Name
Abstract | ||
|---|---|---|
The authors describe a new approach to indexing a specialized database using the color and spatial domain knowledge available for the database. They illustrate their approach by using it to solve the problem of indexing flower images when searching a flower patents database by color. The flower region is isolated from the background using an automatic iterative segmentation algorithm with domain knowledge-driven feedback. The flower's color is defined by the color names present in the flower region and their relative proportions. The database can be queried by example and by color names. The system provides a perceptually correct retrieval with natural language queries by using a natural language color classification derived from the ISCC-NBS color system and the X Window color names. The authors demonstrate the effectiveness of the strategy on a test database |
Year | DOI | Venue |
|---|---|---|
1999 | 10.1109/5254.796084 | IEEE Intelligent Systems |
Keywords | Field | DocType |
color name,natural language color classification,specialized database,test database,indexing flower image,flower region,domain knowledge,domain knowledge-driven feedback,flower patents database,x window color name,iscc-nbs color system,indexing flower patent,indexation,natural language,data management,information retrieval,algorithms,image retrieval,database indexing,botany,image processing,data bases,computer vision,query by example | Color term,Data mining,Information retrieval,Domain knowledge,Computer science,Image processing,Trademark,Search engine indexing,Image retrieval,Database index,Subject indexing | Journal |
Volume | Issue | ISSN |
14 | 5 | 1094-7167 |
Citations | PageRank | References |
37 | 5.06 | 29 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Madirakshi Das | 1 | 131 | 25.69 |
| R. Manmatha | 2 | 3071 | 221.44 |
| E. M. Riseman | 3 | 1402 | 458.95 |