This site has been permanently archived. This is a static copy provided by the University of Southampton.
--- abstract: 'Visual categorization, or making sense of novel shapes and shape classes, is a computationally challenging and behaviorally important task, 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: structural descriptions, geometric models, multidimensional feature spaces, 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' altloc: [] chapter: ~ commentary: ~ commref: ~ confdates: ~ conference: ~ confloc: ~ contact_email: ~ creators_id: [] creators_name: - family: Edelman given: Shimon honourific: '' lineage: '' date: 1997 date_type: published datestamp: 1997-10-17 department: ~ dir: disk0/00/00/05/60 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: [] eprint_status: archive eprintid: 560 fileinfo: /style/images/fileicons/application_postscript.png;/560/2/199710002.ps full_text_status: public importid: ~ institution: ~ isbn: ~ ispublished: ~ issn: ~ item_issues_comment: [] item_issues_count: 0 item_issues_description: [] item_issues_id: [] item_issues_reported_by: [] item_issues_resolved_by: [] item_issues_status: [] item_issues_timestamp: [] item_issues_type: [] keywords: ~ lastmod: 2011-03-11 08:54:04 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: ~ pubdom: FALSE publication: ~ publisher: ~ refereed: FALSE referencetext: ~ relation_type: [] relation_uri: [] reportno: ~ rev_number: 10 series: ~ source: ~ status_changed: 2007-09-12 16:30:56 subjects: - cog-psy succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: Computational Theories of Object Recognition type: preprint userid: 43 volume: ~