| 摘要 |
A content-based image retrieval (CBIR) system has a front-end that includes a pipeline of one or more dynamically-constructed filters for measuring perceptual similarities between a query image (508) and one or more candidate images retrieved from a back-end comprised of a knowledge base accessed by an inference engine (512). The images include at least one color set having a set of properties including a number of pixels each having at least one color, a culture color associated with the color set, a mean and variance of the color set, a moment invariant, and a centroid. The filters analyse and compare the set of properties of the query image to the set of properties of the candidate images (514).
|
