SURF,,., 55%,.,., SURF(Speeded Up Robust Features), 4 (,,, ), SURF.,, 84%, 96%, 28%, 32%.,,,. SURF, i

Similar documents
20 Method for Recognizing Expression Considering Fuzzy Based on Optical Flow

28 TCG SURF Card recognition using SURF in TCG play video

Web Web Web Web Web, i

,,.,.,,.,.,.,.,,.,..,,,, i

i


Wide Scanner TWAIN Source ユーザーズガイド

220 28;29) 30 35) 26;27) % 8.0% 9 36) 8) 14) 37) O O 13 2 E S % % 2 6 1fl 2fl 3fl 3 4

橡最新卒論

SketchPoint Pie-Menu On/Off 3 Pie-Menu 8 6 On/Off SketchPoint i

25 Removal of the fricative sounds that occur in the electronic stethoscope

, (GPS: Global Positioning Systemg),.,, (LBS: Local Based Services).. GPS,.,. RFID LAN,.,.,.,,,.,..,.,.,,, i

kut-paper-template.dvi

kut-paper-template.dvi

16−ª1“ƒ-07‘¬ŠÑ




活用ガイド (ソフトウェア編)


Takens / / 1989/1/1 2009/9/ /1/1 2009/9/ /1/1 2009/9/30,,, i

3_23.dvi

178 5 I 1 ( ) ( ) ( ) ( ) (1) ( 2 )

untitled

生活設計レジメ

44 4 I (1) ( ) (10 15 ) ( 17 ) ( 3 1 ) (2)

I II III 28 29


(MIRU2008) HOG Histograms of Oriented Gradients (HOG)

Web Basic Web SAS-2 Web SAS-2 i

駒田朋子.indd

29 jjencode JavaScript

28 Horizontal angle correction using straight line detection in an equirectangular image

,,,,., C Java,,.,,.,., ,,.,, i

1., 1 COOKPAD 2, Web.,,,,,,.,, [1]., 5.,, [2].,,.,.,, 5, [3].,,,.,, [4], 33,.,,.,,.. 2.,, 3.., 4., 5., ,. 1.,,., 2.,. 1,,

総研大文化科学研究第 11 号 (2015)

1 Fig. 1 Extraction of motion,.,,, 4,,, 3., 1, 2. 2.,. CHLAC,. 2.1,. (256 ).,., CHLAC. CHLAC, HLAC. 2.3 (HLAC ) r,.,. HLAC. N. 2 HLAC Fig. 2

Virtual Window System Virtual Window System Virtual Window System Virtual Window System Virtual Window System Virtual Window System Social Networking

活用ガイド (ハードウェア編)

7,, i

ii

19 Systematization of Problem Solving Strategy in High School Mathematics for Improving Metacognitive Ability

25 D Effects of viewpoints of head mounted wearable 3D display on human task performance

,,,, : - i -

untitled

i

161 J 1 J 1997 FC 1998 J J J J J2 J1 J2 J1 J2 J1 J J1 J1 J J 2011 FIFA 2012 J 40 56

AccessflÌfl—−ÇŠš1

ron.dvi

2

24 Depth scaling of binocular stereopsis by observer s own movements


WebRTC P2P Web Proxy P2P Web Proxy WebRTC WebRTC Web, HTTP, WebRTC, P2P i

( ) [1] [4] ( ) 2. [5] [6] Piano Tutor[7] [1], [2], [8], [9] Radiobaton[10] Two Finger Piano[11] Coloring-in Piano[12] ism[13] MIDI MIDI 1 Fig. 1 Syst

,,.,,., II,,,.,,.,.,,,.,,,.,, II i

soturon.dvi

21 Effects of background stimuli by changing speed color matching color stimulus

IR0036_62-3.indb

,.,.,,.,. X Y..,,., [1].,,,.,,.. HCI,,,,,,, i

75 Author s Address: Possibility of Spatial Frequency Analysis of the Three-dimensional Appearance and Texture of Facial Skin


活用ガイド (ソフトウェア編)

1 1 tf-idf tf-idf i

Human Welfare 8‐1☆/5.林





01-譴カ蜴・-8.fm

2 1 ( ) 2 ( ) i

入門ガイド

..,,,, , ( ) 3.,., 3.,., 500, 233.,, 3,,.,, i

                         2009,3,1

Transcription:

24 SURF Recognition of Facial Expression Based on SURF 1130402 2013 3 1

SURF,,., 55%,.,., SURF(Speeded Up Robust Features), 4 (,,, ), SURF.,, 84%, 96%, 28%, 32%.,,,. SURF, i

Abstract Recognition of Facial Expression Based on SURF Takayuki Yoshimoto An expression plays a very big part in the human communication. It is said that the expression occupies about 55% of the whole dialog. And the expression is an element indispensable in order to perform a smooth dialog. If a computer becomes able to guess feelings from an expression, realization of high human interface understanding a human thought. Therefore, using SURF, I performed the recognition of facial expression experiment of 4 expressions (deadpan, smile, surprise, anger) and SURF characteristic quantity was effective for recognition of facial expression or, in this study, examined it. The result of deadpans 84%, smile 96%, surprise 28% and anger 32% have been obtained. Because it became a high recognition result about a deadpan, the smile, it is found that this technique is effective recognition to facial expression. key words SURF, Recognition of Facial Expression ii

1 1 1.1................................... 1 1.2................................... 2 1.3................................... 2 1.4................................. 3 2 4 2.1 SURF.................................... 4 2.2................................ 5 3 6 3.1................................... 6 3.2................................... 8 3.3................................... 9 3.4................................. 9 3.5................................... 9 3.5.1........................... 9 4 12 4.1................................... 12 4.2................................... 12 4.3.............................. 13 4.4...................................... 13 4.5.................................... 14 4.6................................... 14 iii

4.7................................ 15 5 16 6 17 18 20 iv

3.1................................ 7 3.2.................................... 8 3.3................................ 10 3.4................................. 10 3.5................................. 11 3.6................................. 11 4.1................................ 15 v

3.1................................. 6 3.2.......................... 7 3.3.............................. 7 4.1.................................... 14 vi

1 1.1,,,.,,, ( ),, [1]., face-to-face communication,., [2].,., 7%, 38%, 55%,.,,.,.,.,, 1

1.2 [3]. 1.2.,, [4]., [5]. 1.3, 4 (,,, ).,,,. SURF,.,, 4. SURF,, ITS SIFT. SURF. 2

1.4 1.4, 6. 2, SURF. 3,. 4,. 5,., 6,,. 3

2 2.1 SURF SURF,, [8].,SIFT,,.,,Speeded Up Robust Features(SURF). SURF SIFT,. 4

2.2 2.2. 1..,,, 4,. 2. FaceTool, 4. 3. SURF SURF,. 4... 5., 0 1, 0.1. 5

3 3.1,.,. 4.1.. 3.1 SONY HDR-TD10,,,. 6

3.1 3.2 SONY HDR-TD10 1/4 CMOS ( 420 ) 265 354 F1.8 F3.4 f=2.9-34.8mm(35mm 27.4 328.8mm) MPEG-4 AVC/H.264 Dolby Digital 2ch/5.1ch NTSC EIA SD 3.3 1mm/m=0.0527 5.25mm/m= 0.2999 3.1 7

3.2 3.2,., ( ),.,,.,,. 3.2.,.,,. 3.2 8

3.3 3.3,.,.,,,. 3.4,,,, 4. 3.5 3.5.1 5., FaceTool[6], FaceTool [7]. FaceTool, 3,. IPA( ) MS Windows,. 3.3, 3.4, 3.5, 3.6. 9

3.5 3.3 3.4 10

3.5 3.5 3.6 11

4 4.1 5., 5, 5, 5, 5, 20 1.,.,,. 4.2 5, 100.,. FaceTool 4 SURF,, 128. 4 DB. 100. SURF, DB.,,,., DB. 12

4.3 4.3 F = 127 (x i y i ) 2 < T (4.1) i=0 X = (x 0, x 1,..., x 127 ) : DB Y = (y 0, y 1,..., y 127 ) : T :,. DB,., DB, DB,., DB,. 4.4,,. 0 1, 0.1.,,.,. 13

4.5 4.5 100 (4.2) 25, 25 (1 25 ), DB. 4.6 0.4,. 4.1 84% 96% 28% 32% 14

4.7 4.7. 4.1 15

5,, 0.3. 0.3,. 0.3,, 0.4., 0.7 100%,, 0%., 0.4,,. 0.4, 84%, 96%, 28%, 32%.,,,,.,,. SURF,,.,,,.,,,. 16

6, SURF, 4 (,,, ), SURF. DB,,., DB,,,., 0.4, 84%, 96%, 28%, 32%.,,,,,,.,.,.,,. FaceTool,,., 5,. 17

,,,,. 2,.,,.,.,,.,.,,,.,,.,,.,.,,.,,,. 2,,,,, 2. 2,.,.,,,.,,.,.,,,,,.,,, 18

.,,,,,, 2.,,,.,,.,,.,..,.,.,.,.,.,..,,.,,,.,,,.,4. 19

[1],,,2004. [2], http://noncommu.tants.biz/( 2013-2-2) [3], Vol.85 No.10, pp.766 771 (2002). [4], Vol.85 No.12, pp.936 941 (2002). [5], Vol.86 No.1, pp.54 61 (2003). [6], http://nae-lab. org/project/face/ipa/ [7] PC FaceTool, http://nae-lab.org/ project/face/heikintool/ [8],, 21, 2009 20