( 您好!臺灣時間:2021/02/27 18:42
字體大小: 字級放大   字級縮小   預設字形  


研究生(外文):tingjung kuo
論文名稱(外文):Characteristics are utilized to judge directions of rotation for the facial detection and application.
指導教授(外文):tsongliang huang
外文關鍵詞:facial detection
  • 被引用被引用:1
  • 點閱點閱:212
  • 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
In recent years, because the skill of biotechnology grows with more and more gradual maturity, and its uniqueness and difficulty to copy, it is effective to identify everyone’s characteristics with certain accuracy, for example, fingerprints or the iris can be used to identify one’s identity with high distinguishing rate. Nonetheless, the expense and the range of application of these two technologies are limited to some extent. If using the technology of human face recognition, not only the expense would reduce but also the range of application can be extended from distinguishing the identity to making a number of applications to life, such as adjusting the focus of the camera to people’s face, to increase the facilities of life. However, among relevant researches and documents, we find that the strike-rate of distinguish the other sides of face excluding the front side is still need to improve and enhance.
Therefore, this research attempts making use of the information of facial features to predict the directions of rotation like turning along and against the counter clock hand, left-to-right, and bending-to-lifting, in order to find the closest frontal faces in a surveillance video stream. This research utilizes a novel model called radial template to detect the presence of face rotation. This template is designed to analysis the angle of center-rotated objects. According to the characteristics of skin detection, the extracted feature will be stable under this kind of template. Besides, by using the collection of vertical feature projection, the direction and the angle of face turning can be determined by analyzing the distribution of vertical projection histogram. Furthermore, judging the possibility of bending or lifting of faces based on the relationship of face and neck.
Through the detection of the three directions of rotation above-mentioned, the cooperation to calculate the position between eyes, nose and lip, and the comparison with the symmetry, we can find out the image area that corresponds to facial features most in the picture. Finally, the image test proves that the method in this research has feasibility and reference to human face recognitions.
第一章 前言 7
1.1 研究背景 7
1.2 研究目的 8
1.3 論文架構 9
第二章 相關研究與探討 10
第三章 影像處理 13
3.1人臉膚色之色彩空間 13
3.1.1 HSV 色彩空間 13
3.1.2 YCbCr 色彩空間 14
3.1.3影像二值化 15
3.1.4邊緣偵測 15
3.1.5侵蝕 16
3.1.6膨脹 17
3.1.7侵蝕與膨脹 20
3.2線段平滑 21
3.3標記連通成份 21
3.4 彩色影像中的空間濾波 23
3-4-1 高斯濾波 23
第四章 人臉區域的偵測與旋轉判斷 25
4.1 人臉偵測 25
4.1.1 YCbCr空間轉換 26
4.1.2 膚色分割 26
4.2 特徵分割 27
4.2.1嘴唇定位 28
4.2.2眼睛定位 29
4.3 轉動判斷 30
4.3.1 特徵集中性與垂直投影 30
4.3.2 影像處理過程 32
4.3.3 平面旋轉 34
4.3.4 放射狀樣板 34
4.3.5 樣板比對 36
4.3.6 平面旋轉 38
4.3.7放射狀樣板 38
4.3.8 臉部特徵 40
4.3.9仰俯偵測 41
第五章 實驗結果與討論 44
5.1 系統實作 44
5.2 膚色偵測結果 44
5.3 特徵點定位結果 48
5.3.1 嘴唇偵測與定位 48
5.3.2眼睛偵測與定位 48
5.3.3最終人臉判定 48
5.4 旋轉判斷 49
5.5 實驗結果討論 49
第六章 結論與未來展望 50
6.1 結論 50
6.2未來展望 50
參考文獻 51
[1].C. Lin, K.C Fan “Triangle-based approach to the detection of human face” Pattern Recognition Vol.34 , pp.1271-1284 , 2001.
[2].J. Miao , B. Yin , K. Wang , L. Shen and X. Chen” A Hierarchical Multiscale and Multiangle System for Human Face Detection in a complex Background Using Gravity-Center Template “ Pattern Recognition vol.32 , No.7 , pp.1237-48 , 1999
[3].Y. Ishii, H. Hongo, K. Yamamoto, Y. Niwa “Real-Time Face and Head Detection using Four Directional Features” Automatic Face and Gesture Recognition, Sixth IEEE International Conference 17-19 pp.403 - 408 , 2004.
[4].F.Marquks, V.Vilaplana, A.Buxes “Human Face Segmentation And Tracking Using connected Operators and Partition Projection” Image Processing Vol.3 ,24-28 , pp.617 - 621, 1999.
[5].K.H. Seo, W. Kim , C. Oh , J-J. Lee “Face Detection and Facial Feature Extraction Using Color Snake” Industrial Electronics , IEEE International Symposium Vol.2 ,8-11 , pp.457 – 462 , 2002.
[6].L.Z. Fangl, Y.Z, Sheng1, A.K. Jain, W.Y, Qiong “Face Detection And Facial Feature Extraction In Color Image” Computational Intelligence and Multimedia Applications 27-30 , pp.126 - 130 , 2003.
[7].S.K. Singh , D.S. Chauhan, M. Vatsa, R. Singh, “A Robust Skin Color Based Face Detection Algorithm” Tamkang Journal of Science and Engineering , Vol. 6 , No. 4 , pp.227-234 , 2003.
[8].C.C. Han, H.Y.M. Liao, G.J. Yu, L.H. Chen “Fast face detection via morphology-based pre-processing” Pattern Recognition Vol.33 , pp.1701-1712 , 2000.
[9].C. Garcia, M. Delakis “Convolutional Face Finder : A Neural Architecture for Fast and Robust Face Detection” IEEE Transactions on pattern analysis and machine intelligence , Vol.26, No.11 , 2004.
[10].X. Guang, L.J. Zhou , C.S. Zhang” A Novel Algorithm for Rotated Human Face Detection” Computer Vision and Pattern Recognition vol.1 , 13-15 , pp.760 - 765 , 2000.
[11].H. Liu, S.Yon, X. Chen, W. Gao “Rotated Face Detection in Color Image Using Radial Template(RT)” Acoustics, Speech, and Signal Processing IEEE International Conference Vol.3 , 6-10 pp.III - 213-16 , 2003.
[12].Z.YANG, H.AI, B.WU, S.LAO and L.CAI “Face Pose Estimation and its Application in Video Shot Seletion” Proceeding of the 17th International Conference on Pattern Recognition , 2004.
[13].P. Smith , M. Shah “Determining Driver Visual Attention With One Camera” Intelligent Transportation Systems, IEEE Transactions Vol.4 , Issue 4, pp.205 – 218 , 2003.
[14].S. Han, G.. Pan, Z. Wu “Human Face Orientation Detection Using Power Spectrum Based Measurements” Automatic Face and Gesture Recognition, Sixth IEEE International Conference 17-19pp.791 - 796 , 2004.
[15].W. Cao, H. Feng, G.. Xiao, Y. Gu, S. Wang ”Study of An Algorithm For Face Pose Adjustment Based On Eye Location” Intelligent Control and Automatio Vol.5 , 15-19 pp.4190 - 4194 , 2004.
[16].B. Yegnanarayana, A.K. Sao, M. Savvides “Determination of pose angle of face using dynamic space warping” Information Technology: Coding and Computing Vol.1 , 5-7 pp.661 - 664 , 2004. C. Garcia, and G.Tziritas. “ Face Detection Using Quantized Skin
[17].K. K. Sung , T. Poggio, “Example-based learning for view-based human face detection”, in Proc. Image Understanding Workshop, pp. 843-850 , 1994.
[18].H. A. Rowley, S. Baluja, and T. Kanade, “Human face detection in visual scenes”, Tech. Rep. CMU-CS-95-158R, Carnegie Mellon University, 1995.
[19].S. H. Jeng, H. Y. Liao, C. C. Han, M. Y. Chern, and Y. T. Liu, “An efficient approach for facial feature detection using geometrical face model”, Pattern Recognition, 1997.
[20].B. Moghaddam, and A. Pentland, “Probabilistic Visual Learning for Object Representation,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 19, No. 7, pp. 696-710, 1997.
[21].B. Moghaddam, W. Wahid, and A. Pentland, “Beyond Eigenfaces: Probabilistic Matching for Face Recognition,” IEEE International Conference on Automatic Face and Gesture Recognition, pp. 21-35, 1998.
[22].E. Osuna, R. Freund, and F. Girosi, “Training Support Vector Machines : an Application to Face Detection,” Proc. Computer Vision and Pattern Recognition, pp. 17-19, 1997.
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔