. 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 texture properties to obtain an effective mask for skin regions. The skin mask is shown to be effective for a wide range of shades and colors of skin. These skin regions are then fed to a specialized grouper, which attempts to group a human figure 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 obtained 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 60% precision and 52% recall on a test set of 138 uncontrolled images of naked people, mostly obtained from the internet, and 1401 assorted control images, drawn f...

. Retrieving images from very large collections, using image content as a key, is becoming an important problem. Users prefer to ask for pictures using notions of content that are strongly oriented to the presence of abstractly defined objects. Computer programs that implement these queries automatically are desirable, but are hard to build because conventional object recognition techniques from computer vision cannot recognize very general objects in very general contexts. This paper describes our approach to object recognition, which is structured around a sequence of increasingly specialized grouping activities that assemble coherent regions of image that can be shown to satisfy increasingly stringent constraints. The constraints that are satisfied provide a form of object classification in quite general contexts. This view of recognition is distinguished by: far richer involvement of early visual primitives, including color and texture; hierarchical grouping and learning strategies...

The outline in a single picture of a generic algebraic surface of degree three or greater completely determines the projective geometry of the surface. The result holds for a generic perspective view of ageneric algebraic surface, where the camera calibration parameters and the focal point are unknown. Known camera calibration appears not to reduce the projectiveambiguity.The result is constructive.

It is known that rotationally symmetric surfaces can be recognized from their outlines alone, using crossratio 's of bitangent intersections. This paper demonstrates a successful implementation of this technique, using a novel bitangent finder, that works on images of real scenes. We report on the stability of the crossratios, and compare this to affine invariants. The recognition technique is shown to extend to the case of straight homogeneous generalised cylinders. 1 Introduction This paper continues the work described in [11], where it was shown that surfaces of revolution can be recognised from their outline alone, without knowledge of object pose or camera calibration. The recognition method involves commputing indexes[10, 47, 35, 21] from the outline which are used to recognise the object via a hash table. In this paper, we demonstrate successful indexing for a range of images of real objects using the constructions of [11]. We show that these constructions also yield indexing f...

. Recognising a curved surface from its outline in a single view is a major open problem in computer vision. This paper shows techniques for recognising a significant class of surfaces from a single perspective view. The approach uses geometrical facts about bitangencies, creases, and inflections to compute descriptions of the surface's shape from its image outline. These descriptions are unaffected by the viewpoint or the camera parameters. We show, using images of real scenes, that these representations identify surfaces from their outline alone. This leads to fast and effective recognition of curved surfaces. The techniques we describe work for surfaces that have a rotational symmetry, or are projectively equivalent to a surface with a rotational symmetry, and can be extended to an even larger class of surfaces. All the results in this paper are for the case of full perspective. The results additionally yield techniques for identifying the line in the image plane corresponding to th...

This paper demonstrates an automatic system for telling whether there are naked people present in an image. The approach combines color and texture properties to obtain a mask for skin regions, which is shown to be effective for a wide range of shades and colors of skin. These skin regions are then fed to a specialized grouper, which attempts to group a human figure 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 obtained from a combination of constraints on color and texture and constraints on geometric properties such as the structure of individual parts and the relationships between parts. The system demonstrates excellent performance on a test set of 565 uncontrolled images of naked people, mostly obtained from the internet, and 4289 assorted control images, drawn from a wide collection of sources. Keywords: Object Recognition, Computer Vision, Erotica/Porno...