Canon Kabushiki Kaisha

Microsoft Technology Licensing, LLC

Canon Information Systems, Inc.

Microsoft Corporation

John S Haikin

Todd D Newman

Timothy Louis Kohler

Francisco H Imai

Sharon A Henley

Rong Wang

Arkady Ten

Rocklin James Sloan

Image data of a scene is captured. Spectral profile information is obtained for the scene. A database of plural spectral profiles is accessed, each of which maps a material to a corresponding spectral profile reflected therefrom. The spectral profile information for the scene is matched against the database, and materials for objects in the scene are identified by using matches between the spectral profile information for the scene against the database. Metadata which identifies materials for objects in the scene is constructed, and the metadata is embedded with the image data for the scene.

Image capture for spectral profiling of objects in a scene

An image capturing apparatus, method, and storage medium identifying image metadata based on user interest. The image capturing apparatus includes a first image capturing unit configured to capture an image of a scene for a user, a second image capturing unit configured to capture an image of the user, an identification unit configured to identify at least one region of interest of the scene based on a combination of eye and facial characteristics of the user of the image capturing apparatus during an image capturing operation, a processing unit configured to analyze at least facial characteristics of the user associated with each region of interest during the image capturing operation, a determining unit configured to determine a facial expression classification associated with each region of interest based on corresponding analyzed facial characteristics for each region during the image capturing operation, a recording unit configured to record facial expression metadata based on information representing the at least one region of interest and the facial expression classification associated with an image captured during the image capturing operation, and a rendering unit configured to render the image using the recorded facial expression metadata.

Systems and methods for image capturing based on user interest

An image capturing apparatus that includes an image capture unit, an interface unit, a processing unit, and a display unit, wherein the image capture unit captures an image, the memory unit stores the image, the interface unit loads one or more look transforms into the image capturing apparatus, the processing unit converts color signals of the image from values of the image capturing apparatus into an output rendering space using a device-independent color space, automatically applies the look transform(s) to the image, and generates a rendered image, which is then displayed by the display unit.

Image capturing systems and methods utilizing customizable look management

An image capture device includes an imaging assembly having a spectral sensitivity tunable in accordance with a spectral capture mask. A pre-capture captures a sample image of a scene using the imaging assembly tuned by a first spectral capture mask. A second spectral capture mask is constructed by calculations which use image data of the sample image. The second spectral capture mask is constructed to tune the spectral sensitivity of the imaging assembly so as to adjust respective capture parameters for different objects in the scene. The second spectral capture mask is applied to the imaging assembly. An image of the scene is captured with the second spectral capture mask applied to the imaging assembly.

Adaptive color imaging

The present invention provides for determining a gamut boundary description for a color device, the color device being characterized at least by a destination transform which converts colors from a device-independent color space to a device-dependent color space and which reports out-of-gamut colors. A set of sample values is determined in the device-independent color space. For each of the sample values within the set of sample values, the destination transform is applied to the sample value, and in a case where the sample value is in gamut, the sample value is included within a set of gamut boundary values. The gamut boundary description is determined by forming a set of polygonal surfaces based on the set of gamut boundary values. Accordingly, a gamut boundary description is determined without necessarily having to sample additional color values as the number of colorant channels for the color device increases.

Computation of gamut boundary by sampling device-independent color space

Conversion of colors of an image from a source color space to a destination color space by use of both a color profile and an image profile. The source and destination color spaces are respectively represented by source and destination color space transformations associated with source and destination color profiles. Colors in an image are converted from the source color space to a device-independent color space, using the source color space transformation. A gamut mapping is determined from a source color gamut to a destination color gamut, by using a gamut boundary description constructed either from a source image profile which is separate from the source color profile, or from a destination image profile which is separate from the destination color profile. The gamut mapping is applied, and the gamut mapped colors are transformed from the device-independent color space to the destination color space, using the destination color space transformation.

Converting digital values corresponding to colors of an image from a source color space to a destination color space

Color management converting source-side color images into destination-side color images. A module library includes module entries corresponding to function modules implementing color processing functionalities. Each module entry includes a module locator, and some include a profile interface definition. A profile library includes profile entries corresponding to sources of parameters. Profile entries include a profile locator and a profile interface definition. A rule library includes external and internal rules which characterize color transformation workflows. Each external rule is associated with function modules. An interface receives factual input including factual input derived from source-side color image data. A rule engine determines a sequence of function modules and sources of parameters by using the factual input and the plural and external rules in the rule library, and builds the color transformation workflow from the determined sequence of function modules and sources of parameters.

Rule-based color management and image processing system

A color management module which provides color values in a destination color space by interpolation of a LUT that maps from color values in a source color space to corresponding color values in the destination color space. The LUT includes cells corresponding to color values within a spectrum locus and color values outside the spectrum locus. The LUT is populated differently for cells within the spectrum locus and for those outside the spectrum locus. For cells within the spectrum locus, color values are calculated using a color transform constructed based on device profiles for the source device and for the destination device, and corresponding cells of the LUT are populated based on the calculated values. For cells outside of the spectrum locus, an artificial neural network is trained using the calculated color values, and the corresponding cells are populated based on outputs of the trained neural network.

Constructing a color transform using a neural network for colors outside the spectrum locus

Preservation of rendering intent when a rendering model encapsulated in a transform-based profile is used in a measurement-based CMS. Source device color values are converted to generate perceptually rendered values using a perceptual transform of the transform-based color profile. Perceptually rendered appearance values of a color appearance space are generated by converting the perceptually rendered values using predefined ICC viewing conditions. Using a gamut mapping model (GMM), the generated appearance values are converted to generate destination device color values within a color gamut of a destination device. The GMM uses a PRMG boundary description and a gamut boundary description of the destination device to perform the mapping. A transform is constructed from the source device color values and the corresponding destination device color values. Color values of an image generated by the source device are converted to color values of a destination device using the constructed transform.

Intent preservation when constructing measurement-based color transforms from transform-based profiles

The present invention transforms a source device colorant value to a destination device colorant value, by determining whether all non-black colorant values of the source device colorant value are zero, transforming the source device colorant value to a colorimetric value using a source device model, transforming the colorimetric value to a gamut-mapped colorimetric value using a user-selectable gamut-mapping model, and selecting a destination device colorant value based on the determination. In a case where all of the non-black colorant values of the source device colorant value are zero, the destination device colorant value is selected so that its black colorant value reproduces a lightness of the gamut-mapped colorimetric value, and all of its non-black colorant values are zero. Otherwise, the destination device colorant value is selected so that a combination of its non-black and black colorant values reproduces the gamut-mapped colorimetric value. Accordingly, black content is preserved while accommodating a user-selectable gamut-mapping model.

Color transformation with black preservation

A measurement-based color management system (MBCMS) plugin device model, methods, and a color profiler program that use the plugin device model. The plugin device model provides both an interface used to convert between device dependent and device independent color values, and an interface used to create a color device profile for use with the plugin device model. The color profiler receives color sample information from the plugin device model, using the color profiler interface provided by the plugin device model. The color profiler generates a color target having color samples as specified by the received color sample information. The color values of the color target's color samples are measured. The color device profile is generated, based on the measured color values.

Plug-in for customized device model with interface for device profiler and for color management system

A device model object which numerically constructs colorimetric measurements based on access to a spectrally-based device profile. In situations where a color management module issues a request for spectral measurements, then the device model object provides spectral measurements directly from the spectrally-based device profile. However, in situations where the color management module issues a request for colorimetric measurements, then the device model object numerically constructs colorimetric measurements based on numerical integration of spectral measurements from the spectrally-based device profile against a viewing condition white point. The constructed measurements are provided to the color management module and they are also cached for possible future use. In this way, the device model object is able to support requests for both measurement-based device profiles and spectrally-based device profiles.

Construction of colorimetric measurements from device profile of spectral measurements

Color management which uses a color conversion LUT for transformation from an N-dimensional source device color space (N&#x2267;4) to a destination device color space, in which the color conversion LUT is constructed in a two-step process. In the first step, an intermediate color conversion LUT is constructed that converts colors in a three-dimensional device-independent color space through a gamut mapping step and through an inverse destination device transform so as to obtain colors in the destination device color space. In the second step, the overall color conversion LUT is obtained by applying a source device transform to color combinations in the source device color space so as to obtain color values in the three-dimensional device-independent color space, and thereafter performing three-dimensional color look-ups in the intermediate color conversion table.

Time-efficient generation of color look-up table

A method and apparatus for generating transform-based color profiles by a measurement-based Color Management System (CMS). The measurement-based CMS generates the transform-based profile wherein the measurement-based color system is parameterized by color data and procedures. The CMS may use a reference Profile Connection Space (PCS) loaded from a measurement profile, thus enabling user configuration of the generation process. The reference PCS may also be set to include a gamut that is appropriate for an eventual color-output device. In addition, a Gamut Mapping Model (GMM) used in the generation process is user-selectable as well as a Device Model (DM). The DM may also be supplied as a pluggable module. The CMS also features user-selectable mapping from an International Color Consortium (ICC) intent to a PCS profile and to a DM. The features of the CMS may be used in an application, stand-alone profiling tool or in an operating system utility.

Creation of transform-based profiles by a measurement-based color management system

Managing color data to transform source color image data from a source device into destination color image data for rendering by a destination device, including accessing a source color data file corresponding to the source device, the source color data file containing source device color characteristic data, constructing a source color transform based on the source device color characteristic data contained in the source color data file, and applying the source color transform to the source color image data to transform the source color image data from a source device color space into interim color image data in an interim color space.

Growing community of inventors

Fremont, CA, United States of America

John S Haikin