Lewis is back from SIGGRAPH and we're happy to report everything went extremely well. We're getting great exposure and look forward to further developing the Lewis project in the future.

Check out some of the reviews on our media page.


Lewis Links:
1. Finding Faces
2. Calculating Position
3. Photography and Composition
4. Path Planning
5. Future R&D

More Lewis Info:
Technical Information
Sample Photos
Additional Sample Photos
Media Links

Lewis Home Page

[an error occurred while processing this directive]

Finding Faces


Chromosity scale (white=skin, black=not skin)


Pixels within white region on chromosity scale are colored blue above. Distance data from the laser is shown at the bottom.

Lewis finds candidate faces in a camera image by identifying contiguous regions of skin-colored pixels. All human skin falls into a clustered area in the YUV color space. By looking for contiguous areas of pixels with colors in this region, Lewis can find skin-colored blobs in the image. Lewis removes candidate regions that are the wrong shape (faces are roughly elliptical), or the wrong size (skin-colored walls, for example, are too large), or at the wrong height.

The laser provides Lewis with a good guess for all of the above, since he knows how far away the closest person is, what the camera tilt angle is, and approximately how tall people are. Lewis currently assumes that people are between 4 and 7 feet tall, so children may need to stand on a chair.