This document summarizes the development of a prototype wrist contour sensor device for hand shape classification. [1] The device measures wrist contour variation using photo reflector arrays to overcome limitations of existing methods. [2] A classification experiment using k-NN and boosting methods on data from 7 subjects achieved around 70% accuracy when including a subject's data, but only 45-48% when excluding it, showing need to account for individual differences. [3] Future work will focus on downsizing the device, improving classification performance, and handling wrist position changes.

1. Hand Shape Classification
with a Wrist Contour Sensor
Development of a Prototype Device
Rui Fukui, Masahiko Watanabe, Tomoaki Gyota,
Masamichi Shimosaka, Tomomasa Sato (Univ. of Tokyo)

2. Background
 Gesture recognition is common
in households.
TV control, Video games, etc…
 Hand shapes can express much
information, but are not so popular. •Playing a video game with
gestures
Major hand shape recognition methods
•Wired glove •Electromyogram signals •Camera
Existing methods have some problems to introduce into households.
Disturbing haptic sense, stress on the user, confined space, etc…

3. Concept
 To overcome the problems, we take a different approach.
 We focus on “wrist contour※ " variation.
(※Wrist circumference contour near wrist ulna)
・ Examples of wrist contour variation

4. Prototype wrist contour measuring device

5. Application idea
 We suppose usage as an uncomplicated interface.
 Application idea example
– Game interface (baseball game)
 Players can express gripping and throwing motion more
naturally.

6. Demo movie

7. Problem: Individual differences
 Wrist contours of 3 hand shapes from 2 subjects
※ 実データの例
 Problem: Wrist contours vary not only with hand shapes
but also with subjects.
How to deal with these differences?
→Introduce feature extraction.
We organized 16 feature candidates and evaluated them. 7

8. Feature example
 Features are normalized by calibration data※.
(※Wrist contours of Fist and Open hand)
 Max increment value (One of feature
candidates)
・ Explanation and chart of Max increment
8
value

9. Hand shape classification experiment
 Settings
– Output classes: Well-known 8 hand shapes.
※Arm posture was fixed in one posture.
– Categories
A. Learning data include the subject’s data
Subjects ： 7, Attachment state: 5, Number of data: 30 per class
B. Learning data exclude the subject’s data
Subjects ： 10, Attachment state: 1, Number of data: 30 per class
– Classification method: k-NN method and boosting method

10. Experiment results
 Results
– Results are evaluated by Classification rate※ .
• Classification rate = (Num. of correct samples)/(Num. of all samples)
Classification k-NN Boosting
rate method method
A
(including 73.2% 64.1%
subject’s data)
B
(excluding 45.6% 47.8%
subject’s data)
・ Average classification rates of A, ・ Result of A by k-NN method.
B by two classification methods. Row : input class
Column: output class
When excluding subject's data, the
Diagonal line indicates correct answers.
rate decreaced by 20~30%. ※The larger number, the deeper color.

11. Conclusions & future works
 Conclusions
– We developed a wrist contour measuring device with
photo reflector arrays.
– We collected wrist contour data and considered relationships
with hand shapes.
– With features as input and 8 hand shapes as output,
we executed hand shape classification experiment
and got around 70% classification rate.
 Future works
– Development of a wrist-concentrated
device by downsizing.
– Improve classification performance.
– Deal with change of wrist pronation.
•Classification with a little slippage of the
band. Incorrect classification between
Fist and Thumbs up occurs.
We will demonstrate hand shape classification today.