Indexing flowers by color names using domain knowledge-driven segmentation
- 27 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
We describe a solution to the problem of indexing imagesof flowers for searching a flower patents database by color.We use a natural language color classification derived fromthe ISCC-NBS color system and the X Window color namesto effectively use the domain knowledge available, provideperceptually correct retrieval and allow natural languagequeries. We have developed an automatic iterative segmentationalgorithm with knowledge-driven feedback to isolatea flower region from the background. The color of the floweris defined by the color names present in the flower regionand their relative proportions. The database can be queriedby example and by color names. We demonstrate the effectivenessof the strategy on a test database.Keywords
This publication has 8 references indexed in Scilit:
- FOCUS: Searching for multi-colored objects in a diverse image databasePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Foreground/background segmentation of color images by integration of multiple cuesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Color segmentation in the HSI color space using the K-means algorithmPublished by SPIE-Intl Soc Optical Eng ,1997
- Segmentation of objects in images of natural colored surfacesPublished by SPIE-Intl Soc Optical Eng ,1996
- Image segmentation based on an adaptive 3D analysis of the CIE-L*a*b* color spacePublished by SPIE-Intl Soc Optical Eng ,1996
- Annotation of natural scenes using adaptive color segmentaionPublished by SPIE-Intl Soc Optical Eng ,1995
- Detection of Regions Matching Specified Chromatic FeaturesComputer Vision and Image Understanding, 1995
- QBIC project: querying images by content, using color, texture, and shapePublished by SPIE-Intl Soc Optical Eng ,1993