¾½ ¾ ½ ÁÐÐÙ ÓÒÀÓÐ µ ½ ÁÐÐÙ ÓÒÀÓÐ ¾ ¾º½ ½ È ÁÐÐÙ ÓÒÀÓÐ È ¾º¾ ½¼ ÁÐÐÙ ÓÒÀÓÐ ½¼ ¾ ¾º È ÁÐÐÙ ÓÒÀÓÐ ¾ ¼ ¾º ÁÐÐÙ ÓÒÀÓÐ ÁÐÐÙ ÓÒÀÓÐ ÁÐÐÙ ÓÒÀÓÐ ÁÐÐÙ ÓÒÀÓÐ ¾ ¼

Size: px

Start display at page:

Download "¾½ ¾ ½ ÁÐÐÙ ÓÒÀÓÐ µ ½ ÁÐÐÙ ÓÒÀÓÐ ¾ ¾º½ ½ È ÁÐÐÙ ÓÒÀÓÐ È ¾º¾ ½¼ ÁÐÐÙ ÓÒÀÓÐ ½¼ ¾ ¾º È ÁÐÐÙ ÓÒÀÓÐ ¾ ¼ ¾º ÁÐÐÙ ÓÒÀÓÐ ÁÐÐÙ ÓÒÀÓÐ ÁÐÐÙ ÓÒÀÓÐ ÁÐÐÙ ÓÒÀÓÐ ¾ ¼ "

さわつまがみ
7 years ago
Views:

1 - ( ) Visual Sticky Visual Sticky Both 3 4, 16, 32, 48 cm cm Visual Sticky Both Normal Visual Normal Both Sticky Visual Normal cm cm Visual Sticky Both Normal Visual Sticky Both Pointing time [ms] Initial target width Final target width 1: Task method Visual Sticky Both Normal Target distance [cm] 2: Pointing time [ms] Distracter situation 1 loop 2 loops Visual Sticky Both Normal Method 3: Visual Normal Sticky Both 4 2 Visual Sticky Visual 2 Sticky Both Visual 5

0 18 1 3 Visual Sticky Both Pointing time [ms] 1200 1000 800 600 400 Initial target width Final target width 1: Task method Visual Sticky Both Normal 4

2 ¾½ ¾ ½ ÁÐÐÙ ÓÒÀÓÐ µ ½ ÁÐÐÙ ÓÒÀÓÐ ¾ ¾º½ ½ È ÁÐÐÙ ÓÒÀÓÐ È ¾º¾ ½¼ ÁÐÐÙ ÓÒÀÓÐ ½¼ ¾ ¾º È ÁÐÐÙ ÓÒÀÓÐ ¾ ¼ ¾º ÁÐÐÙ ÓÒÀÓÐ ÁÐÐÙ ÓÒÀÓÐ ÁÐÐÙ ÓÒÀÓÐ ÁÐÐÙ ÓÒÀÓÐ ¾ ¼ º ÈË ½ ÈË ¾¼ ÁÐÐÙ ÓÒÀÓÐ ½ µ µ ÁÐÐÙ ÓÒÀÓÐ ¾ µ ½ µ ¾

3 1 3 3 3 1 2 2.1 24 17 20 37 ActiveCube 5 4 40Hz x y z 16 50% 2.

3 ActiveCube Hz x y z 16 50% 2.2 (SOM) ( ) % 30% 5 81% : 1: 3:

4 WWW 1 WWW (World Wide Web) WWW Dice Jaccard Simpson Cosine 1 Simpson (1) K 10 ( ) (X, Y ) = (1 Simpson (X, Y )) K (1) (1) 2.4 1(c) WWW PL 3-gram PL (1) WWW 3 4 WWW 2.2 WWW gram (2 3 4 ) PL 1(a) WWW PL 4-gram PL (1) 2.3 1(b) WWW PL 4-gram PL : 1:

(1 Simpson (X, Y )) K (1) 0.773 0.895 (1) 2.4 1(c) WWW PL 3-gram PL 0.54 0.904 0.

Material for Master s Thesis Recital Department of Multimedia Engineering, Graduate School of Information Science and Technology, Osaka University 2009/2/13 Non Example-based Automatic Detection of

5 Material for Master s Thesis Recital Department of Multimedia Engineering, Graduate School of Information Science and Technology, Osaka University 2009/2/13 Non Example-based Automatic Detection of Stroke Correspondences in 2D Drawings 2 Ngo Thi Tu Trung (Human Interface Engineering Lab.) 1 Introduction Sketch is an easy and fast way to express one s thought. In recent years, extensive efforts related to sketch have been developed such as sketch inbetweening and Chinese character recognition. These researches require a technique called stroke correspondence detection. This is a process to find correspondence between strokes which make up the drawings. However, most conventional methods are based on existed examples with properly defined structures or drawing order and stroke s connection relations (mutual adjoined strokes). This limits users freedom and contradicts with the intrinsic ambiguous and messy nature of sketch. We propose a non example-based method to automatically detect stroke correspondences of two drawings without considering strokes input order and connection relations. The method is composed of two stages: drawings normalization and stroke correspondence detection. 2 Non Example-based Automatic Stroke Correspondence Detection 2.1 Objective Drawings Normalization Before applying the main correspondence detection algorithm, two input drawings such as the ones in Figure 1 are normalized. First, we find stroke s two principal axes using statistical principal component analysis method. Stroke s center is the center of the rectangle surrounding each stroke which is found based on two principal axes. Similarly, drawing s center is found based on composed strokes centers. Next, drawing s center is translated to coordinate system s origin and all contained strokes centers are translated together with it. Then scaling is conducted to fit the drawing and all strokes centers to the unit square. 2.2 Finding Stroke Correspondences In this stage, we first calculate three kinds of similarity based on 2D coordinates of centers of strokes and drawing: Euclidean distance, angle and mix feature similarity which is the sum of two former similarities. We then apply stable marriage algorithm for each of the similarity and find matching results for each of them. Stable marriage algorithm is a method to find a stable matching - a matching in which both elements of one pair cannot find other element which prefers them over their present match. These results are compared and same point pairs are extracted. The loop of similarity calculation, stable marriage algorithm and comparision is repeated until there is no point left. 3 Evaluation An experiment is performed to evaluate efficiency of our stroke correspondence detection method. 3.1 Experiment We used a databse of 60 drawings with different stroke number. We showed each of 20 drawings randomly to a participant. We have 6 participants use mouse to draw drawings with same stroke number and same structure with the ones they are shown. Figure 1(a) shows an example in database and (b) shows a subject-drawn one. After drawing, corresponded strokes are displayed in same colors. Each participant is asked to count strokes which are corresponded differently from their intuition. Participants are students with average age of 25 and more than 5 years of computer experience. Most of them have little experience with doodles. (a) Database s drawing (b) User s drawing Figure 1: Experiment s example 3.2 Results and Discussion Data collected from participants is calculated to find average correct correspondence rate for each stroke number. We plotted a graph to show the relation of stroke number and correct correspondence rate (Figure 2). From the result, drawings with stroke number from 3 to 6 have higher correct correspondence rate. When stroke number increases, correct correspondence rate decreases but still oscillates between 0.7 and Our algorithm s accuracy falls when the drawing has many strokes which distribute densely like the legs in Figure 3. Because our algorithm bases largely on a position of strokes center in the drawing, the more stroke number is, distances between strokes centers have almost same values and this causes inaccuracy. In 14 and 22 cases, the rate suddenly decreases. Based on users comments, we consider small sample number (comparing to other cases) and messy drawings are the reasons. Figure 2: Relation of stroke number and correct correspondence rate Figure 3: Case with low correspondence rate 4 Conclusion We propose a method to automatically detect stroke correspondence in 2D drawings in relatively real time. The method allows users to draw relatively freely with accuracy rate ranges from In the future, we plan to employ stroke s size, stroke s merging and splitting.

In recent years, extensive efforts related to sketch have been developed such as sketch inbetweening and Chinese character recognition.

6 ( ) PC A D 2 E F 6 2 (, ) A B () C D () E () F 1 2: 2: 60Hz 2: 1: 3: A D (p <.05) A D ( p <.01 p <.05)

2 6 4 A D 2 E F 6 2 (, ) A B () C D () E () F 1 2: 2:

() 1 2 1(a) (b) 4100Hz 5 Support Vector Machine (SVM) 3 1 1 2 5 1 5 2 1 40 2 42 (W) 1.6 2.1 64 0.64 128 1.28 256 2.56 3 1 (Leave-one-trial out: LOTO).

7 () 1 2 1(a) (b) 4100Hz 5 Support Vector Machine (SVM) (W) (Leave-one-trial out: LOTO). 2 W=64 W=256 5 W= % 2 1(b) LOTO 4 2 0% 2 SVM Dynamic Bayesian Network(DBN) 1 SVM DBN SVM 95% 1 LOTO SVM DBN SVM 90.4% DBN 92.9% 2 SVM 79.6% DBN 74.4% DBN 4 (a) (b) 1: 2:

2 W=64 W=256 5 W=256 2 85% 2 1(b) 4 1 2 4 LOTO 4 2 0% 2 SVM Dynamic Bayesian

8 ( ) 1 3 kd ( ) (kd ) kd : 2: kd 8 kd kd kd 1 3:

3 ( ) 1 3 3 3 3 CSS 2 3 2.1 3 CSS(Cascading Style Sheets) Web PC 2.2 2.

9 3 ( ) CSS CSS(Cascading Style Sheets) Web PC CSS CSS 1 CSS 3 CPU: Pentium 4 3 GHz : 1 GB GPU: NVIDIA GeForce 6600GT(128 MB) PC OS Windows XP Apache HTTP Server PHP Gbps LAN 3 1(a) CSS 1(b) 200 4,175, pixel % 4 1 CSS msec (a) 1: 1: (msec) (b)

10 ( ) 1 (HCI) (POF) 2 1 POF 2.1 POF POF mm mm POF 28,800 POF 2.2 POF mm POF mm : 2:

卒業論文2.dvi

卒業論文2.dvi 15 GUI A study on the system to transfer a GUI sub-picture to the enlarging viewer for operational support 1040270 2004 2 27 GUI PC PC GUI Graphical User Interface PC GUI GUI PC GUI PC PC GUI i Abstract