?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Real-time+trajectory+analysis+using+stacked+invariance+methods&rft.creator=Kitts%2C+B.&rft.subject=Artificial+Intelligence&rft.subject=Complexity+Theory&rft.description=Invariance+methods+are+used+widely+in+pattern+recognition+as+a+preprocessing+stage+before+algorithms+such+as+neural+networks+are+applied+to+the+problem.+A+pattern+recognition+system+has+to+be+able+to+recognise+objects+invariant+to+scale%2C+translation%2C+and+rotation.+Presumably+the+human+eye+implements+some+of+these+preprocessing+transforms+in+making+sense+of+incoming+stimuli%2C+for+example%2C+placing+signals+onto+a+log+scale.+This+paper+surveys+many+of+the+commonly+used+invariance+methods%2C+and+assesses+their+performance+on+one+particular+problem%2C+estimating+the+quality+of+human+motor+imitation+invariant+to+rotation%2C+scale+and+translation.&rft.date=1998&rft.type=Preprint&rft.type=NonPeerReviewed&rft.format=application%2Fpostscript&rft.identifier=http%3A%2F%2Fcogprints.org%2F456%2F2%2Fpreproc21.ps&rft.identifier=++Kitts%2C+B.++(1998)+Real-time+trajectory+analysis+using+stacked+invariance+methods.++%5BPreprint%5D++++(Unpublished)++&rft.relation=http%3A%2F%2Fcogprints.org%2F456%2F