臺灣博碩士論文加值系統

隨著電腦速度提升，即時人臉辨識或人眼追蹤應用在個人電腦上門檻越來越低。考量視訊攝影機(Webcam)產品價位低廉亦具備方便性與可攜性，筆記型電腦也普遍都有此裝置，研究成品應用性高，所以採用平價的網路視訊攝影機及一般個人電腦為研究平台發展人眼追蹤的相關研究。
本論文設計一個倒傳遞類神經網路產生每幀影像的二值化門檻值，將視訊影像二值化處理，突顯影像中人臉特徵。再以快速連通元件標記法標示二值化影像中各個圖塊元件，並計算其不變矩，與樣本不變矩比對找尋人眼圖塊元件。最後在尋到的人眼影像上，繪出上下眼瞼的輪廓線，以兩眼角的角度作為判斷眼睛開闔程度的依據。經實驗結果證明，本系統可有效的進行即時的人眼追蹤以及眨眼偵測。

With computer process speed increasing, real-time face recognition, or eye tracking applications on personal computers getting lower and lower threshold. In this thesis, considering the video cameras (Webcam) are cheap, convenient and portability, thus the most of laptops have this device generally. So this study use personal computer with a webcam to develop the eye-tracking research.
This thesis developed a backpropagation neuronal network to generate threshold value for each frame image. Thresholding video image could highlight face features in the image. Using fast connected component labeling to mark all components of a binary image, and calculating the moment invariants to search eye features. Finally, the upper and lower eyelid contours are drawn on eye images for judging the eyes are close or open. Experimental results show that this system can effectively carry out real-time eye tracking and blink detection.

中文摘要 i
ABSTRACT ii
目錄 iii
圖目錄 v
表目錄 vii
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 1
1.3 研究範圍與限制 2
1.4 研究流程 2
第二章 文獻探討 4
2.1 機械視覺 4
2.2 人臉偵測 5
2.3 人眼追蹤及人眼特徵 6
2.4 影像特徵值 8
2.5 自動二值化門檻值法 9
2.5.1 P-Tile二值化法 10
2.5.2 Otsu二值化法 11
2.5.3 Kapur二值化法 14
2.6 類神經網路(Artificial Neural Network) 15
2.6.1倒傳遞類神經網路 15
第三章 研究方法 19
3.1 系統架構 19
3.2 影像前處理 25
3.2.1 灰階化(Grayscale) 25
3.2.2 二值化(Thresholding) 25
3.2.3 利用倒傳遞類神經網路產生二值化門檻值 25
3.3 快速連通元件標記法 28
3.4 抽取影像特徵 32
3.4.1 相近特徵值分類 35
3.4.2 調整樣本特徵值 35
3.5 搜尋演算法 35
3.5.1 差異影像搜尋 35
3.5.2 初始搜尋 37
3.5.3 正常搜尋 37
3.5.4 重新搜尋 38
3.6 分析眼部影像張閉狀態 38
3.6.1 描繪眼瞼輪廓線的步驟 39
3.6.2 判斷張閉眼 41
第四章 實驗結果與分析 43
4.1 實驗環境 43
4.2 測試過程及實驗結果分析 44
4.2.1 單純背景人眼追蹤實驗 46
4.2.2 自動二值化門檻值實驗 47
4.2.3 多位受測者人眼追蹤實驗 50
4.2.4 多位受測者眨眼偵測實驗 53
4.2.5 長時間閉眼偵測實驗 56
第五章 結論及後續研究建議 58
5.1 結論 58
5.2 研究貢獻 58
5.3 後續研究建議 59
參考文獻 60
附錄一 倒傳遞類神經網路二值化法實驗結果 64
附錄二 百分比法二值化法實驗結果 65
附錄三 25位未配戴眼鏡受測者 人眼追蹤實驗結果 66
附錄四 5位配戴眼鏡受測者 人眼追蹤實驗結果 68
附錄五 25位未配戴眼鏡受測者 眨眼實驗結果 69
附錄六 5位配戴眼鏡受測者 眨眼實驗結果 70
附錄七 長時間閉眼偵測實驗結果 71

[1]Balasubramanian, M., S. Palanivel and V. Ramalingam, ”Real time face and mouth recognition using radial basis function neural networks,” Expert Systems with Applications, vol. 36, 2009, pp. 6879–6888.
[2]Basheer, I.A. and M. Hajmeer, “Articial neural networks: fundamentals, computing, design, and application,” Journal of Microbiological Methods, vol. 43, 2000, pp. 3-31.
[3]Bhattacharyya, Siddhartha, Ujjwal Maulik and Paramartha Dutta, “Multilevel image segmentation with adaptive image context based thresholding,” Applied Soft Computing, 2010.
[4] Feng, Zhang, Liu Shang-qian, Wang Da-bao and Guan Wei, “Aircraft recognition in infrared image using wavelet moment invariants, ” Image and Vision Computing, vol. 27, 2009, pp. 313–318.
[5]Geetha, A., V. Ramalingam, S. Palanivel and B. Palaniappan, “Facial expression recognition – A real time approach,” Expert Systems with Applications, vol. 36, 2009, pp. 303–308.
[6]Hansen, Dan Witzner and Riad I. Hammoud, “An improved likelihood model for eye tracking,” Computer Vision and Image Understanding, vol. 106, 2007, pp. 220–230.
[7]Horng, Ming-Huwi, “A multilevel image thresholding using the honey bee mating optimization,” Applied Mathematics and Computation, vol. 215, 2010, pp. 3302–3310.
[8]Hu, M. K., "Visual pattern recognition by moment invariants," IRE Trans. Info. Theory, vol. IT-8, pp.179–187, 1962.
[9]Hsu, Rein-Lien, Mohamed Abdel-Mottaleb, and Anil K.Jain, “Face detection in color images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, May 2002, pp. 696–706.
[10]Kapur, J. N. ,Sahpp, P. K., and Wong, A. K. C. “ A new method for gray-level picture thresholding using the entropy of the histogram, ” Computer vision graphics and image processing, vol. 29, 1985, pp. 273-285.
[11]Kittler J and Illingworth J. “Minimum Error Thresholding,” Pattern Recognition, vol. 19, no. 1, 1986, pp. 41-47.
[12]Liu, Charles C., Simon G. Hosking and Michael G. Lenné, “Predicting driver drowsiness using vehicle measures: Recent insights and future challenges,” Journal of Safety Research, 2009.
[13]Messom, C. H., S. Demidenko, K. Subramaniam and G. Sen Gupta, “Size/position identification in real-time image processing using run length encoding,” IEEE Instrumentation and Measurement Technology Conference, Anchorage, AK, USA, 21-23 May 2002.
[14]Morris, T. and V. Chauhan, “Facial feature tracking for cursor control,” Journal of Network and Computer Applications, vol.29, no. 1, January 2006, pp. 62-80.
[15]Nasri, Mehdi and Hossein Nezamabadi-pour, “Image denoising in the wavelet domain using a new adaptive thresholding function,” Neurocomputing, vol.72, 2009, pp. 1012–1025.
[16]Otsu, N., “A threshold selection method from gray level histogram,” IEEE Transactions on Systems, Man and Cybernetics, vol. 9, no. 1, January 1979, pp. 62-66.
[17]Pai, Yu-Ting, Yi-Fan Chang and Shanq-Jang Ruan, “Adaptive thresholding algorithm: Efficient computation technique based on intelligent block detection for degraded document images,” Pattern Recognition, vol. 43, 2010, pp. 3177–3187.
[18]Santis, Alberto De and Daniela Iacoviello, “Robust real time eye tracking for computer interface for disabled people,” Computer methods and programs in biomedicine, 2009.
[19]Sun, Te-Hsiu and Fang-Chih Tien, “Using backpropagation neural network for face recognition with 2D + 3D hybrid information,” Expert Systems with Applications, vol.35, 2008, pp. 361–372.
[20]Tizhoosh, Hamid R., “Image thresholding using type II fuzzy sets,” Pattern Recognition, vol. 38, 2005, pp. 2363 – 2372.
[21]Torricelli, Diego, Silvia Conforto, Maurizio Schmid and Tommaso D’Alessio, “A neural-based remote eye gaze tracker under natural head motion, ” computer methods and programs in biomedicine, vol. 9 2, 2008, pp. 66–78.
[22]Tsai, W., “Moment-preserving threshoding: a new approach,” Computer vision graphics and image processing, vol. 29, 1985, pp. 377-393.
[23]Wang, Peng and Qiang Ji, “Multi-view face and eye detection using discriminant features,” Computer Vision and Image Understanding vol. 105, 2007, pp. 99-111.
[24]Wu, Jian-Da and Tuo-Rung Chen, “Development of a drowsiness warning system based on the fuzzy logic images analysis,” Expert Systems with Applications, vol. 34, no. 2, February 2008, pp. 1556-1561.
[25]Yan, Feixiang, Hong Zhang and C. Ronald Kube, “A multistage adaptive thresholding method,” Pattern Recognition, vol. 26, 2005, pp. 1183-1191.
[26]Zhao, Mansuo, Yibing Yang and Hong Yan, “An adaptive thresholding method for binarization of blueprint images,” Pattern Recognition, vol. 21, 2000, pp. 927-943.
[27]Zheng, Zhonglong, Jie Yang and Limin Yang, “A robust method for eye features extraction on color image,” Pattern Recognition Letters, vol. 26, 2005, pp. 2252–2261.
[28]吳成柯；程湘君；戴善榮；雲立實，數位影像處理，台北市：儒林圖書有限公司，2001。
[29]葉怡成，應用類神經網路，台北市：儒林圖書有限公司，2002。
[30]葉怡成，類神經網路模式應用與實作，台北市：儒林圖書有限公司，2003。
[31]繆紹綱譯，數位影像處理，台北市：高立圖書有限公司，2003。
[32]葉郡維，“料盤中之液晶顯示器驅動IC瑕疵檢測”, 國立台北科技大學自動化科技碩士論文，2007。