Some Aspects of Pattern Recognition by Computer
A computer may gather a lot of information from its environment in an optical or graphical manner. A scene, as seen for instance from a TV camera or a picture, can be transformed into a symbolic description of points and lines or surfaces. This thesis describes several programs, written in the...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6887 |
| _version_ | 1826208076627181568 |
|---|---|
| author | Guzman-Arenas, Adolfo |
| author_facet | Guzman-Arenas, Adolfo |
| author_sort | Guzman-Arenas, Adolfo |
| collection | MIT |
| description | A computer may gather a lot of information from its environment in an optical or graphical manner. A scene, as seen for instance from a TV camera or a picture, can be transformed into a symbolic description of points and lines or surfaces. This thesis describes several programs, written in the language CONVERT, for the analysis of such descriptions in order to recognize, differentiate and identify desired objects or classes of objects in the scene. Examples are given in each case. Although the recognition might be in terms of projections of 2-dim and 3-dim objects, we do not deal with stereoscopic information. One of our programs (Polybrick) identifies parallelepipeds in a scene which may contain partially hidden bodies and non-parallelepipedic objects. The program TD works mainly with 2-dimensional figures, although under certain conditions successfully identifies 3-dim objects. Overlapping objects are identified when they are transparent. A third program, DT, works with 3-dim and 2-dim objects, and does not identify objects which are not completely seen. Important restrictions and suppositions are: (a) the input is assumed perfect (noiseless), and in a symbolic format; (b) no perspective deformation is considered. A portion of this thesis is devoted to the study of models (symbolic representations) of the objects we want to identify; different schemes, some of them already in use, are discussed. Focusing our attention on the more general problem of identification of general objects when they substantially overlap, we propose some schemes for their recognition, and also analyze some problems that are met. |
| first_indexed | 2024-09-23T14:00:05Z |
| id | mit-1721.1/6887 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:00:05Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/68872019-04-12T08:32:46Z Some Aspects of Pattern Recognition by Computer Guzman-Arenas, Adolfo A computer may gather a lot of information from its environment in an optical or graphical manner. A scene, as seen for instance from a TV camera or a picture, can be transformed into a symbolic description of points and lines or surfaces. This thesis describes several programs, written in the language CONVERT, for the analysis of such descriptions in order to recognize, differentiate and identify desired objects or classes of objects in the scene. Examples are given in each case. Although the recognition might be in terms of projections of 2-dim and 3-dim objects, we do not deal with stereoscopic information. One of our programs (Polybrick) identifies parallelepipeds in a scene which may contain partially hidden bodies and non-parallelepipedic objects. The program TD works mainly with 2-dimensional figures, although under certain conditions successfully identifies 3-dim objects. Overlapping objects are identified when they are transparent. A third program, DT, works with 3-dim and 2-dim objects, and does not identify objects which are not completely seen. Important restrictions and suppositions are: (a) the input is assumed perfect (noiseless), and in a symbolic format; (b) no perspective deformation is considered. A portion of this thesis is devoted to the study of models (symbolic representations) of the objects we want to identify; different schemes, some of them already in use, are discussed. Focusing our attention on the more general problem of identification of general objects when they substantially overlap, we propose some schemes for their recognition, and also analyze some problems that are met. 2004-10-20T20:04:29Z 2004-10-20T20:04:29Z 1967-02-01 AITR-224 http://hdl.handle.net/1721.1/6887 en_US AITR-224 3205410 bytes 2526732 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Guzman-Arenas, Adolfo Some Aspects of Pattern Recognition by Computer |
| title | Some Aspects of Pattern Recognition by Computer |
| title_full | Some Aspects of Pattern Recognition by Computer |
| title_fullStr | Some Aspects of Pattern Recognition by Computer |
| title_full_unstemmed | Some Aspects of Pattern Recognition by Computer |
| title_short | Some Aspects of Pattern Recognition by Computer |
| title_sort | some aspects of pattern recognition by computer |
| url | http://hdl.handle.net/1721.1/6887 |
| work_keys_str_mv | AT guzmanarenasadolfo someaspectsofpatternrecognitionbycomputer |