Nec Laboratories America, Inc.

Other

Kriegman-belhumeur Vision Technologies, LLC

David W Jacobs

Karvel K Thornber

David J Kriegman

Peter Neil Belhumeur

Neeraj Kumar

Ronen Ezra Basri

A system is provided for localizing parts of an object in an image by training local detectors using labeled image exemplars with fiducial points corresponding to parts within the image. Each local detector generates a detector score corresponding to the likelihood that a desired part is located at a given location within the image exemplar. A non-parametric global model of the locations of the fiducial points is generated for each of at least a portion of the image exemplars. An input image is analyzed using the trained local detectors, and a Bayesian objective function is derived for the input image from the non-parametric model and detector scores. The Bayesian objective function is optimized using a consensus of global models, and an output is generated with locations of the fiducial points labeled within the object in the image.

Method and system for localizing parts of an object in an image for computer vision applications

A method is provided for localizing parts of an object in an image by training local detectors using labeled image exemplars with fiducial points corresponding to parts within the image. Each local detector generates a detector score corresponding to the likelihood that a desired part is located at a given location within the image exemplar. A non-parametric global model of the locations of the fiducial points is generated for each of at least a portion of the image exemplars. An input image is analyzed using the trained local detectors, and a Bayesian objective function is derived for the input image from the non-parametric model and detector scores. The Bayesian objective function is optimized using a consensus of global models, and an output is generated with locations of the fiducial points labeled within the object in the image.

The present invention is a method of deriving a reflectance function that analytically approximates the light reflected from an object model in terms of the spherical harmonic components of light. The reflectance function depends upon the intensity of light incident at each point on the model, the intensity of light diffusely reflected, and the intensity of light broadened-specularly reflected in the direction of an observer. This reflectance function is used in the process of machine vision, by allowing a machine to optimize the reflectance function and arrive at an optimal rendered image of the object model, relative to an input image. Therefore, the recognition of an image produced under variable lighting conditions is more robust. The reflectance function of the present invention also has applicability in other fields, such as computer graphics.

Broadened-specular reflection and linear subspaces for object recognition

The present invention is a method of deriving a reflectance function that analytically approximates the light reflected from an object model in terms of the spherical harmonic components of light. The reflectance function depends upon the intensity of light incident at each point on the model, but excludes light originating from below a local horizon, therefore not contributing to the reflectance because of the cast shadows. This reflectance function is used in the process of machine vision, by allowing a machine to optimize the reflectance function and arrive at an optimal rendered image of the object model, relative to an input image. Therefore, the recognition of an image produced under variable lighting conditions is more robust. The reflectance function of the present invention also has applicability in other fields, such as computer graphics.

Cast shadows and linear subspaces for object recognition

The Torrance-Sparrow model of off-specular reflection is recast in a significantly simpler and more transparent form in order to render a spherical-harmonic decomposition more feasible. By assuming that a physical surface consists of small, reflecting facets whose surface normals satisfy a normal distribution, the model captures the off-specular enhancement of the reflected intensity distribution often observed at large angles of incidence and reflection, features beyond the reach of the phenomenological broadening models usually employed. In passing we remove a physical inconsistency in the original treatment, restoring reciprocity and correcting the dependence of reflectance on angle near grazing incidence. It is noted that the results predicted by the model are relatively insensitive to values of its one parameter, the width of the distribution of surface normals.

Torrance-sparrow off-specular reflection and linear subspaces for object recognition

A method for choosing an image from a plurality of three-dimensional models which is most similar to an input image is provided. The method includes the steps of: (a) providing a database of the plurality of three-dimensional models; (b) providing an input image; (c) positioning each three-dimensional model relative to the input image; (d) for each three-dimensional model, determining a rendered image that is most similar to the input image by: (d)(i) computing a linear subspace that describes an approximation to the set of all possible rendered images that each three-dimensional model can produce under all possible lighting conditions where each point in the linear subspace represents a possible image; and one of (d)(ii) finding the point on the linear subspace that is closest to the input image or finding a rendered image in a subset of the linear subspace obtained by projecting the set of images that are generated by positive lights onto the linear subspace; (e) computing a measure of similarly between the input image and each rendered image; and (f) selecting the three-dimensional model corresponding to the rendered image whose measure of similarity is most similar to the input image. Step (d) is preferably repeated for each of a red, green, and blue color component for each three-dimensional model. The linear subspace is preferably either four-dimensional or nine-dimensional.

Growing community of inventors

Bethesda, MD, United States of America

David W Jacobs