A playful toothbrush to motivate proper brushing for young children

Abstract

We have explored the design of a playful toothbrush to assist parents in motivating and getting their young children into a habit of proper and thor-ough tooth brushing. Our system includes a vision-based motion tracker that recognizes different tooth brushing motions, and a fun tooth brushing game in which a young child cleans a virtual picture of his/her dirty teeth by physically brushing his/her own teeth.

Full text

Page 1

A Playful Toothbrush to Motivate Proper Brushing for
Young Children
Yu-chen Chang1, Chao-ju Huang1, Jin-ling Lo3, Hao-hua Chu1,2
Department of Computer Science and Information Engineering1
Graduate Institute of Networking and Multimedia2
Department of Occupational Therapy3
National Taiwan University
hchu@csie.ntu.edu.tw
Abstract. We have explored the design of a playful toothbrush to assist parents
in motivating and getting their young children into a habit of proper and thor-
ough tooth brushing. Our system includes a vision-based motion tracker that
recognizes different tooth brushing motions, and a fun tooth brushing game in
which a young child cleans a virtual picture of his/her dirty teeth by physically
brushing his/her own teeth.
1Introduction
Proper brushing is essential for cleaning teeth and gums effectively and for maintain-
ing oral hygiene [1]. For many parents, tooth brushing is a required routine for young
children before bedtime. However, it is by no means an easy task for parents to get
their young children into a habit of brushing their teeth properly and thoroughly.
Several commercial products have been developed to entice a child to tooth brushing,
such as sugary toothpaste from Colgate [2], the music-rewarding ToothTune tooth-
brush from Hasbro [3], etc. Although these products can attract a child’s interest in
brushing, but they still fall short of getting a child to brush properly and thoroughly.
American Dental Association (ADA) recommends proper brushing methods for dif-
ferent groups of teeth [1]. For examples, the outer and inner tooth surfaces should be
brushed with a back & forth circular motion, the chewing surfaces of the teeth should
be cleaned by holding the brush flat and moving in backward and forward motion,
etc.
In this work, we would like to adapt Ubicomp and persuasive technology to help
young children learn and develop proper tooth brushing habit as recommended by
ADA [1]. Our system is based on the principles of pediatric occupational therapy in
which “play is a child’s way of learning and an outlet for his innate need of activity”
[4]. By embedding an interactive game into a young child’s tooth brushing activity,
we can make the tooth brushing activity playful to engage the young child into active
participation and learn proper tooth-brushing method.
We would like to distinguish between two purposes of the playful toothbrush. First,
for children who dislike brushing their teeth, the goal of our playful toothbrush would

Page 2

be to attract them to perform this task, which is similar to the Hasbro’s ToothTune
[3]. For children who already have the habit of brushing teeth routinely but not brush-
ing properly and thoroughly, the goal of our playful toothbrush would be to teach
them how to brush their teeth properly and thoroughly. These two purposes are not at
the same level and require different strategies in game design. For the former pur-
pose, the game should be simple and playful in order to attract children to perform the
task of brushing teeth. For the latter purpose, the game needs to engage children to
learn brushing teeth properly. To design the game, we not only have to motivate chil-
dren to do the activity but also need to take into account the requirement of cognitive
function for children to learn the proper brushing method through the game. To
achieve the learning part, we need to apply teaching-learning theory, such as informa-
tion processing [5], into the game design. The technical part of our system is con-
sisted of (1) a vision-based brushing motion tracker to recognize child brushing mo-
tions, and (2) a playful game to guide and reward proper brushing motions to a child.
Recently, several related projects are embedding digital persuasion into everyday
objects for a variety of human behavior modifications. Examples include the “Tooth
Tunes” tooth brush [3], the playful eating tray [6], the ViTo TV remote [7], the nutri-
tional-aware kitchen [8], etc. Our playful toothbrush shares a similar goal of adapting
technology into human behavior change. However, since a different behavior is tar-
geted, it has different design and technical considerations.
2 Preliminary Design and Implementation
Our system contains the following HW/SW components shown in Fig. 1: (1) a tooth-
brush extension is coded with different LED marker patterns on its four faces to aid
the vision-based motion recognition, in which the brush extension can be attached to
the end of a child’s standard toothbrush; (2) a single-camera vision system captures
the top-down view of brushing motions; (3) a tooth brushing game on a LCD display
takes a child’s physical brushing motions as game inputs. We will first describe the
vision-based brushing motion recognition, followed by the tooth brushing game.
Fig. 1. On the left shows the camera positioned at the top of a child’s head. In the middle is the
brush extension with LED marker patterns that can be attached to the end of a toothbrush. On
the right shows a child using the playful toothbrush.

Page 3

Brushing motion recognition. The vision-based approach is adapted to recognize 11
different brushing motions, in which each motion corresponds to brushing a different
part of teeth shown in Fig. 2 (a). To recognize these brushing motions, a web camera
positioned above a child’s head is used to capture the top-down view of the
toothbrush extension. Four rectangular faces (denoted as A, B, C, and D on Fig. 2(b),
where the face A is the same side as the toothbrush bristles) of the box-shaped brush
extension are coded with LED markers showing unique patterns distinguishable from
computer vision. By analyzing the 2D images from the camera, the orientation of the
brush extension and bristle can be reconstructed; furthermore, a child’s current brush-
ing motion can be determined. Consider the example in Fig. 2, to recognize Motion
#1 (brushing outer left teeth), the top-down view from the camera would see the brush
extension’s face B. In addition, the face B’s 2D orientation on the flat plane, which
can be calculated from the orientation of the LED marker pattern, should fall within
90~130 degrees angle. Since the brush extension’s orientation tells which direction
the toothbrush bristle is pointing at, we can infer the target group of teeth being
brushed.
Fig. 2. One the left shows eleven brushing motions corresponding to different groups of teeth.
On the right shows four LED markers encoded on the four faces of the brush extension.
Preliminary results. A preliminary experiment was conducted to evaluate the accu-
racy of our system. The results of three real teeth brushing sessions are shown in
Table 1. The total time is the time duration of each teeth brushing session, the error
time is the amount of time when our system fails to recognize correct brushing mo-
tions, and the recognition accuracy is the percentage of time our system correctly
recognizes brushing motions. The average accuracy is 97%, which is high. However,
since the tested subjects are adults, not young children, our future work will conduct
real tests on young children.
Tooth brushing game. The current game design starts with a virtual picture of dirty
teeth shown in Fig 3. The goal is for a young child to thoroughly clean these virtual
dirty teeth using his/her own physical tooth brushing motions as game inputs. For
example, while a child is brushing his/her outer left group of teeth, it is mapped to
cleaning the virtual outer left group of teeth in the game with visible spots of plaques
1. Outer Left
2. Outer Middle
3. Outer Right
4. Middle Left up
5. Middle Left down
6. Middle Right up
7. Middle Right down
8. Inner Left
9. Inner Right
10. Inner Middle up
11. Inner Middle down
(b)

Page 4

falling off. Fig. 3 shows two game screenshots. The child needs to finish cleaning all
the spots of plaques on a virtual picture of his/her dirty teeth to win the final applause.
Table 1. The error time and the recognition accuracy of the experiment
Sessions
1
2
3
Error Time (sec)
4.5
3
3.7
Total Time (sec)
129
123
142
Recognition Accuracy
96.5%
97.6%
97.4%
Fig. 3. Two game screenshots: on the left shows dirty teeth at the start of the game, on the right
shows when a child is brushing the front biting surface of the teeth.
3 Future Work
Our future work will conduct user study on young children to evaluate effectiveness
of our system in changing young children’s brushing habit. We are interested in com-
paring effectiveness between the traditional dental teaching methods versus our tooth
brushing game. Furthermore, we will explore different possible designs of tooth
brushing games, perhaps creating different versions for boys and girls.
References
[1]
[2]
[3]
[4]
[5]
American Dental Association, http://www.ada.org/public/games/animation/index.asp
Colgate-Palmolive Company, http://www.colgate.com
Hasbro, Inc., “TOOTH TUNES,” http://www.hasbro.com/toothtunes/.
N. Alessandrini, “A. Play – A child’s world,” Am J Occup Ther, vol. 3, 1949, pp. 9-12.
V. R. Todd, “Visual information analysis: Frame of reference for visual perception,” in P.
Kramer, J. Hinojosa (Eds.) Frames of reference for pediatric occupational therapy, Bal-
timore, MD: Lippincott, Williams & Wilkins, 1999, pp.205-255.
J. Lo, T. Lin, H. Chu, H. Chou, J. Chen, J. Hsu, and P. Huang, “Playful tray: Adopting
ubicomp and persuasive techniques into play-based occupational therapy for reducing
poor eating behavior in young children,” in Proc. of UBICOMP 2007, Sep. 2007.
J. Nawyn, S. S. Intille, and K. Larson, “Embedding behavior modification strategies into a
consumer electronic device: a case study,” in Proc. of UBICOMP 2006, Sep. 2006, pp
297-314.
P. Chi, J. Chen, H. Chu, and B. Chen, “Enabling nutrition-aware cooking in a smart
kitchen”, in ACM CHI 2007 extended abstract, April 2007.
[6]
[7]
[8]