摘要 |
A method of recognizing different perspective views or images (i.e., multivariant views) of the same object (i.e., intraclass patterns). Each intraclass pattern, or different representation of the same object, is described as an orthonormal basis function expansion, and a single averaged matched spatial filter is produced from a weighted linear combination of these functions. The method eliminates the multiple matched spatial filters, and the extensive postprocessing of the matrix output from a multichannel correlator, which are used in the prior art.
|