摘要:
A method for automatically identifying persons in digital media assets associated with a database of individual user accounts, comprising: providing access to a database of individual user accounts, wherein the database includes connections between the individual user accounts; receiving a digital media asset associated with a first individual user account; analyzing the received digital media asset to detect an unidentified person; designating collections of digital media assets associated with the first individual user account and other connected individual user accounts; training person identifiers for the previously identified persons by analyzing digital media assets containing the previously identified persons; using a processor to identify the detected unidentified person using the trained person identifiers; and associating metadata providing an indication of the one or more identified persons with the received digital media asset.
摘要:
A digital image capture device for use in capturing underwater digital images, comprising: a watertight housing; an image sensor for capturing a digital image; an optical system for imaging a scene onto the image sensor; a means for setting the digital image capture device to operate in an underwater photography mode or a normal photography mode; and a processor. The processor performs the steps of: capturing a digital image of a scene using the image sensor; controlling a color reproduction of the captured digital image responsive to whether the digital image capture device is operating in an underwater photography mode or a normal photography mode; and storing the captured digital image in a processor accessible memory.
摘要:
A digital camera for capturing an image containing the photographer, comprising: an image sensor; an optical system for forming an image of a scene on the image sensor; a processor for processing the output of the image sensor in order to detect the presence of one or more faces in a field of view of the digital camera; a feedback mechanism for providing feedback to the photographer while the photographer is included within the field of view, responsive to detecting at least one face in the field of view, and a means for initiating capture of a digital image of the scene containing the photographer.
摘要:
A method for determining a sharpness predictor for an input digital image includes determining one or more image metrics by analyzing the input digital image; and determining the sharpness predictor from the one or more image metrics.
摘要:
A method for automatically compensating for scanner metamerism errors associated with scanning input images using a digital color image scanner, wherein the input images can be on a variety of different input media having colorants with different spectral characteristics, comprising scanning an input image on a digital color image scanner to produce a scanned image; determining one or more estimated color balance error values in a color balance parameter space by analyzing the scanned image using a color balance analysis algorithm; assigning an input medium from a set of possible input media for the scanned input image in response to the estimated color balance error values; selecting a scanner metamerism correction color transform associated with the assigned input medium; and applying the selected scanner metamerism correction color transform to the scanned image to produce a corrected image compensated for scanner metamerism errors.
摘要:
Method for building color transforms for color imaging devices having concave color gamut regions, including forming a device model that relates device control signals for a color imaging device to corresponding device-independent color values in a device-independent color space; forming a device color gamut representing the set of colors in the device-independent color space that are producible by the color imaging device; and forming a convex color gamut by fitting a convex hull to the device color gamut. The method further includes forming an expanded device model that relates device control signals for the color imaging device to expanded device-independent color values in the device-independent color space, such that the expanded device-independent color values fill the convex color gamut; and building a color transform that relates input device-independent color values to corresponding device control signals for the color imaging device using the expanded device model.
摘要:
In an image enhancement method, a regular enhancement function and an aggressiveness parameter are computed using characteristics of a digital image. A first, relatively slow enhancement algorithm is applied to the digital image using the regular enhancement function, when an aggressiveness parameter is in a predetermined high range. A second, relatively fast enhancement algorithm is applied to the digital image using the regular enhancement function, when an aggressiveness parameter is in a predetermined low range. A modified enhancement function is calculated using characteristics of the digital image and is used with a second, relatively fast enhancement algorithm, when the aggressiveness parameter is in a predetermined medium range.
摘要:
A method for producing an extended color gamut luminance-chrominance digital image from a captured digital image includes determining an estimate of the colors of the captured digital image of an original scene and further processing to produce an extended range output RGB image value including values outside the range that can be displayed on the output image display device, and producing an extended color gamut luminance-chrominance digital image by transforming the extended range output RGB image values to a luminance-chrominance representation.
摘要:
Disclosed is a method for converting an input digital color image having a set of possible input colors to an output digital color image having a set of palette colors, the number of palette colors being less than the number of possible input colors, wherein the set of palette colors is determined based on the distribution of colors in the input digital image boosted by a distribution of important colors contained in the input digital image.
摘要:
A method for correcting for exposure in a digital image, captured by an image capture device, including rendering such captured digital image suitable for display and displaying such captured digital image as a first displayed digital image; and using an adjustable exposure setting to nonlinearly modify the rendered captured digital image to effect an exposure change and displaying the exposure modified rendered captured digital image as a second digital image simultaneous with the first displayed digital image.