穨 PDF

Size: px

Start display at page:

Download "穨 PDF"

璎牲庄
7 years ago
Views:

1 * ** ** * (Feature Extraction System) (Fourier Transform) * **

2 104 [2-7] [4-7] [8-9] [7,10-11] [12-13] [14];[15] (Fourier Descriptors, FD) ;[16] ;[17] ;Wu[18] B (B-spline) 6 : (edge enhancement) (edge detection) [19] 2.1 (sliding) (stretch) ( ) / / ( ) [19-20] ( ) P P (mask) [19] ( )

3 105 P P ( ) 2.2 (Sobel) (Gx Gy) ( ) (thinning)[19] ( ) (pattern representation) (b) 3.2(c)

4 106

5 (d) 3.7(e) 3.7(f)

9 ( ) 3.13 ( ) (pattern recognition) 4.1 (boundary representation) (region representation) (moment representation) (chain codes)b AR (autogressive model)

10 112 AR 4.2 (Nyquist sampling theorem) (band limited signal) (discrete Fourier transform) (fast Fourier transform) N (N=32) N (N/2)(N/2)-1 N-2 ( ) Qc P Qc P X 2 /N N α α f(t) Qc t0 F(u) 1( F(t) 1 t0 ) F(u) F(u) 2 F(u) = F(u) *e j(1 +2) F(u) F(u) u = 0 ~ (2 k 1) F(0) (normalized feature spectrum) 2 k = N 4.3 (statistical pattern recognition) (neural network pattern recognition)

11 113 (Euclidean distance) 4.4 ( ) ( ) 1 ( ) 1 ( 1 ) ( ) ( ) (spatial index) (spatial database) (Computer Aided Design) (Geographical Information System) N(N=4) (N-dimensional hyperplane ) (hyper-polygon region) (norm) 4096

12 i (level i0i3) (link) i+1 norm j ( j+1 1j4) 01 ( 0.125*K)(0.125*(K+1)) K+1 ( 18) K=0,1,2, norm norm ( lower bound + upper bound) / 2 16

13 115 N1N2N3 L L N1 N1L N1R N1 N2 N2 (N2L,N2R) N1L N1R i 3 i i=1 234 M M M M M i 5 i i=1234 M M M 1 M

14 116

15 117

16 118 O, O Tb(O) O D D M ( ) Ti = 7 i= 1 Wi / Di O Tb(i) Di=Dmax Dmax Tb(i) D Ti K( )

17 ( ) R-tree [1] Chellappa, R., Wilson, C.L., and Sirohey, S. A. (1995) Human and machine recognition of faces: a survey. Proceedings of the IEEE 83 (5), [2] Sakai, T., Nagao, M., and Fujibayashi, S. (1969) Line extraction and pattern recognition in a photograph. Patt. Recog. 1,

18 120 [3] Kelly, M. D. (1970) Visual identification of people by computer. Tech. Rep. AI-130, Stanford AI Proj., Stanford, CA. [4] Craw, I., Tock, D., and Bennett, A. (1992) Finding face features. in Proc. 2nd Europe Conf. On Compu. Vision, [5] Craw, I., Ellis, H., and J. Lishman, J. (1987) Automatic extraction of face features. Patt. Recog. Lett. 5, [6] Sirohey, S.A. (1993) Human face segmentation and identification. Tech. Rep. CAR-TR-695, Center for Autom. Res., Univ. Maryland, College Park, MD. [7] Akamatsu, S., Sasaki, T., Fukamachi, H., and Suenaga, Y. (1991) A robust face identification scheme KL expansion of an invariant feature space. in SPIE Proc., Intell. Robots and Computer Vision X: Algorithms and Techn. 1607, [8] Kaya Y., and Kobayashi, K. (1972) A basic study on human face recognition. in Frontiers of Pattern Recognition (Watanabe, S., Ed.), Academic, New York, pp [9] Kanade, T., (1977) Computer Recognition of Human Faces. Birkhauser, Basel and Stuttgart. [10] Cheng, Y., Liu, K., Yang, J., Zhuang, Y., and Gu, N. (1991) Human face recognition method based on the statistical model of small sample size. in SPIE Proc. : Intell. Robots and Compu. Vision X : Algorithms and Techn. 1607, [11] Cheng, Y., Liu, K., Yang, J., and Wang, H. (1992) A robust algebraic method for human face recognition. in Proc. 11 th 1nt. Conf. On Patt. Recog., [12] Brunelli, R., and Poggio, T. (1993) Face recognition: Features versus templates. IEEE Trans. Patt. Anal. and Mach. Intell. 15, [13] Rahardja, A., Sowmya, A., and Wilson, W. (1991) A neural network approach to component versus holistic recognition of facial expressions in images. in SPIE Proc.:Intell. Tobots and Computer Vision X: Algorithms and Techn. 1607, [14] Kaufman, G.J. Jr., and Breeding, K.J. (1976) The automatic recognition of human faces from profile sihouettes. IEEE Trans. Syst., Man, and Cybern. SMC-6, [15] Zahn, C.T., and R. S. Roskies, R.S. (1972) Fourier descriptors for plane closed curves. IEEE Trans. Computers COM-21,

19 121 [16] Harmon, L., and Hunt, W. (1997) Automatic recognition of human face profile. Computer Graphic and Image Process. 6, [17] Harmon, L., Khan, M., Lasch, R., and Ramig, P. (1981) Machime identification of human faces. Patt. Recog. 13, [18] Wu, C. and Huang, J. (1990) Human face profile recognition by computer. Patt. Recog. 23, pp [19] Gonzalez, R.C., and Woods, R.E. (1992) Digital image processing. Addison-Wesley. [20] Lindley, C.A. (1994) Practical image processing in C. Big Apple Tuttle-Mori.

20 122 An Application of Image Database on Facial Recognition The Database of Lawbreakers Fang-Yie Leu * Shau-Tang Yu ** Min-Shiung Shiu ** Chau-Li Lin * Abstract The goal of this project is to construct a human image database of lawbreakers. After the police get the human image drawn by the witness, they can use the human image database and retrieval system to find out the possible upsets. At first, we should construct the image data of lawbreakers, then scan the standard mug shot taken by the police and transfer it to the image file. After retrieving the features of face organs including eyes, eyebrows, lips, outline of face and profile, by using edge enhancement, Sober edge detection, Hough transform and thinning techniques, we can obtain the outlines of each organ. The outlines are then transform into Fourier descriptors with Fourier Transform. After that a normalized feature spectrum is generated. The second to fifth spectrums are extracted to construct organ relations. We also construct the spatial index for every relation. The human image drawn by the witness is also proceeded by the same techniques described above. We use the image to query the spatial index to downsize the searching space. The importance of weight of each organ is also discussed in this article. Keyword: Image Database, Image Database of Lawbreakers, Face Reconization * Institute of Computer and Information Sciences, Tunghai University, Taichung 407, TAIWAN. ** Department of Computer and Information Sciences, Tunghai University, Taichung 407, TAIWAN

P(x,y) P(x-1,y) P(x,y-1) P(x,y+1) P(x+1,y) 1 3.2 Sobel LaplacePrewittRoberts Sobel [2] Sobel 3.3 2 [6] 0 1 1: P(x,y) t (4-connectivity) 2: P(x,y) t 3:

P(x,y) P(x-1,y) P(x,y-1) P(x,y+1) P(x+1,y) 1 3.2 Sobel LaplacePrewittRoberts Sobel [2] Sobel 3.3 2 [6] 0 1 1: P(x,y) t (4-connectivity) 2: P(x,y) t 3: chdong@npic.edu.tw rola@mail.stu.edu.tw (ITS) (LPR) ITS 2. [1][8] [3][9][12] [9] frequency table Sobel [3][12] RGB HSB color model [11] Hough transformation Sobel [4] [10] 1. Intelligent Transportation

穨 PDF

穨 PDF