Finding Naked People

This paper demonstrates a content based retrieval strategy that can tell whether there are naked people present in an image No manual intervention is required The approach combines color and tex ture properties to obtain an e ective mask for skin regions The skin mask is shown to be e ective for a wide range of shades and colors of skin These skin regions are then fed to a specialized grouper which at tempts to group a human gure using geometric constraints on human structure This approach introduces a new view of object recognition where an object model is an organized collection of grouping hints ob tained from a combination of constraints on geometric properties such as the structure of individual parts and the relationships between parts and constraints on color and texture The system is demonstrated to have precision and recall on a test set of uncontrolled images of naked people mostly obtained from the internet and assorted control images drawn from a wide collection of sources