This paper addresses the problem of recognizing three-dimensional objects b
ounded by smooth curved surfaces from image contours found in a single phot
ograph. The proposed approach is based on a viewpoint-invariant relationshi
p between object geometry and certain image features under weak perspective
projection. The image features themselves are viewpoint-dependent. Concret
ely, the set of all possible silhouette bitangents, along with the contour
points sharing the same tangent direction, is the projection of a one-dimen
sional set of surface points where each point lies on the occluding contour
for a five-parameter family of viewpoints. These image features form a one
-parameter family of equivalence classes, and it is shown that each class c
an be characterized by a set of numerical attributes that remain constant a
cross the corresponding five-dimensional set of viewpoints. This is the bas
is for describing objects by "invariant" curves embedded in high-dimensiona
l spaces. Modeling is achieved by moving an object in front of a camera and
does not require knowing the object-to-camera transformation; nor does it
involve implicit or explicit three-dimensional shape reconstruction. At rec
ognition time, attributes computed from a single image are used to index th
e model database, and both qualitative and quantitative verification proced
ures eliminate potential false matches. The approach has been implemented a
nd examples are presented. (C) 1998 Academic Press.