Appling parallelism in image mining
Image mining deals with the study and development of new technologies that allow accomplishing this subject. A common mistake about image mining is identifying its scopes and limitations. Clearly it is different from computer vision and image processing areas. Image mining deals with the extraction...
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Objeto de conferencia |
| Lenguaje: | Inglés |
| Publicado: |
2007
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/20462 |
| Aporte de: |
| Sumario: | Image mining deals with the study and development of new technologies that allow accomplishing this subject. A common mistake about image mining is identifying its scopes and limitations. Clearly it is different from computer vision and image processing areas. Image mining deals with the extraction of image patterns from a large collection of images, whereas the focus of computer vision and image processing is in understanding and/or extracting specific features from a single image. On the other hand it might be thought that it is much related to content-based retrieval area, since both deals with large image collections. Nevertheless, image mining goes beyond the simple fact of recovering relevant images, the goal is the discovery of image patterns that are significant in a given collection of images. As a result, an image mining systems implies lots of tasks to be done in a regular time. Images provide a natural source of parallelism; so the use of parallelism in every or some mining tasks might be a good option to reduce the cost and overhead of the whole image mining process.
At this work we will try to draw the image minnig problem: its computational cost, and to propose a possible global or local parallel solution. |
|---|