Abstract | ||
---|---|---|
The processing, description and recognition of dynamic (time-varying) textures are new exciting areas of texture analysis. Many real-world textures are dynamic textures whose retrieval from a video database should be based on both dynamic and static features. In this article, a method for extracting features revealing fundamental properties of dynamic textures is presented. These features are based on the normal flow and on the texture regularity though the sequence. Their discriminative ability is then successfully demonstrated on a full classification process. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11492542_28 | IbPRIA (2) |
Keywords | Field | DocType |
normal flow,fundamental property,new exciting area,static feature,dynamic texture recognition,dynamic texture,discriminative ability,texture regularity,real-world texture,full classification process,texture analysis | Computer vision,Video retrieval,Pattern recognition,Computer science,Image processing,Image retrieval,Normal flow,Artificial intelligence,Texture recognition,Discriminative model | Conference |
Volume | ISSN | ISBN |
3523 | 0302-9743 | 3-540-26154-0 |
Citations | PageRank | References |
39 | 3.15 | 10 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Renaud Péteri | 1 | 352 | 19.38 |
Chetverikov, D. | 2 | 956 | 99.89 |