In EDS ansehen

Efficient indexing and retrieval of color image database based on color, shape and spatial relations

Gespeichert in:
Bibliographische Detailangaben
Titel: Efficient indexing and retrieval of color image database based on color, shape and spatial relations
Autoren: Wang, Ching-Sheng
Verlagsinformationen: Aletheia University, Tamsui, Taipei
Schlagwörter: Information storage and retrieval of data, spatial relation, Database theory, color image database, Computing methodologies for image processing
Beschreibung: Summary: This paper presents a total solution to extract color, shape and spatial features for indexing and retrieval color image database. As a technical contribution, a Seed-Filling like algorithm that could extract the shape and spatial relationship feature of image is proposed. In addition, this paper propose a new automatic indexing scheme of image database according to our clustering method and color sensation, which could be used to retrieve image efficiently. Due to the difficulty of determining how far objects are separated, this system uses qualitative spatial relations to analyze object similarity. Also, the system is incorporated with a visual interface and a set of tools, which allows the users to express the query by specify or sketch the images conveniently. Whether it is based on spatial relation, shape extraction, or color histogram similarity; our system considers various approaches and the integration of relevance feedback factors. The experience shows that the system provides a satisfactory solution toward Content-based Image Retrieval problem.
Publikationsart: Article
Dateibeschreibung: application/xml
Zugangs-URL: https://zbmath.org/1851074
Dokumentencode: edsair.c2b0b933574d..a8c100eda7d40a7dc14ab1babe4fc870
Datenbank: OpenAIRE
Beschreibung
Abstract:Summary: This paper presents a total solution to extract color, shape and spatial features for indexing and retrieval color image database. As a technical contribution, a Seed-Filling like algorithm that could extract the shape and spatial relationship feature of image is proposed. In addition, this paper propose a new automatic indexing scheme of image database according to our clustering method and color sensation, which could be used to retrieve image efficiently. Due to the difficulty of determining how far objects are separated, this system uses qualitative spatial relations to analyze object similarity. Also, the system is incorporated with a visual interface and a set of tools, which allows the users to express the query by specify or sketch the images conveniently. Whether it is based on spatial relation, shape extraction, or color histogram similarity; our system considers various approaches and the integration of relevance feedback factors. The experience shows that the system provides a satisfactory solution toward Content-based Image Retrieval problem.