- Title:
- Region-Based Image Retrieval with High-Level Semantic Color Names
- Presenter:
- Ying Liu
- Date:
- November 19, 2004
- Abstract:
- Due to the 'semantic gap' between low-level visual features and the rich
semantics in user's mind, performance of traditional content-based image
retrieval systems is far from user's expectation. In attempt to reduce the 'semantic gap', this presentation introduces a region-based image retrieval
system with high-level semantic color names used. For each segmented region, we define a perceptual color as the low-level color feature of the region. This perceptual color is then converted to a semantic color name. In this way, the system reduces the 'semantic gap' between numerical image features and the richness of human semantics. Four different ways to calculate perceptual color are compared. The experimental results confirm the performance gain that can be obtained through the
proposed system.
Brief Bio presenter:
Ms Ying Liu Received her B.Sc degree from dept. of Information Engineering in Xidian University China. She obtained her M.Eng degree from dept. of Electrical Engineering, National University of Singapore.
She worked as a Research Engineering in Center for Signal Processing in Nanyang Technological University (Singapore) before her PhD study. Her research interest includes image/video processing, pattern recognition, image feature extraction, image database retrieval.
Her PhD research topic is image database retrieval.
Back to:
|
