[English/ Japanese]

TagTansu: a Wardrobe to Support Creating a Picture Database of Clothes
Last Update: 2008/5/22@Creation Date: 2008/5/22



Abstract

We propose a novel capture and annotation system called TagTansu, which can easily capture pictures of clothes and add annotations to support creating a picture database of clothes. TagTansu consists of hook sensors and capture components attached inside the doors of a tansu (a wardrobe).Using TagTansu, users can easily take pictures of clothes and add annotations (e.g. types and weight of clothes) to the pictures just by hanging the clothes on a hook.

Figure 1. Basic concept of TagTansu



Implementation

TagTansu mainly consists of several devices attached to the inside doors of a tansu (a wardrobe). We selected a wardrobe with double doors to utilize both door surfaces. As shown in figure 2, we attach hook sensors to one door and attach capture components -a camera, lights and an LCD- to the other door.

There are three hook sensors attached on a human shaped wood plate (Figure 3). We embedded a pressure sensor to each hook for detecting weight of clothes hung on the hook. Users can add different tags by hanging clothes on different hooks: a "tops" tag on the upper hooks and a "bottom" tag on the lower hook.

A captured picture is displayed on the LCD and saved to the host PC in JPEG format. The system adds annotations -one of the three types and estimated weight of the clothes, and a timestamp- to the picture as EXIF information. Figure 4 shows examples of pictures captured by TagTansu. The picture is also uploaded to the Flickr (Figure 5).

 

Figure 2: Prototype of TagTansu.
(1) hook sensors, (2) lights, (3)LCD, (4) USB camera, (5) a magnet switch, (6) a host PC.

Figure 3: Prototype of hook sensors.
flickr
Figure 4: Examples of pictures captured by TagTansu
Figure 5: Example of pictures uploaded to the Flickr



Publication
  • Tsukada, K., Tsujita, H., Siio, I.: TagTansu:A Wardrobe to Support Creating a Picture Database of Clothes, Adjunct Proceedings of Pervasive2008, pp. 49-52, (2008). [PDF]