A region-based approach to face segmentation and tracking in video sequences
In this paper we propose an algorithm for face segmentation and tracking which is able to obtain the actual shape of a face present in a video sequence and track it in time. The face segmentation step relies on an initial partition of the image, based on color homogeneity, which is fine enough to co...
Guardado en:
| Publicado: |
2001
|
|---|---|
| Materias: | |
| Acceso en línea: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_03270793_v31_n2_p99_Vilaplana http://hdl.handle.net/20.500.12110/paper_03270793_v31_n2_p99_Vilaplana |
| Aporte de: |
| id |
paper:paper_03270793_v31_n2_p99_Vilaplana |
|---|---|
| record_format |
dspace |
| spelling |
paper:paper_03270793_v31_n2_p99_Vilaplana2023-06-08T15:33:09Z A region-based approach to face segmentation and tracking in video sequences Face detection Face segmentation Face tracking Principal component analysis In this paper we propose an algorithm for face segmentation and tracking which is able to obtain the actual shape of a face present in a video sequence and track it in time. The face segmentation step relies on an initial partition of the image, based on color homogeneity, which is fine enough to contain, among others, all the regions that form the face. Since a face contains a set of regions with chrominance homogeneity, the regions of the initial partition are merged following this criterion. The sequence of mergings is represented as a binary tree. For each node in the tree a similarity measure between the node and a face class is calculated. This measure is related to the likelihood of an image of being a face. The node which maximizes this likelihood is selected, giving a first estimate of the face. The final face is obtained by a refinement step that merges the remaining face regions to the face estimate. In the tracking step, the face partition in the previous image is motion compensated (projected) and the final face is obtained by a merging process. 2001 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_03270793_v31_n2_p99_Vilaplana http://hdl.handle.net/20.500.12110/paper_03270793_v31_n2_p99_Vilaplana |
| institution |
Universidad de Buenos Aires |
| institution_str |
I-28 |
| repository_str |
R-134 |
| collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
| topic |
Face detection Face segmentation Face tracking Principal component analysis |
| spellingShingle |
Face detection Face segmentation Face tracking Principal component analysis A region-based approach to face segmentation and tracking in video sequences |
| topic_facet |
Face detection Face segmentation Face tracking Principal component analysis |
| description |
In this paper we propose an algorithm for face segmentation and tracking which is able to obtain the actual shape of a face present in a video sequence and track it in time. The face segmentation step relies on an initial partition of the image, based on color homogeneity, which is fine enough to contain, among others, all the regions that form the face. Since a face contains a set of regions with chrominance homogeneity, the regions of the initial partition are merged following this criterion. The sequence of mergings is represented as a binary tree. For each node in the tree a similarity measure between the node and a face class is calculated. This measure is related to the likelihood of an image of being a face. The node which maximizes this likelihood is selected, giving a first estimate of the face. The final face is obtained by a refinement step that merges the remaining face regions to the face estimate. In the tracking step, the face partition in the previous image is motion compensated (projected) and the final face is obtained by a merging process. |
| title |
A region-based approach to face segmentation and tracking in video sequences |
| title_short |
A region-based approach to face segmentation and tracking in video sequences |
| title_full |
A region-based approach to face segmentation and tracking in video sequences |
| title_fullStr |
A region-based approach to face segmentation and tracking in video sequences |
| title_full_unstemmed |
A region-based approach to face segmentation and tracking in video sequences |
| title_sort |
region-based approach to face segmentation and tracking in video sequences |
| publishDate |
2001 |
| url |
https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_03270793_v31_n2_p99_Vilaplana http://hdl.handle.net/20.500.12110/paper_03270793_v31_n2_p99_Vilaplana |
| _version_ |
1768544867370139648 |