(3.238.235.155) 您好!臺灣時間:2021/05/16 08:18
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:張詩岳
研究生(外文):Chang Shih Yuen
論文名稱:人臉偵測系統與視窗介面設計
論文名稱(外文):Human Face Detection System And Graphical User Interface Design
指導教授:陶金旭
學位類別:碩士
校院名稱:國立中興大學
系所名稱:電機工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2001
畢業學年度:89
語文別:中文
論文頁數:87
中文關鍵詞:人臉偵測人臉辨識視窗介面動差偵測膚色分割ROI類神經模糊網路
外文關鍵詞:human face detectionhuman face recognitiongraphical user interfacemotion detectionskin segmentationregion of interestneuro-fuzzy network
相關次數:
  • 被引用被引用:6
  • 點閱點閱:268
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
人臉偵測在許多不同的應用中,是不可或缺的前置處理。藉由人臉成功的偵測,我們可以應用在人臉辨識、唇語辨識、視訊會議及人機介面等場合。由於人臉是一個複雜且又不穩定的圖形,這使得偵測人臉的困難度又大大增加。在這篇論文中,我們提出一套在自然景像中利用動差及膚色資訊來偵測人臉的視窗介面系統。由於人在影像中會因為心跳、呼吸或習慣性的抖動而照成動差,同時背景區域通常是不動的,所以我們可以利用動差偵測來獲知人臉大概的位置。另外,我們必須選擇一個適合膚色及非膚色分割的彩色模型,接著利用一類神經模糊網路-NEFCAR分割出膚色區域,而膚色區域就對應於人臉可能的位置。因此我們提出的人臉偵測方法是利用動差偵測以及膚色分割來找出ROI (Region of Interest),接著在利用類神經模糊網路-NEFCAR來完成人臉的定位。此外,我們藉由瞳孔的定位來校正已找出人臉區域的大小及傾斜度,這使得進一步應用時,較為方便。實驗結果證明,我們的系統能能即時地在自然的景像中自動偵測出大小及傾斜度不同的人臉,並予以校正。
Human face detection is an indispensable preprocess in many applications. Human face detection can be applied to several applications such as human face recognition, lip reading, video conferencing, and human-computer interaction. Due to the complexity and unstability of the patterns of human faces, it is difficult to detect human faces in an unconstrained environment. In this thesis, we design a graphical user interface system to detect human faces automatically. People have motion because of heartbeat, breathing, and habitual quivering. Therefore, we can use the technique of motion detection to find the approximate location of human faces. A proper color model is adopted to segment the image into skin and non-skin regions. A neuro-fuzzy network (NEFCAR) is trained to find the skin regions whose may contain human faces. In our human face detection system, motion detection and skin region segmentation are utilized to find the region of interest. Then the system uses the NEFCAR to find the precise positions of human faces. In addition, we use the eye positions to correct the size and tilt of the human faces. Experiment results show that our proposed human face detection system is robust and fast.
目錄
第一章緒論…………………………………………………1
1.1 前言……………………………….……………………….1
1.2 數位影像處理系統……….……………………………… 2
1.2.1 影像的擷取...………………………………………2
1.2.2 影像的儲存………………………………………...4
1.2.3 影像的處理………………………………………...5
1.2.4 影像的通訊………………………………………...6
1.2.5 影像的顯示………………………………………...6
1.3 人臉偵測與辨識系統的研究動機………………………..7
1.4 文獻回顧及探討…………………………………………9
1.5 論文大綱及架構………………………………………..11
第二章理論分析…………………………………………..13
2.1 影像分析系統……………………………………………13
2.2 識別的決策理論方法……………………………………14
2.2.1 簡介……………………………………………….14
2.2.2 匹配 — 最小距離分類器………………………...16
2.2.3 最佳統計分類器………………………………….17
2.2.4 類神經網路……………………………………….19
2.3 類神經模糊網路分類器 — NEFCAR……………………24
2.3.1 NEFCAR架構……………………………………..25
2.3.2 NEFCAR之訓練演算法……………………..…30
2.4 彩色模型…………………………………………………36
2.4.1 彩色基礎…………………………………………36
2.4.2 彩色模型轉換……………………………………38
第三章人臉偵測系統及視窗介面設計…………………48
3.1 前言………………………………………………………48
3.2視窗介面設計……………………………………………..50
3.2.1簡介...………………………..……………………..50
3.2.2如何設計視窗介面…………..…………………….51
3.3 動差偵測…………………………………………………54
3.4膚色偵測及分割…………………………………………56
3.5 利用動差偵測及膚色分割找出ROI……………………62
3.6 臉部定位(T-sharp Location)……………………………62
3.6.1 建立雙類別NEFCAR訓練樣本…………………63
3.6.2 以雙類別NEFCAR完成臉部定位………………66
3.7 瞳孔定位…………………………………………………67
3.8 對ROI之傾斜及大小校正………………………………71
第四章 實驗結果……………………………………………74
4.1 前言………………………………………………………74
4.2 實驗結果…………………………………………………74
4.3 執行時間…………………………………………………74
第五章 結論及未來發展……………………………………79
5.1 結論………………………………………………………79
5.2 未來發展…………………………………………………79
參考文獻(Bibliography)……………………………………81
圖目錄
圖 1.1 數位影像處理系統…………………………..………3
圖 2.1 影像分析系統………………………………………15
圖 2.2 兩個模式類的機率密度函數………………………18
圖 2.3 (a) 生物神經元模型…………………….………….20
圖 2.3 (b) 人工神經元模型………………..………………20
圖 2.4 類神經網路模型-以倒傳遞網路為例……..……….22
圖 2.5 M類別的NEFCAR架構圖………………….…26
圖 2.6 不同部位的膚色圖…...………………………….…40
圖 2.7 (a) 膚色輸入樣本…………………………………..40
圖 2.7 (b) 非膚色輸入樣本……………………………..…40
圖 2.8 RGB彩色模型……………………………………....41
圖 2.9 SPH彩色模型………………………………………44
圖 2.10 Lpro平面在立方空間為1的RGB彩色模型………45
圖 2.11 參考點與投影點之相對垂直及水平距離…………46
圖 2.12 膚色在彩色模型分布圖……………………………47
圖 3.1 人臉偵測系統流程圖………………………………49
圖3.2 用來編輯按鈕的放大圖…………….…………..…52
圖3.3 給按鈕一個Identifier………………………………52
圖3.4 決定函式名稱………………………………………53
圖 3.5 視窗功能表選單……………………………………55
圖 3.6 彩色影像序列其中兩張………..…………………..57
圖 3.7 動差影像………………………..…………….…….58
圖 3.8 膚色偵測與分割流程圖……………………………60
圖 3.9 膚色測試影像………………………………………61
圖 3.10 膚色分割結果…………………………………..…61
圖 3.11 掃描圖3.10膚色外框……………………………64
圖 3.12 人像偵測系統在視窗介面找到的ROI…………...64
圖 3.13 正負訓練樣本……………….…………………....65
圖 3.14 T字部位定位結果……………………………….67
圖 3.15 瞳孔遮罩…………………………………………..69
圖 3.16 膚色資訊宇瞳孔定位的示意圖………….……….70
圖 3.17 瞳孔定位及ROI校正的前後比較………………..73
表目錄
表4.1 實驗結果………………………………………………76
表4.2 執行時間………………………………………………78
參考文獻
[1]S.A. Sirohey, Human face segmentation and identification, Master’s thesis, University of Maryland, 1993.
[2]G. Yang and T.S. Huang, “Human face detection in a complex background”, Pattern Recognition, 27(1), Page(s): 53 —63, 1994.
[3]V. Govindaraju, S.N. Srihari, and D. B. Sher, “A computation model for face location”, In Proc. Computer Vision and Pattern Recognition, Page(s): 718 —721, 1990.
[4]T.K. Lenug, M.C. Burl, and P. Perona, “Finding faces in clustered scenes using random labeled graph matching”, In Proc. Computer Vision and Pattern Recognition, Page(s): 637 —644, Cambridge, Mass., Jun. 1995.
[5]K.K. Sung and T. Piggio, “Example-based learning for view-based human face detection”, In Proc.Image Understanding Workshop, Page(s): 843 —850, Monterey, Calif., Nov. 1994.
[6]K. Sobottka and I. Pitas,”Extraction of facial regions and features Using color and shape information”, In Proc. 13th International Conference Pattern Recognition, Page(s): 421 —425, Vienna, Austria, Aug. 1996.
[7]C.H. Lee, J.S. Kim and K.H. Park, “Automaic Human Face Location In a Complex Background Using Motion and Color Information”, Pergamon, Pattern Recognition, Volume: 29, No.11, Page(s): 1877 —1889, 1996.
[8]S.J. Mckenna, S. Gong, anf Y. Raja, “Modelling facial colour and identity with gaussian mixtures”, In Proc. Pattern Recognition. Volume: 31, No. 12, Page(s): 1883 —1892, 1998.
[9]J. Cai and A. Goshtasby, “Detecting human faces in color images”, ELSEVIER, Image and Vision Computing 18th Page(s): 63 —75, 1999.
[10]S.H. Kim, H.G. Kim and K.H. Tchah, “Object oriented face detection using colour transformation and range segmentation”, ELECTRONICS LETTERS, 14th Volume: 34, No. 10, May 1998.
[11]C. Garcia and G. Tziritas, “Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis”, IEEE Transaction on Multimedia, Volume: 1, No. 3, September 1999.
[12]N. Tsapatsoulis and S. Kollias, “Face Detection in Color Image and Video Sequences”, IEEE, 10th Mediterranean Electrotechnical Conference, MeleCon 2000, Volume: II.
[13]M. Fang, A. Singh, and M. Y. Chiu, “A fast method for eye localization”, Siemens Corporate Res. Tech. Rep. SCR-94-TR- 488, 1994.
[14]Pentland, B. Moghaddam and T. Starner“, View-based and modular eigenspaces for face recognition”, Technical Report No. 245 Perceptual Computing Section, Media Laboratory, MIT, 1994.
[15]S.H. Lin, S.Y. Kung, and L.J. Lin, ”Face recognition /detection by probabilistic decision-based neural network”, IEEE Trans. On Neural Networks, Volume: 8, No. 1, January, 1997
[16]R. Mariani, “Subpixellic Eyes Detection”, IEEE 1999 International Conference on Proceedings. Image Analysis and Processing, Page(s): 496 —501, 1999.
[17]W. Huang, Q. Sun, C. -P. Lam and J. -K. Wu, ” A Robust Approach to Face and Eyes Detection From Images With Cluttered Background”, 1998. Proceedings. Fourteenth International Conference on Pattern Recognition, Volume: 1, Page(s): 110 -113, 1998.
[18]C. Chen and S. -P. Chiang, “Detection of human faces in colour images”, IEE Proc.-Vis. Image Signal Process, Volume: 144, No. 6, December 1997.
[19]T. Darrel, B. Moghaddam, and A. P. Pentland, ”Active face tracking and pose estimation in an interactive room”, In Proc Computer Vision and Pattern Recognition, Page(s): 67 —72, San Francisco, California, Jun. 1996.
[20]H.A. Rowley, S. Baluja and T.K. Kanade, “Neural network-based face detection”, IEEE Trans. On Pattern Analysis and Intelligence, Volume: 20, No. 1, Page(s): 23 —37, January 1998.
[21]H. -C. Fu, P.S. Lai, R.S. Lou and H. -T. Pao, “Face Detection And Eye Location By Neural Network Based Color Segmentation”, Proceedings of the 2000 IEEE Signal Processing Society Workshop Neural Networks for Signal Processing X, 2000. Volume: 2, Page(s): 507 —516, 2000.
[22]C.T. Huang and O.R. Mitchell, “A Euclidean distance transform using grayscale morphology decomposition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume: 16, Page(s): 443 —448, April 1994.
[23]F.Y.-C. Shih and O.R. Mitchell, “A mathematical morphology approach to Euclidean distance transformation”, IEEE Transactions on Image Processing, Volume: 1, Page(s): 197 —204, April 1992.
[24]G. Yaorong and J.M. Fitzpatrick, “On the generation of skeleton from discrete Euclidean distance maps”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume: 18, Page(s): 1055 —1066, Nov. 1996.
[25]O. Richard, E. Peter and G. David, “Pattern Classification”, Second Edition, Page(s): 51 —53, 2000.
[26]J. Cartinhour, “A Bayes classifier when the class distributions come from a common multivariate normal distribution”, IEEE Transactions on Reliability, Volume: 41, Page(s): 124 —126, March 1992.
[27]H. -S. Wu, J. Gil and J. Barba, “Optimal segmentation segmentation of cell images”, IEE Proceedings- Vision, Image and Signal Processing, Volume: 145, Page(s): 50 —56, Feb. 1998.
[28]Robert H. -N., “Neurocomputing”, HNC, Inc. and University of California, San Diego, 1990.
[29]葉怡成, “類神經網路模式應用與實作”, 儒林, 1993.
[30]R. P. Lippman, ”An introduction to computing with neural nets”, IEEE ASSP Magazine, Page(s): 4-22, April 1978.
[31]D. Rumelhart, G.E. Hinton and R.J. Williams, “Learning internal representation by error propagation”, in Parallel Distributed Processing, Volume: 1, Page(s): 318 —362, 1986.
[32]N.B. Karayiannis, “Reformulated radial basis neural networkd trained by gradient descent”, IEEE Transactions on Neural Networks, Volume: 10, Page(s): 657 —671, May 1999.
[33]P. Baldi, “Gradient descent learning algorithm overview: a general dynamical systems perspective”, IEEE Transactions on Neural Networks, Volume: 6, Page(s): 182 —195, Jan. 1995.
[34]J. Hopfield and D. Tank, “Neural compuations of decisions in optimization problem”, Biological Cybernetics, Page(s): 141 —152, 1985.
[35]J.S. Taur and C.W. Tao, “An On-line Face Detection and Recognition System Using Neuro-Fuzzy Classifier”, In Proc., International Symposium on Multimedia Information Processing, Page(s): 297 —302, December 1998.
[36]J.S. Taur and C.W. Tao, “Face Detection Using Neuro-Fuzzy Classifier”, In Proc., International Symposium on Multimedia Information Processing, Page(s): 309 —314, December 1998.
[37]林鈺山, “模糊類神經網路在人像偵測與辨識之應用”, 中興大學電機工程研究所碩士論文, 1999.
[38]方良慧, “類神經模糊技術於乾癬影像分割之應用”, 中興大學電機工程研究所碩士論文, 2000.
[39]J. —S. R. Jang, C. —T. Sun and E. Mizutani, “Neuro-Fuzzy And Soft Computing: A Computational Approach to Learning and Machine Intelligence”, Prentice Hall Upper Saddle River, 1997.
[40]吳成柯…等譯, “數位影像處理”, 儒林, 4.6.1 彩色基礎, Page(s): 221 —223, 1993.
[41]Young-Chang Chang; Reid, J.F. “RGB calibration for color image analysis in machine vision”, IEEE Transactions on Image Processing, Volume: 5, Page(s): 1414 —1422, Oct. 1996.
[42]R. Nishimura et al., “A RGB-gamma CCD camera with a novel color matrix”, IEEE Transactions on Consumer Electronics, Volume: 35, Page(s): 375 —381, Aug. 1989.
[43]Y.S. Feng and N.M. Nasrabadi, “Dynamic address-vector quantisation of RGB colour images”, IEE Proceedings I, Communications, Speech and Vision, Volume: 138, Page(s): 225 —231, Aug. 1991.
[44]H. Wang and S.-F. Chang, “A High Efficient System for Automatic Face Region Detection in MPEG Video”, IEEE Transactions on Circuits and System for Video Technology, Volume: 7, Page(s): 615 —628, August 1997.
[45]C. Garcia and G. Tziritas, “Face detection using quantized skin color regions merging and wavelet packet analysis”, IEEE Transactions on Multimedia, Volume: 1, Page(s): 264 —277, Sept. 1999.
[46]J. Huang and Y. Wang “Compression of color facial images using feature correction two-stage vector quantization”, IEEE Transactions on Image Processing, Volume: 8, Page(s): 102 —109, Jan. 1999.
[47] N. Mark and F. Clemens, “Analysis of Skin Erythema Using True-Color Images”, IEEE Transactions on Medical Imaging, Volume: 16, Page(s): 711 —716, December 1999.
[48]C. Connolly and T. Fleiss, “A study of efficiency and accuracy in the transformation from RGB to CIELAB color space”, IEEE Transactions on Image Processing, Volume: 6, Page(s): 1046 —1048, July 1997.
[49]E.D. Montag and M.D. Fairchild, “Psychophysical evaluation of gamut mapping techniques using simple rendered images and artificial gamut boundaries”, IEEE Transactions on Image Processing, Volume: 6, Page(s): 977 —989, July 1997.
[50]N. Liu,; H. Yan, “Colour image edge enhancement by two-channel process” Electronics Letters Volume: 30, Page(s): 939 —940 June 1994.
[51]E. Scott, H. Randy and V. William, “Automatic Color Segmentation of Images with Application to Detection of Variegated Coloring in Skin Tumors”, IEEE Transactions on Medicine and Biology Magazine, Page(s): 43 —52, December 1989.
[52]E. Scott, H. Randy and V. William, “Automatic Color Segmentation Algorithms with Application to Skin Tumor Feature Identification”, IEEE Transactions on Medicine and Biology Magazine, Page(s): 75 —82, September 1993.
[53]N.A. Dodgson, “Quadratic interpolation for image resampling”, IEEE Transactions on Image Processing, Volume: 6, Page(s): 1322 —1326, Sept. 1997.
[54]J.R. Price and M.H. Hayes, ”Resampling and reconstruction with fractal interpolation functions”, IEEE Signal Processing Letters, Volume: 5, Page(s): 228 —230, Sept. 1998.
[55]N.A. Dodgson, “Quadratic interpolation for image resampling”, IEEE Transactions on Image Processing, Volume: 6, Page(s): 1322 —1326, Sept. 1997.
[56]T.M. Lehmann, C. Gonner and K. Spitzer, “Survey: interpolation methods in medical image processing”, IEEE Transactions on Medical Imaging, Volume: 18, Page(s): 1049 —1075, Nov. 1999.
[57]繆紹綱, “數位影像處理 活用—Matlab”, 全華, 1999.
[58]郭尚君, “精通視窗程式設計 適用Visual C++ 6.0版”, 文魁, 1999.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top