?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Computational+Theories+of+Object+Recognition&rft.creator=Edelman%2C+Shimon&rft.subject=Cognitive+Psychology&rft.description=Visual+categorization%2C+or+making+sense+of+novel+shapes+and+shape+classes%2C+is+a+computationally+challenging+and+behaviorally+important+task%2C+which+is+not+widely+addressed+in+computer+vision+or+visual+psychophysics+(where+the+stress+is+rather+on+the+generalization+of+recognition+across+changes+of+viewpoint).+This+paper+examines+the+categorization+abilities+of+four+current+approaches+to+object+representation%3A+structural+descriptions%2C+geometric+models%2C+multidimensional+feature+spaces%2C+and+similarities+to+reference+shapes.+It+is+proposed+that+a+scheme+combining+features+of+all+four+approaches+is+a+promising+candidate+for+a+comprehensive+and+computationally+feasible+theory+of+categorization&rft.date=1997&rft.type=Preprint&rft.type=NonPeerReviewed&rft.format=application%2Fpostscript&rft.identifier=http%3A%2F%2Fcogprints.org%2F560%2F2%2F199710002.ps&rft.identifier=++Edelman%2C+Shimon++(1997)+Computational+Theories+of+Object+Recognition.++%5BPreprint%5D+++++&rft.relation=http%3A%2F%2Fcogprints.org%2F560%2F