Learning Three-Dimensional Shape Models for Sketch Recognition
Artifacts made by humans, such as items of furniture and houses, exhibit an enormous amount of variability in shape. In this paper, we concentrate on models of the shapes of objects that are made up of fixed collections of sub-parts whose dimensions and spatial arrangement exhibit variation. Our g...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/7424 |
| _version_ | 1811073661550985216 |
|---|---|
| author | Kaelbling, Leslie P. Lozano-Pérez, Tomás |
| author_facet | Kaelbling, Leslie P. Lozano-Pérez, Tomás |
| author_sort | Kaelbling, Leslie P. |
| collection | MIT |
| description | Artifacts made by humans, such as items of furniture and houses, exhibit an enormous amount of variability in shape. In this paper, we concentrate on models of the shapes of objects that are made up of fixed collections of sub-parts whose dimensions and spatial arrangement exhibit variation. Our goals are: to learn these models from data and to use them for recognition. Our emphasis is on learning and recognition from three-dimensional data, to test the basic shape-modeling methodology. In this paper we also demonstrate how to use models learned in three dimensions for recognition of two-dimensional sketches of objects. |
| first_indexed | 2024-09-23T09:36:34Z |
| format | Article |
| id | mit-1721.1/7424 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T09:36:34Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/74242019-04-12T08:40:22Z Learning Three-Dimensional Shape Models for Sketch Recognition Kaelbling, Leslie P. Lozano-Pérez, Tomás sketch recognition object recognition computer vision Artifacts made by humans, such as items of furniture and houses, exhibit an enormous amount of variability in shape. In this paper, we concentrate on models of the shapes of objects that are made up of fixed collections of sub-parts whose dimensions and spatial arrangement exhibit variation. Our goals are: to learn these models from data and to use them for recognition. Our emphasis is on learning and recognition from three-dimensional data, to test the basic shape-modeling methodology. In this paper we also demonstrate how to use models learned in three dimensions for recognition of two-dimensional sketches of objects. Singapore-MIT Alliance (SMA) 2004-12-13T06:56:19Z 2004-12-13T06:56:19Z 2005-01 Article http://hdl.handle.net/1721.1/7424 en Computer Science (CS); 408469 bytes application/pdf application/pdf |
| spellingShingle | sketch recognition object recognition computer vision Kaelbling, Leslie P. Lozano-Pérez, Tomás Learning Three-Dimensional Shape Models for Sketch Recognition |
| title | Learning Three-Dimensional Shape Models for Sketch Recognition |
| title_full | Learning Three-Dimensional Shape Models for Sketch Recognition |
| title_fullStr | Learning Three-Dimensional Shape Models for Sketch Recognition |
| title_full_unstemmed | Learning Three-Dimensional Shape Models for Sketch Recognition |
| title_short | Learning Three-Dimensional Shape Models for Sketch Recognition |
| title_sort | learning three dimensional shape models for sketch recognition |
| topic | sketch recognition object recognition computer vision |
| url | http://hdl.handle.net/1721.1/7424 |
| work_keys_str_mv | AT kaelblinglesliep learningthreedimensionalshapemodelsforsketchrecognition AT lozanopereztomas learningthreedimensionalshapemodelsforsketchrecognition |