Color-metric pattern-card matching for viewpoint invariant image retrieval

In this paper, viewpoint independent image retrieval by color-metric pattern-card matching is presented. First, a photometric color invariant is proposed measuring a local color property of a pixel and its neighboring pixels while discounting the disturbing influences of shading, shadows and highlights. Color-metric pattern-cards are constructed on the basis of the photometric color invariant indicating whether a particular discrete photometric color invariant value is present in an image. To express similarity between color-metric pattern-cards, similarity functions are proposed and evaluated on a database of 500 images taken from 2-D and 3-D colored man-made objects in real world 3-D scenes. The experimental results show that high image retrieval accuracy is achieved by two distinct similarity functions depending on the presence of object clutter in the scene. Furthermore, image retrieval by color-metric pattern-card matching is to a large degree robust to partial occlusion and a change in viewing position. Good run-time performance of the pattern-card matching process is achieved allowing for fast image retrieval by example image.