Margaret M. Fleck

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 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 from a wide collection of sources.

From informing to remembering: ubiquitous systems in interactive museums

Museums are excellent locations for testing ubiquitous systems; the Exploratorium in San Francisco offers a unique and challenging environment for just such a system. An important design consideration is how users switch between virtual and physical interactions.

D-Theory: Talking about Talking about Trees

Linguists, including computational linguists, have always been fond of talking about trees. In this paper, we outline a theory of linguistic structure which talks about talking about trees; we call this theory Description theory (D-theory). While important issues must be resolved before a complete picture of D-theory emerges (and also before we can build programs which utilize it), we believe that this theory will ultimately provide a framework for explaining the syntax and semantics of natural language in a manner which is intrinsically computational. This paper will focus primarily on one set of motivations for this theory, those engendered by attempts to handle certain syntactic phenomena within the framework of deterministic parsing.

Automatic Detection of Human Nudes

This paper demonstrates an automatic system for telling whether there are human nudes present in an image. The system marks skin-like pixels using combined color and texture properties. These skin regions are then fed to a specialized grouper, which attempts to group a human figure using geometric constraints on human structure. If the grouper finds a sufficiently complex structure, the system decides a human is present. The approach is shown to be effective for a wide range of shades and colors of skin and human configurations. This approach offers an alternate 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 human nudes, mostly obtained from the internet, and 4289 assorted control images, drawn from a wide variety of sources.

Finding Pictures of Objects in Large Collections of Images

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 in the classification process; the ability to deal with rather general objects in uncontrolled configurations and contexts. We illustrate these properties with four case-studies: one demonstrating the use of color and texture descriptors; one showing how trees can be described by fusing texture and geometric properties; one learning scenery concepts using grouped features; and one showing how this view of recognition yields a program that can tell, quite accurately, whether a picture contains naked people or not.

Some defects in finite-difference edge finders

This work illustrates and explains various artifacts in the output of five finite difference edge finders, those of J.F. Canny (1983, 1986), R.A. Boie et al. (1986) and R.A. Boie and I.J. Cox (1987), and three variations on that of D. Marr and E.C. Hildreth (1980), reimplemented with a common output format and method of noise suppression. These artifacts include gaps in boundaries, spurious boundaries, and deformation of region shape. >

Identifying nude pictures

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.

Jigsaw puzzle solver using shape and color

The jigsaw puzzle assembly problem is significant in that it can be applied to diverse areas such as repair of broken objects, restoration of archaeological findings, molecular docking problem for drug design, etc. This paper describes a new pictorial jigsaw puzzle solver which, in contrast to previous apictorial jigsaw puzzle solvers, uses chromatic information as well as geometric shape. We develop three new puzzle assembly algorithms (TSP&Kbest-based, TSP&AP-based, and AP-based algorithm) and new boundary and color matching operation. We tested the new puzzle solver with 6 different sets of color puzzle pieces. Experimental results show that chromatic information greatly aids in seeking the solution to the jigsaw puzzle problem. It is also discovered that in terms of how rapidly each assembly algorithm reaches a solution, the TSP and Kbest-based algorithm is the best, followed by TSP and AP-based algorithm, and followed by AP-based algorithm.

The topology of boundaries

Abstract High-level representations used in reasoning distinguish a special set of boundary locations, at which function values can change abruptly and across which adjacent regions may not be connected. Standard models of space and time, based on segmenting R n, do not allow these possibilities because they have the wrong topological structure at boundaries. This mismatch has made it difficult to develop formal mathematical models for high-level reasoning algorithms. This paper shows how to modify an R n model so as to have an appropriate topological structure. It then illustrates how the new models support standard reasoning algorithms, provide simple models for previously difficult situations, and suggest interesting new analyses based on change or non-change in scene topology.

Multiple widths yield reliable finite differences (computer vision)

A finite difference edge finder in which the finite difference is computed at a range of widths, i.e. a range of distances between data points, is introduced. Wide operators report low-amplitude responses more reliably than narrow operators, so if wide operators are used to fill gaps in narrow operator responses, each operator can be restricted to report only statistically reliable responses without losing many real features. This sharply reduces the noise in the final output. Theoretical bounds on spurious responses in the finite difference outputs, given only weak assumptions about the signal and noise, are presented. The expected response of the edge finder to an ideal straight step edge is also analyzed. These performance measures are compared with those of a standard algorithm based on Gaussian smoothing and those of a second algorithm that also considers the spatial structure of noise. The algorithms prove equally good at suppressing noise, but are better able to detect faint or blurred features. These predictions are confirmed by empirical tests on real images. >