Finding objects by grouping primitives

Digital library applications require very general object recognition techni ques. We describe an object recognition strategy that operates by grouping together image primitives in increasingly distinctive collections. Once a s ufficiently large group has been found, we declare that an object is presen t. We demonstrate this method on applications such as finding unclothed peo ple in general images and finding horses in general images. Finding clothed people is difficult, because the variation in colour and texture on the su rface of clothing means that it is hard to find regions of clothing in the image. We show that our strategy can be used to find clothing by marking th e distinctive shading patterns associated with folds in clothing, and then grouping these patterns.