A new discrimination method based on fuzzy subset theory is proposed in this paper. This approach uses Zernike moment invariants of the silhouette of the unknown object to form a set of fuzzy-weighted quantities called fuzzy quaternions. These are matched against those of known objects at predetermined viewpoints. To speed up the recognition process, a modified simplex method of the Nelder-Mead algorithm is used. Results obtained demonstrate the potential of the fuzzy quaternion as a viable basis for discrimination.