31]R. L. Hsu, M. A. Mottaleb and A. K. Jain,”Face Detection in Color Images”, IEEE Trans pattern Anal.Machine intell, vol 24, no. 5, May 2002.
[32]R. Xiao, M. J. Li and H. J. Zhang, ”Robust multipose Face Detection Images”, IEEE Trans on circutis and systems for video technology, vol. 14, no. 1, jan 2004.
[33]D.M.J. Tax, ”One-class classi'cation”, PhD thesis,Delft University of Technology, June 2001.