國家圖書館典藏電子全文

Size: px

Start display at page:

Download "國家圖書館典藏電子全文"

羽鸳娄
7 years ago
Views:

2 VRML Cosmo VRML player MPEG

3 3

4 4

5 5

6 6 Roberto Bruell Tomaso Poggo Geometrc

7 7

8 8

9 9

10 40 80 MPEG-4 84 MPEG-4 <7.> <.5><.> VRML 3 MPEG-4 Feature Pots Extracto VRML 3 3 0

11 4 VRML,,, 3 3 3,, j j j um um j j j / = = um: C m V V V 3 V m

12 * * w w V = = z y x V V V w * w * V = = z y x V V V * * w w V = = z y x V V V * * w w V + = = z y x V V V * * w w Vm = = m z y m m x V V V

13 m S s = m k= Vk x Vjk x + Vk y Vjk y + Vk z Vjk z S.0~.0 W W = y = S SF : y S: S SF: S Global Face Local Face 6 S =.6 S P 5 S S N P : = P = P N 3

14 5 4

15 MDB SDB SDB SDB SA MDB MDB MA MW Global Face.5.9 MDBBer 3D 5

16 . Uversty of Ber 9 58 MIT : Ber 9 MDB 5.5 MIT SDB MPEG-4 4 Ber 9 MDB : ,.6 MPEG-4 6

17 5. 3D Ber 9 3D 3D 90% 3 7 Global Face,45 3D 8 3D / % / / , / / / ,9-3,34-37,74-77 Global Face / /

18 3D VRML A B A B A B A B A B 5.3 D D 3D 3D 4 9 D 0 8

19 D D 3D D 54/58 93.% 46/ % / % 34/ % /58 93.% 35/ %.9. 5/ % 35/ %.9.0 4/58 7.4% 30/58 5.7% /58 98.% 44/ %.4.9 Global Face 56/ % 50/58 86.%.8.9 D VRML VRML A B C 9

20 D A B VRML A B A B A B A B S P 3D 96.5% D 87.9% 3 0

21 3D VRML A B D VRML A B

22 3D D 4/ 63.6% 3/ 59.0% 4/ 63.6% 7/ 3.8% 5/.7% / 9.0% 6/ 7.7% / 54.5% 7/ 77.% 6/ 7.7% 9/ 86.3% 4/ 63.6% Global Face 8/ 8.8% 8/ 8.8% Local Face 8/ 8.8% 5/ 68.% 3D 3D 3D D 68/ % 54/ % /80 86.% 39/ % /80 7.5% 36/ % / % 49/80 6.% /80 7.5% 43/ % / % 57/80 7.%.6.9 Global Face 74/80 9.5% 68/ %.9. Local Face 74/80 9.5% 66/80 8.5%

23 Precsso Rate = Recall Rate = 3D D 3D 3

24 : 4 3D D D 3D MPEG-4 <3.5> <3.6> <3.9><3.0> MPEG-4 eutral state <3.5><3.6> <3.9><3.0> : MPEG-4 3D D 6 D 3D : 8 MPEG-4 4

25 : 0 : MPEG-4 : D 3D <.5><.> 5

26 MPEG-4 :.. 6

27 7

28 [] Ferado Perera, MPEG-4 Facal Amato Techology: Survey, Implemetato, ad Results, IEEE Trasactos o Crcuts ad Systems for Vdeo Techology, Vol. 9, No., pp , March 999. [] Sh ch Satoh et al., Name-It: Namg ad Detectg Faces News Vdeos, IEEE Multmeda, Vol. 6, No., pp. -35, Ja. Mar [3] Takeo Kaade, et al., Neural Network-Based Face Detecto, IEEE Trasactos o Patter Aalyss ad Mache Itellgece, Vol. 0, No., pp. 3-38, Jauary 998. [4] Jo Lous Betley, Multdmesoal Bary Search Trees Used for Assocatve Search, Comm. of the ACM, Vol. 8, No.9, pp , Sep [5] Ha Tao, et al., Compresso of MPEG-4 Facal Amato Parameters for Trasmsso of Talkg Heads, IEEE Trasactos o Crcuts ad Systems for Vdeo Techology, Vol. 9, No., pp.64-76, March 999. [6] Turk M. ad Petlad A., Face Recogto usg Egefaces, Proceedg of the IEEE, Computer Socety Coferece o Computer Vso ad Patter Recogto, pp , Mau, Hawa, Jue 99. [7] Hayua Wu, et al., Face Detecto From Color Images Usg a Fuzzy Patter Matchg Method, IEEE Trasactos o Patter Aalyss ad Mache Itellgece, Vol., No. 6, pp , Jue 999. [8] Adreas Lats, et al., Automatc Iterpretato ad Codg of Face Images Usg Flexble Models, IEEE Trasactos o Patter Aalyss ad Mache Itellgece, Vol. 9, No. 7, pp , July 997. [9] Ia Craw, et al., How Should We Represet Faces for Automatc Recogto? IEEE Trasactos o Patter Aalyss ad Mache Itellgece, Vol., No.8, pp , August 999. [0] JA Goldste, el al., Idetfcato of Huma Faces, Proceedg of the IEEE, Vol. 59, No. 5, pp , May 97. [] M. Vezjak, et al., Systems for Descrpto ad Idetfcato of Idvduals, Electrotechcal Coferece, 99 Proceedg, 6th Medterraea, Vol., pp. 5-54, 99. [] F. Goudal, et al., Face Recogto System Usg Local Autocorrelatos ad Multscale Itegrato, IEEE Trasactos o Patter Aalyss ad Mache Itellgece, Vol. 8, No. 0, pp , October

29 [3] F. Goudal, et al., Fast Face Recogto Method Usg Hgh Order Autocorrelatos, Proceedgs of Iteratoal Jot Coferece o Neural Networks, pp , 993. [4] Sta. L ad Juwe Lu, Face Recogto Usg the Nearest Feature Le Method, IEEE Trasactos o Neural Network, Vol. 0, No., pp , March 999. [5] aoguag Ja ad Mark S. Nxo, Extedg the Feature Vector for Automatc Face Recogto, IEEE Trasactos o Patter Aalyss ad Mache Itellgece, Vol. 7, No., pp , December 996. [6] Roberto Bruell ad Tomaso Poggo, Face Recogto: Features versus Templates, IEEE Trasactos o Patter Aalyss ad Mache Itellgece, Vol. 5, No. 0, pp , October 993. [7], MPEG-4 Processg of Workshop o the st Cetury Dgtal Lfe ad Iteret Techologes, 00. 9

30 30

31 3

32 7 Cosmo VRML player 3

33 33

34 34

35 35

36 36

37 37

38 38

Sep (SCI) 10. Jiann-Ming Wu, Annealing by two sets of interactive dynamics, IEEE Trans. on Systems Man and Cybernetics Part B-Cybernetics 34 (3)

Sep (SCI) 10. Jiann-Ming Wu, Annealing by two sets of interactive dynamics, IEEE Trans. on Systems Man and Cybernetics Part B-Cybernetics 34 (3) 03-863-3531 E-mail jmwu@mail.ndhu.edu.tw /(1990/06-1994/06) (1988/06-1990/06) (1984/09-1988/06) / (1997/8-) (1996/08-1997/07) () 1996 8 Wu, Jiann-Ming ( SCI EI SSCI TSSCI EconLit A&HCI ) 1. Pei-Hsun Hsu