Color based retrieval and recognition

In content based retrieval, color indexing is one of the most prevalent retrieval methods. Two key problems in color indexing are: (1) determination of the color space, and (2) finding the best distance measure. Most of the attention from the research literature has been focussed on the color model with little or no consideration of the noise models. By focusing on the noise model, we show how to find a distance measure which is optimal in the sense that it maximizes the similarity probability. Our results include experiments in color based retrieval and object recognition. Furthermore, we implement and test several promising algorithms from the research literature as benchmarks