Indexing images by trees of visual content

An unsupervised algorithm for arranging an image database as a binary tree is described. Tree nodes are associated with image subsets, maintaining the property that the similarity among the images associated with the children of a node is higher than the similarity among the images associated with the parent node. Experiments with datasets of hundreds and thousands of images show that shallow trees can produce clustering into “meaningful” classes. Visual-content search trees can be used to automate image retrieval by content, or help a human to interactively search for images