Vectorizing Face Images by Interpreting Shape and Texture Computations
The correspondence problem in computer vision is basically a matching task between two or more sets of features. In this paper, we introduce a vectorized image representation, which is a feature-based representation where correspondence has been established with respect to a reference image. This re...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6641 |
| _version_ | 1826201069975240704 |
|---|---|
| author | Beymer, David |
| author_facet | Beymer, David |
| author_sort | Beymer, David |
| collection | MIT |
| description | The correspondence problem in computer vision is basically a matching task between two or more sets of features. In this paper, we introduce a vectorized image representation, which is a feature-based representation where correspondence has been established with respect to a reference image. This representation has two components: (1) shape, or (x, y) feature locations, and (2) texture, defined as the image grey levels mapped onto the standard reference image. This paper explores an automatic technique for "vectorizing" face images. Our face vectorizer alternates back and forth between computation steps for shape and texture, and a key idea is to structure the two computations so that each one uses the output of the other. A hierarchical coarse-to-fine implementation is discussed, and applications are presented to the problems of facial feature detection and registration of two arbitrary faces. |
| first_indexed | 2024-09-23T11:46:08Z |
| id | mit-1721.1/6641 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T11:46:08Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/66412019-04-11T02:52:38Z Vectorizing Face Images by Interpreting Shape and Texture Computations Beymer, David The correspondence problem in computer vision is basically a matching task between two or more sets of features. In this paper, we introduce a vectorized image representation, which is a feature-based representation where correspondence has been established with respect to a reference image. This representation has two components: (1) shape, or (x, y) feature locations, and (2) texture, defined as the image grey levels mapped onto the standard reference image. This paper explores an automatic technique for "vectorizing" face images. Our face vectorizer alternates back and forth between computation steps for shape and texture, and a key idea is to structure the two computations so that each one uses the output of the other. A hierarchical coarse-to-fine implementation is discussed, and applications are presented to the problems of facial feature detection and registration of two arbitrary faces. 2004-10-08T20:36:06Z 2004-10-08T20:36:06Z 1995-09-01 AIM-1537 http://hdl.handle.net/1721.1/6641 en_US AIM-1537 2729286 bytes 921596 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Beymer, David Vectorizing Face Images by Interpreting Shape and Texture Computations |
| title | Vectorizing Face Images by Interpreting Shape and Texture Computations |
| title_full | Vectorizing Face Images by Interpreting Shape and Texture Computations |
| title_fullStr | Vectorizing Face Images by Interpreting Shape and Texture Computations |
| title_full_unstemmed | Vectorizing Face Images by Interpreting Shape and Texture Computations |
| title_short | Vectorizing Face Images by Interpreting Shape and Texture Computations |
| title_sort | vectorizing face images by interpreting shape and texture computations |
| url | http://hdl.handle.net/1721.1/6641 |
| work_keys_str_mv | AT beymerdavid vectorizingfaceimagesbyinterpretingshapeandtexturecomputations |