(3.236.214.19) 您好!臺灣時間:2021/05/07 12:14
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:莊宜叡
研究生(外文):Yi-Jui Chuang
論文名稱:熱人臉影像辨識之特徵抽取與分類器比較分析
論文名稱(外文):A Comparative Analysis of Thermal Infrared Face Images Feature Extractions and Classifiers
指導教授:劉益宏劉益宏引用關係
指導教授(外文):Yi-Hung Liu
學位類別:碩士
校院名稱:中原大學
系所名稱:機械工程研究所
學門:工程學門
學類:機械工程學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:中文
論文頁數:122
中文關鍵詞:廣義鑑別分析線性鑑別分析核心主成份分析主成份分析支持向量機器熱人臉影像辨識
外文關鍵詞:kernel-based Generalized Discriminant AnalysisLinear Discriminant AnalysisKernel Principal Component AnalysisPrincipal Component AnalysisIR Thermal Face Recognition
相關次數:
  • 被引用被引用:1
  • 點閱點閱:658
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
自動化人臉辨識、表情辨識系統等人身安全相關的新興科技在近代中受到愈來愈多的重視,也吸引了許多學者從事相關的研究。然而在可見光人臉辨識系統中常常會因為光源改變直接影響了分類的成效,所以可見光人臉辨識需要控制光源因素,才能有良好的成效。本文將過去文獻中所使用的特徵抽取方法(主成份分析Principal Component Analysis、線性鑑別分析Linear Discriminant Analysis、廣義鑑別分析Generalized Discriminant Analysis)且加入了核心主成份分析(Kernel Principal Component Analysis)運用到熱人臉影像做統合性的比較。在本文中,我們加入了支持向量機(SVM)分類器與先前所使用的分類器(最近平均分類器和K個最近鄰居分類器)進行比較。由特徵抽取比較實驗結果顯示,由分類成效可知資料點先經由核函數映射至高維特徵空間中進行特徵抽取,比直接在輸入空間中進行特徵抽取來得好。在分類器比較方面,將SVM運用在熱人臉影像辨識所得到的分類成效均比其他的分類器好,同時也證明直接運用熱影像的灰階值也可得到很高的分類率。本文中建立了中原大學熱紅外人臉影像資料庫,其中包含50個人,每個人60張熱影像照片,總共包含3000張熱影像照片。每人隨機挑選10張影像進行實驗。由實驗結果可得知對於包含人臉輪廓的資料分別運用主成份分析、核心主成份分析、線性鑑別分析和廣義鑑別分析分類率可高達100%,其中分類器為SVM。對於未包含人臉輪廓的資料使用SVM分類器,配合廣義鑑別分析分類率為99.2%,而配合核心主成份分析分類率可高達100%。
Fully automatic face and expression recognition systems have received increasingly attention in recently years. However, the classification performance in the visible light face recognition system is often directly affected by the light source changed. Therefore, the visible light face recognition must control the factors of the light source to get the better results. This thesis used the previous feature extraction methods (Principal Component Analysis, Linear Discriminant Analysis, and Generalized Discriminant Analysis) and joined the Kernel Principal Component Analysis to apply to the thermal face images to make the comprehensive comparison. In this thesis, we joined the Support Vector Machine (SVM) classifier and the previous classifiers (Nearest Mean Classifier and K Nearest Neighbor Classifier) for the comparison. Comparing the SVM classifier with the others ,the classification performance using it in the thermal imagery face recognition is better than the others, and the result also establishes that directly using the gray-level values of the thermal images to classify can get higher classification rates. This thesis establishes the thermal infrared face image database of Chung Yuan Christian University which includes 50 individuals, each person 60 thermal images, totally 3000 images. The results show that using the images containing face contours using PCA, KPCA, LDA and GDA respectively and using the SVM classifier can achieve 100% of the classification rate. For the images do not contain the face contours, the classified rate using the SVM classifier with GDA is 99.2 percent, and with KPCA can reach as higher as 100%.
目錄
中文摘要-------------------------------------------------------------I
Abstract-------------------------------------------------------------II
誌謝-----------------------------------------------------------------III
目錄-----------------------------------------------------------------IV
圖目錄---------------------------------------------------------------VII
表目錄---------------------------------------------------------------X
***
第一章 緒論----------------------------------------------------------1
1.1 前言-------------------------------------------------------------1
1.2 研究動機與目的---------------------------------------------------2
1.3 文獻回顧---------------------------------------------------------3
1.4 研究方法---------------------------------------------------------4
1.5 本論文架---------------------------------------------------------5

第二章 熱影像的介紹--------------------------------------------------7
2.1 何謂紅外線?-----------------------------------------------------7
2.2 紅外線的種類和不同之處-------------------------------------------10
2.3 紅外線優缺點及應用-----------------------------------------------11

第三章 研究理論------------------------------------------------------14
3.1 影像前處理技術---------------------------------------------------14
3.1.1 熱影像正規化---------------------------------------------------14
3.1.2 熱影像二值化---------------------------------------------------14
3.1.3 形態學處理-----------------------------------------------------15
3.1.4 連通物件標籤法-------------------------------------------------17
3.1.5 邊緣抽取演算法-------------------------------------------------18
3.1.6 直方圖等化-----------------------------------------------------20
3.1.7 影像縮放-------------------------------------------------------21
3.2 圖樣相似性測量---------------------------------------------------24
3.2.1 圖樣相似性測量的基本觀念---------------------------------------24
3.2.2 K個最近鄰居分類器----------------------------------------------24
3.2.3 最近平均分類器-------------------------------------------------25
3.2.4 計算距離方的法-------------------------------------------------26
3.3 支持向量機器-----------------------------------------------------27
3.3.1 最佳化理論-----------------------------------------------------27
3.3.2 最佳分離超平面-------------------------------------------------29
3.3.3 建構最佳分離超平面---------------------------------------------30
3.4 特徵抽取---------------------------------------------------------40
3.4.1 主成份分析-----------------------------------------------------40
3.4.2 核心主成份分析-------------------------------------------------42
3.4.3 線性識別分析---------------------------------------------------45
3.4.4 廣義判別分析---------------------------------------------------49
3.5 交叉驗證---------------------------------------------------------54
3.6 最佳參數搜尋法-格子搜尋演算法------------------------------------55

第四章 實驗系統架構與流程分析----------------------------------------56
4.1 熱人臉影像辨識系統描述-------------------------------------------56
4.2熱人臉影像資料庫的介紹--------------------------------------------57
4.2.1 軟體硬體的介紹-------------------------------------------------57
4.2.2 環境的設置-----------------------------------------------------60
4.2.3 拍照的變異-----------------------------------------------------60
4.3 熱影像前處理-----------------------------------------------------63
4.3.1 熱影像正規化---------------------------------------------------63
4.3.2 熱人臉影像剪裁-------------------------------------------------65
4.3.3 熱人臉影像剪裁之討論-------------------------------------------74
4.4 實驗設計---------------------------------------------------------75
第五章 軟硬體系統說明及實驗結果與討論--------------------------------77
5.1 系統軟硬體說明---------------------------------------------------77
5.2 比較徵抽取的方法-------------------------------------------------77
5.3 圖樣未經特徵抽取的分類器比較與討論-------------------------------79
5.4 圖樣經過PCA特徵抽取的分類器比較與討論----------------------------84
5.5 圖樣經過LDA特徵抽取的分類器比較與討論----------------------------89
5.6 圖樣經過KPCA特徵抽取的分類器比較與討論---------------------------93
5.7 圖樣經過GDA特徵抽取的分類器比較與討論----------------------------98
第六章 結論與未來研究方向--------------------------------------------104
6.1 結論-------------------------------------------------------------104
6.2 未來工作方向-----------------------------------------------------105
參考文獻-------------------------------------------------------------106

圖目錄
圖2.1 電磁波頻譜(Spectrum of Electromagnetic Radiation)---------------7
圖2.2 熱輻射曲線(Thermal radiation curves)----------------------------9
圖3.1 熱影像正規化之結果----------------------------------------------14
圖3.2 熱影像二值化之結果----------------------------------------------15
圖3.3 3×3結構元素-----------------------------------------------------15
圖3.4 形態學處理之結果------------------------------------------------16
圖3.5 4鄰居位置圖-----------------------------------------------------17
圖3.6 連通物件標籤法示意圖--------------------------------------------17
圖3.7 BEA方向示意圖---------------------------------------------------18
圖3.8 方向值J所對應影像中的位置---------------------------------------19
圖3.9 邊緣抽取之結果--------------------------------------------------19
圖3.10 直方圖等化之結果-----------------------------------------------21
圖3.11 最近相鄰內插法說明圖-------------------------------------------22
圖3.12 雙線性內插法說明圖---------------------------------------------23
圖3.13 雙立方內插法說明圖---------------------------------------------23
圖3.14 K個最近鄰居分類器示意圖(K=1)-----------------------------------25
圖3.15 K個最近鄰居分類器示意圖(K=3)-----------------------------------25
圖3.16 最近平均分類器示意圖-------------------------------------------26
圖3.17 分離平面說明圖-------------------------------------------------29
圖3.18 支持向量說明圖-------------------------------------------------33
圖3.19 彈性變數與最佳分離平面的關係圖---------------------------------34
圖4.1 熱人臉影像辨識系統實驗架構流程示意圖----------------------------56
圖4.2 FLIR PHOTON 320外觀---------------------------------------------58
圖4.3 FLIR PHOTON 320 配件--------------------------------------------58
圖4.4 National Instruments PCI-1422 擷取卡----------------------------59
圖4.5 Photon OEM GUI操作介面圖----------------------------------------59
圖4.6 環境的設置------------------------------------------------------60
圖4.7 中原大學熱影像人臉資料庫示意圖----------------------------------61
圖4.8 中原大學熱影像人臉資料庫部份影像--------------------------------62
圖4.9 熱影像正規化流程圖----------------------------------------------63
圖4.10 熱影像正規化之結果---------------------------------------------63
圖4.11 資料庫經過正規化的部份影像-------------------------------------64
圖4.12 第一階段熱人臉影像剪裁流程圖-----------------------------------65
圖4.13 熱影像二值化之結果---------------------------------------------66
圖4.14 形態學處理之結果1----------------------------------------------66
圖4.15 形態學處理之結果2----------------------------------------------66
圖4.16 經過修剪後形態學熱影像的結果-----------------------------------67
圖4.17 邊緣抽取處理的結果---------------------------------------------67
圖4.18 第一階段剪裁的熱人臉影像結果1----------------------------------68
圖4.19 第一階段剪裁的熱人臉影像結果2----------------------------------68
圖4.20 部份熱人臉影像經過第一階段熱人臉剪裁結果之集合-----------------69
圖4.21 第二階段熱人臉剪裁流程圖---------------------------------------70
圖4.22 直方圖等化之結果-----------------------------------------------70
圖4.23 第二階段熱人臉水平投影結果-------------------------------------71
圖4.24 第二階段熱人臉剪裁之結果---------------------------------------71
圖4.25 部份影像經過第二階段熱人臉剪裁結果之集合-----------------------72
圖4.26 第三階段熱人臉影像處理流程圖-----------------------------------73
圖5.1 IR_1&IR_2未經特徵抽取+NMC分類率比較表---------------------------80
圖5.2 IR_1&IR_2未經特徵抽取+K-NN分類率比較表--------------------------81
圖5.3 IR_1未經特徵抽取+SVM(當σ固定,C對於分類率的影響)---------------82
圖5.4 IR_2未經特徵抽取+SVM(當σ固定,C對於分類率的影響)---------------83
圖5.5 IR_1&IR_2經過PCA特徵抽取+NMC分類率比較表------------------------85
圖5.6 IR_1&IR_2經過PCA特徵抽取+K-NN分類率比較表-----------------------85
圖5.7 IR_1經過PCA特徵抽取+SVM(當σ固定,C對於分類率的影響)------------87
圖5.8 IR_2經過PCA特徵抽取+SVM(當σ固定,C對於分類率的影響)------------87
圖5.9 IR_1&IR_2經過LDA特徵抽取+NMC分類率比較表------------------------89
圖5.10 IR_1&IR_2經過LDA特徵抽取+K-NN分類率比較表----------------------90
圖5.11 IR_1經過LDA特徵抽取+SVM(當σ固定,C對於分類率的影響)-----------92
圖5.12 IR_2經過LDA特徵抽取+SVM(當σ固定,C對於分類率的影響)-----------92
圖5.13 IR_1&IR_2經過KPCA特徵抽取+NMC分類率比較表----------------------94
圖5.14 IR_1&IR_2經過KPCA特徵抽取+K-NN分類率比較表---------------------94
圖5.15 IR_1經過KPCA特徵抽取+SVM(當σ固定,C對於分類率的影響)----------96
圖5.16 IR_2經過KPCA特徵抽取+SVM(當σ固定,C對於分類率的影響)----------97
圖5.17 IR_1&IR_2經過GDA特徵抽取+NMC分類率比較表-----------------------99
圖5.18 IR_1&IR_2經過GDA特徵抽取+K-NN分類率比較表----------------------99
圖5.19 IR_1經過GDA特徵抽取+SVM(當σ固定,C對於分類率的影響)-----------101
圖5.20 IR_2經過GDA特徵抽取+SVM(當σ固定,C對於分類率的影響)-----------101

表目錄
表 2.1 紅外線輻射源---------------------------------------------------11
表 3.1 常用的核心函數表-----------------------------------------------40
表 4.1 FLIR PHOTON 320規格表------------------------------------------57
表 4.2 FLIR PHOTON 320 配件表-----------------------------------------58
表 5.1 記錄每種特徵抽取參數實驗表-------------------------------------78
表 5.2 IR_1未經特徵抽取+SVM實驗結果-----------------------------------81
表 5.3 IR_2未經特徵抽取+SVM實驗結果-----------------------------------82
表 5.4 IR_1&IR_2未經過特徵抽取實驗結果--------------------------------83
表 5.5 IR_1&IR_2未經過特徵抽取NMC與K-NN的分類率比較-------------------84
表 5.6 IR_1經過PCA特徵抽取+SVM實驗結果--------------------------------86
表 5.7 IR_2經過PCA特徵抽取+SVM實驗結果--------------------------------86
表 5.8 IR_1&IR_2經過PCA特徵抽取實驗結果-------------------------------88
表 5.9 IR_1&IR_2經過PCA特徵抽取NMC與K-NN的分類率比較------------------88
表 5.10 IR_1經過LDA特徵抽取+SVM實驗結果-------------------------------91
表 5.11 IR_2經過LDA特徵抽取+SVM 實驗結果------------------------------91
表 5.12 IR_1&IR_2經過LDA特徵抽取實驗結果------------------------------93
表 5.13 IR_1&IR_2經過LDA特徵抽取NMC與K-NN的分類率比較-----------------93
表 5.14 IR_1經過KPCA特徵抽取+SVM實驗結果------------------------------95
表 5.15 IR_2經過KPCA特徵抽取+SVM實驗結果------------------------------96
表 5.16 IR_1&IR_2經過KPCA特徵抽取實驗結果-----------------------------97
表 5.17 IR_1&IR_2經過KPCA特徵抽取NMC與K-NN的分類率比較----------------97
表 5.18 IR_1經過GDA特徵抽取+SVM實驗結果-------------------------------100
表 5.19 IR_2經過GDA特徵抽取+SVM實驗結果-------------------------------100
表 5.20 IR_1&IR_2經過GDA特徵抽取實驗結果------------------------------102
表 5.21 IR_1&IR_2經過GDA特徵抽----------------------------------------102
表 5.22 分類器測試時間------------------------------------------------103
[1]S. R. Hunter, G. Mauter, L. Jaing, and G. Simelgor, “High-sensitivity uncooled microcantilever infrared imaging arrays,” Proeeding SPIE, vol.6206, pp. 1-12, 2006.
[2]F. J. Prokoski, “History, current status, and future of infrared identification, ” in IEEE Workshop on Computer Vision Beyond the Visible Spectrum, Hilton Head, 2000.
[3]Y. Yoshitomi, T. Miyaura, S. Tomita, and S. Kimura, “Face identification using thermal image processing,” Proceeding. IEEE International Workshop Robot and Human Communication, pp. 374–379, 1997.
[4]D. Socolinsky, A. Selinger and J. Neuheisel, “Face recognition with visible and thermal infrared imagery, ” Computer Vision and Image Understanding, vol. 91, pp. 72–114, 2003.
[5]D. Socolinsky and A. Selinger, “Thermal face recognition in an operational scenario, ” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2004.
[6]S. G. Kong, J. Heo, B. R. Abidi, J. Paik, and M.A. Abidi, “Recent advances in visual and infrared face recognition—a review, ” Computer Vision and Image Understanding, vol. 97, pp. 103–135, 2005.
[7]Y. Adini, Y. Moses, and S. Ullman, “Face recognition: the problem of compensating for changes in illumination direction, ” IEEE Transactions Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 721–732, 1997.
[8]Y. I. Tian, T. Kanade, and J.F. Cohn, “Recognizing action units for facial expression analysis, ” IEEE Transactions Pattern Analysis Machine Intelligence, vol. 23, no. 2, pp. 97–115, 2001.
[9]J. Ben-Arie and D. Nandy, “A volumetric/iconic frequency domain representation for objects with application for pose invariant face recognition, ” IEEE Transactions Pattern
- 107 -
Analysis Machine Intelligence , vol. 20, no. 5, pp. 449–457, 1998.
[10]F. J. Prokoski, “Method and apparatus for recognizing and classifying individuals based on minutiae, ” United Staest Patent: 6173068B1, 2001.
[11]P. Buddharaju, I. Pavlidis, and I. A. Kakadiaris, “Face recognition in the thermal infrared spectrum,” Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition Workshop, pp. 133-133, Washington DC, USA, 2004.
[12]P. Buddharaju, I. Pavlidis, and P. Tsiamyrtzis, “Physiology-based face recognition using the vascular network extracted from thermal facial images: a novel approach,” Proceedings of IEEE Advanced Video and Signal Based Surveillance, Lake Como, Italy, pp. 354-359, 2005.
[13]C. Eveland, D. Socolinsky, and L. Wolff, “Tracking human faces in infrared video,” Proceeding IEEE Workshop Computer Vision Beyond and Visible Spectrum: Method Application, 2001.
[14]J. Dowdall, I. Pavlidis, and G. Bebis, “A face detection method based on multi-band feature extraction in the near-IR spectrum,” Proceeding IEEE Workshop in Computer Vision Beyond the Visible Spectrum: Method an Application, 2001.
[15]J. Dowdall, I. Pavlidis, and G. Bebis, “Face detection in the near-IR spectrum,” Image and Vision Computing, vol. 21, no. 7, pp. 565–578, 2003.
[16]I. Pavlidis, P. Symosek, B. Fritz, M. Bazakos, and N. Papanikolopoulos, “Automatic detection of vehicle occupants—the imaging problem and its solution,” Machine Vision and Applications, vol. 11, no. 6, pp. 313–320, 2000.
[17]F. Prokoski, “Disguise detection and identification using infrared imagery,” Proceedings of SPIE, Optics, and Images in Law Enforcement II. A.S. Hecht, Ed, Arlington, VA, pp. 27-31, 1982.
[18]I. Pavlidis and P. Symosek, “The imaging issue in an automatic face/disguise detection system,” Proceeding IEEE Workshop Computer Vision Beyond the Visible Spectrum: Methods and Application, pp. 15–24, 2000.
- 108 -
[19]D. Socolinsky and A. Selinger, “A comparative analysis of face recognition performance with visible and thermal infrared imagery,” Proceeding IEEE Patten Recognition, 16th International Conference 4 pp. 217–222, 2002.
[20]S. Q. Wu, W. Song, L. J. Jiang, S. Xie, F. S. L Pan, W. Y. Yau, and S. Ranganth, “Infrared face recognition by using blood perfusion data,” Proceeding Audio- and Video-based Biometric Person Authentication, NY, July, (AVBPA), pp. 320-328, 2005.
[21]S. Q. Wu, Z. H. Gu, K. A. Chia, and S. H. Ong, “Infrared facial recognition using modified blood perfusion,” Proceedings IEEE Information, Communication & Signal Processing,6th International Conference on pp.1-5, Singapore, 2007.
[22]J. Wang, J. Liang, H. Hu, Y. Li, and B. Feng, “Performance evaluation of infrared and visible image fusion algorithms for face Recognition,” Proceeding the 2007 International Conference on Intelligent Systems and Knowledge Engineering Chengdu, pp. 15-16, 2007.
[23]Kar-Ann Toh, Youngsung Kim, Sangyoun Lee, and Jaihie Kim, “Fusion of visual and infra-red face scores by weighted power series,” Proceeding Pattern Recognition, vol. 29, pp. 603-615, 2008.
[24]A. Selinger and D. Socolinsky, Appearance-based facial recognition using visible and thermal imagery: a comparative study, Technical Report 02-01, Equinox Corporation, 2001.
[25]I. Alexandropoulos and M. P. Fargues, “Uncooled infrared imaging face recognition using kernel-based feature vector selection,” 40th Asilomar Conference on Signals, Systems and Computers, pp. 613-617, 2006.
[26]Dong-Ho Lee, “Thermal analysis of intergrated-circuit chips using thermographic imageing techniques,” IEEE Transactions on Instrumentation and Measurement, vol. 3, no. 6, pp. 824-829, 1994.
[27]維基百科 URL: http://zh.wikipedia.org/wiki/%E7%BA%A2%E5%A4%96%E7%BA%BF.
- 109 -
[28]繆紹綱,數位影像處理活用-Matlab,全華科技圖書股份有限公司,1999年。
[29]繆紹綱,數位影像處理,普林斯頓國際有限公司,2004年。
[30]R. Jain, R. Kasturi, B. G. Schunck, Machine Vision, McGraw-Hill, New York, 1995.。
[31]Y. H. Liu, Feature analysis and classifier design and their applications to pattern recognition and data mining, Ph.D. Dissertation, Department of Mechanical Engineering, National Taiwan University, 2003.
[32]呂學信,結合SVDD及SVM分類器於會員人臉確認之研究, 私立中原大學機械工程研究所碩士學位論文,2007.
[33]R. C. Gonzalez, R. E. Woods, Digital Image Processing, 2nd Edition, Prentice-Hall, Inc., 2002.
[34]M. Unser, A. Aldroubi, and M. Eden, “Enlargement or reduction of digital images with minimum loss of information,” IEEE Transactions on Image Processing, vol. 4, pp. 247-258, Mar. 1995.
[35]K. Jensen and D. Anastassiou, “Subpixel edge localization and the interpolation of still images,” IEEE Transactions On Image Processing, Vol. 4, pp. 285-295, Mar. 1995.
[36]M. Sonka, V. Hlavac, and R. Boyle, “Image porcessing, analysis, and machine vision ", Second Edition, PWS Pubishing, pp. 67-68, 1999.
[37]楊淑瑩,模式識別與智能計算——Matlab技術實現, 電子工業出版社,2008年。
[38]D. I. Domboulas, Infrared imaging face recognition using nonlinear kernel-based classifiers, Electrical Engineer Thesis, Naval Postgraduate School, Monterey, CA, 2004.
[39]V. Vapnik, The Nature of Statistical Learning Theory, New York: Springer-Verlag, 1995
[40]K. I. Diamantaras and S. Y. Kung, Principal Component Neural Networks: Theory and Applications, John Wiley and Sons, New York , 1996.
[41]陳衍廷,應用核心主成份分析及非平衡式SVM於影像中人臉偵測之研究, 私立中原大學機械工程研究所碩士學位論文, 2006.
[42]Richard O. Duda, Peter E. Hart, and David G. Stork Pattern, Classification Second Edition, WILEY-INTERSCIENCE
- 110 -
[43]J. Duchene and S. Leclercq, “An Optimal Transformation for Discriminant and Principal Component Analysis,” IEEE Transactions On Pattern Analysis and Machine Intelligence, vol. 10, no 6, pp. 978-983, 1988.
[44]G. Baudat and F. Anouar, “Generalized Discriminant Analysis Using a Kernel Approach,” Neural Computation, vol. 12, no. 10, pp. 2385-2404, 2000.
[45]C. S. Ong, A. J. Smola, and R. C. Williamson, “Hyperkernels,” In Neural Information Processing Systems, vol.15, pp. 495-502, 2002.
[46]C. K. Lee, Infrared face recognition, Naval Postgraduate School Thesis, 2004
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊
 
系統版面圖檔 系統版面圖檔