as a visiting scientist from Kyoto University in Japan. My plan for research during the stay was to develop a model-based object recognition program. Upon arrival, I chose an image of an office scene (Fig. 1 ) as an example image; the image was one of a set that Ron Ohlander had used in his research on color image segmentation. The task I set for my program was to recognize the chair in this image.
I began to write a "knowledge-based" program for chair recognition by creating a set of heuristic rules for the task. It seemed that in addition to geometric relationships, a good source of constraints was color information, such as "the back and the seat of a chair have the same color". The effort of creating heuristic rules one after another, however, was not a satisfying game, since every time I came up with a reasonably functioning program, I could also find a chair that was an exception to the rules.
2. The Origami world
Ohlander's color segmentation program, which was quite famous at the time, could segment the image of Fig. 1 into regions as shown in Fig. 2. As I stared at the results, not only could I still see a chair without using color information, but I could also perceive the shape of the object without