Image Recognition on Mobile Phones

One of the first algorithms utilizing color was proposed by Swain et al. [1]. This algorithm computes color histograms for images, followed by an intersection of the histograms to perform the similarity search. Improvements that add spatial information and correlation to color histograms were proposed in [2] and [3]. Since color histograms are very sensitive to noisy images, applying this to our domain is likely to cause problems since cameras on mobile phones tend to take relatively noisy pictures.