Abstract: A system and method are provided for determining a color palette model from an image of a document. Pixel values of the image of the document are clustered to provide image clusters. Color layers of the image are determined, each color layer corresponding to an image cluster. Aspects of the color palette model can be determined using the color layers. Aspects of the color palette model include a foreground-background color pair for a content block in the document and a background-area color of the document.

Abstract: One or more text blocks, one or more images, and one or more contextual advertisements related to the text blocks are input into a mixed-content page layout model. One or more pages are generated by the mixed-content page layout model such that the text blocks, the images, and the contextual advertisements are displayed on the pages. For each contextual advertisement, a dynamic weight to a particular text block is determined. The mixed-content page layout model uses the dynamic weight for a contextual advertisement in determining where the advertisement is displayed within the pages in relation to the particular text block.

Abstract: A method for reducing view-dependent artifacts in a multi-projector system includes the steps of measuring, from multiple viewpoints, projection characteristics of an image projected by a multi-projector system, estimating view-dependent projection parameters that can reduce view-dependent artifacts, and computing rendering parameters for each projector so as to reduce the view-dependent artifacts.

Abstract: A method for tone mapping a digital image comprised of a plurality of high bit depth intensity values in linear space is disclosed. First, a plurality of liner intensity values are mapped from the linear space to a non-linear space (402). Then a left and a right boundary interval value are determined in the linear space for each of the plurality of high bit depth intensity value (404). A dither pattern is then overlaid onto the plurality of high bit depth intensity values in linear space (406). For each one of the plurality of high bit depth intensity values in linear space, one of the boundary interval values is selected, based on the current high bit depth intensity value, the left and right boundary interval values for the current pixel, and the dither pattern value overlaid onto the current pixel (408). Each of the selected boundary interval values are mapped into a lower bit depth non-linear space (410). And then the mapped selected boundary interval values are stored onto a computer readable medium.

Abstract: Systems and methods are provided for identifying an image having a target individual therein. An example system includes an image capture system that generates image data representing a set of a captured images of a predetermined area, an image database that stores the image data, a feature information database that stores feature information for identifying a person caught in an image as the target individual, a target individual image database that stores exemplar image data representing an image of the individual, and a processing subsystem for processing the image data to detect the target individual using the feature information and the exemplar image data.

Abstract: A method for automatic delivery of consistent imagery in a multi-projector system includes the steps of dividing the projectors into a plurality of sub-groups of projectors, each projector oriented to project a sub-frame to a sub-group display location, and adjusting the output of each projector in each sub-group to provide selected target display characteristics across all sub-groups.

Abstract: A method of determining a gamma curve of a display device includes identifying a region of interest of a display surface of the display device. A centroid of the region of interest is calculated. A plurality of input levels is applied to the display device to generate a corresponding plurality of displayed images on the display surface. At least one image of each of the displayed images is captured with a camera. A gamma curve of the display device is calculated based on the captured images and the centroid.

Abstract: A projection system for displaying an arbitrary combination of superimposed and tiled images using a plurality of projectors. A sub-frame generator generates a plurality of sub-frames corresponding to an image frame for simultaneous display by the projectors in at least partially overlapping positions on a display surface. The sub-frames are generated using optimal sub-pixel blending maps that are derived by forming a simulated image to approximate a target image subject to at least one smoothing constraint between the simulated image and the target image. The target image is formed from the image frame using at least one property (e.g., luminance or color) of each of the plurality of projectors.

Abstract: A method of displaying an image with a display device is provided. The method includes generating a first sub-frame and a second sub-frame corresponding to image data for the image including calculating a first sub-frame pixel value in the first sub-frame using a first sharpening factor associated with a first plurality of gradients from the image data, and alternating between displaying the first sub-frame in a first position and displaying the second sub-frame in a second position spatially offset from the first position.

Abstract: A method comprising analyzing a portion of image data to identify a characteristic of the portion of the image data and determining an algorithm based on the characteristic is provided. The algorithm is configured to generate at least first and second image data subsets with distortion using the image data such that the first and the second image data subsets are configured to cause an image corresponding to the image data to be reproduced without the distortion in response to being simultaneously displayed with first and second projection devices, respectively.

Abstract: Denoising of a plurality of pixels of a color digital image includes analyzing the plurality of pixels to identify those pixels having a high likelihood of containing significant noise; and forcing those pixels having a high likelihood of containing significant noise to be photometrically coherent with nearby pixels having a lower likelihood of containing significant noise.

Abstract: A method of displaying an image is provided. The method comprises receiving interlaced image data for the image where the interlaced data comprises a first field and a second field, generating a first sub-frame and a second sub-frame for the image using the first field, generating a third sub-frame and a fourth sub-frame for the image using the second field, and alternating between displaying the first sub-frame in a first position at a first time, displaying the second sub-frame in a second position horizontally offset from the first position at a second time that is subsequent to the first time, displaying the third sub-frame in a third position vertically offset from the first position at a third time that is subsequent to the second time, and displaying the fourth sub-frame in a fourth position horizontally and vertically offset from the first position at a fourth time that is subsequent to the second time.

Abstract: A method of dynamically displaying content to an audience is disclosed. The method includes displaying content to the audience wherein at least a portion of the audience is proximate a display means, capturing a plurality of responses from the audience, aggregating the plurality of responses and dynamically updating the displayed content based on the aggregated plurality of responses.

Abstract: A method of calibrating a camera includes capturing a set of dark images at each of a plurality of different exposure settings, thereby generating a plurality of sets of dark images. Each set of dark images is averaged, thereby generating a fixed pattern noise image corresponding to each one of the exposure settings. The method includes determining fixed pattern noise for at least one pixel of the camera based on an exposure setting of the camera and at least one of the fixed pattern noise images.

Abstract: A method of determining a gamma curve of a display device includes identifying a region of interest of a display surface of the display device. A centroid of the region of interest is calculated. A plurality of input levels is applied to the display device to generate a corresponding plurality of displayed images on the display surface. At least one image of each of the displayed images is captured with a camera. A gamma curve of the display device is calculated based on the captured images and the centroid.

Abstract: A method of displaying an image with a display device includes receiving image data for the image. The method includes generating a plurality of sub-frames corresponding to the image data. The method includes displaying the sub-frames at a set of spatially offset positions located on a circle.

Abstract: A system for providing advertising content includes a public display; a database configured to store the advertising content; and a central processing element configured to dynamically interact with participants in an activity and present the advertising content in connection with information about the activity on the public display. A method of providing advertising content includes conducting an activity involving participants; receiving input regarding the participants engaged in the activity; and displaying advertising content from a database concurrently with information regarding the activity.

Abstract: A method performed by a display system is provided. The method includes projecting a first infrared pattern from a first projection plane of a first projector into a scene, capturing the first infrared pattern from the scene in a capture plane of at least one image capture device, and determining a first correspondence mapping between the first projector and the image capture device from at least the first infrared pattern in the first projection plane and the first infrared pattern in the capture plane.

Abstract: A method of displaying images with a display system includes receiving image data for the images. The method includes generating at least a first sub-frame and at least a second sub-frame corresponding to the image data. The first sub-frame is projected with a first projector onto a target surface. The second sub-frame is projected with a second projector onto the target surface at a temporal offset from the projection of the first sub-frame, wherein the first and second projectors are positioned to project sub-frames that spatially overlap on the target surface.

Abstract: A method of displaying an image with a display system includes receiving image data for the image. The method includes generating a first single-color sub-frame and a second single-color sub-frame corresponding to the image data. The method includes projecting the first sub-frame with a first projector onto a target surface. The method includes projecting the second sub-frame with a second projector onto the target surface, wherein the first and the second sub-frames at least partially overlap on the target surface.