Abstract: A digital image that includes first and second regions is processed. An intrinsic color of a given pixel located in an area of interest that is adjacent to at least one of the first and second regions is estimated by extrapolating from colors of multiple pixels in one of the first and second regions and multiple pixels in the other of the two regions.

Abstract: Methods and apparatus, including computer program products, for determining parameter values for adjusting an image. A first function of a local attribute is specified based on values of the local attribute in the image. A second function of the local attribute is specified based on an image adjustment depending upon an adjustment parameter. An object function value is calculated for each of two or more values of the adjustment parameter, each object function value including accumulated differences between the first and second function at multiple values of the local attribute. Based on the calculated object function values, a value of the adjustment parameter is determined for adjusting the image.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for masking and extracting a foreground portion from a background portion of a digital video. An input defining an initial border region is received, which includes a border between a foreground portion and a background portion of an initial digital image in a digital video. A border region for another digital image in the digital video is generated. The initial and automatically generated border regions are used for masking the foreground portion from the background portion in the digital video.

Abstract: Methods and systems, including computer program products, for determining a plurality of color clusters based on a plurality of pixels associated with a color image, the clusters being fewer than the pixels. A grayscale value for each one of a plurality of points in a color space is determined. Each grayscale value is based on a weighted average of target differences between each point and the clusters. Each of the pixels is associated with one or more of the points. A grayscale value for each pixel is identified based on the grayscale value of the associated one or more points.

Abstract: A method, system, and computer-readable storage medium are disclosed for combining raster image masks in a digital image. A first raster image mask may be generated that comprises a first set of one or more pixels having a first intermediate value for membership in the first raster image mask. A second raster image mask may be generated that comprises the first set of one or more pixels having a second intermediate value for membership in the second raster image mask. The first raster image mask and the second raster image mask may be combined to generate a third raster image mask, wherein a boundary of the third raster image mask is not greater than a combined boundary of the first raster image mask and the second raster image mask.

Abstract: A digital image that includes first and second regions is processed. An intrinsic color of a given pixel located in an area of interest that is adjacent to at least one of the first and second regions is estimated by extrapolating from colors of multiple pixels in one of the first and second regions and multiple pixels in the other of the two regions.

Abstract: Methods and apparatus implementing a technique for adjusting the color of pixels in an image. The technique includes identifying a target region of pixels in the image that represent an object, the object having a shape and a predefined set of features; and adjusting the color of one or more pixels in the target region by an amount determined based on one or more probability functions and one or more spatial profile functions, each probability function defining a probability value at each of the one or more pixels in the target region, the probability value representing the probability that the pixel corresponds to one or more features of the object, each spatial profile function being defined based on one or more spatial properties of the object or one or more of its features.

Abstract: A digital image that includes first and second regions is processed. An intrinsic color of a given pixel located in an area of interest that is adjacent to at least one of the first and second regions is estimated by extrapolating from colors of multiple pixels in one of the first and second regions and multiple pixels in the other of the two regions.

Abstract: A system to perform modifications, or adjustments, to a digital image includes an interface component to receive selection input to enable selection of the digital data to be modified. A detector then detects a characteristic of the digital data. A configurator automatically configures a function, supported by a data modification component, to modify the digital data. The automatic configuration of the function is performed using the detected characteristic of the digital data to be modified.

Abstract: According to some embodiments, a method, an apparatus and a system perform object detection in an image. In some embodiments, a method includes receiving an image. The method also includes detecting whether an object is in the image. The detecting comprises determining one or more features based on a projection for one or more pixels in the image, wherein the projection is dependent on a statistical probability of the colors of objects and non-objects at the one or more pixels in the image. The detecting also includes determining a likelihood value for the one or more features in the image.

Abstract: Systems and techniques for blending image data such that noise, texture and/or high-frequency data may be better preserved in a resulting blended image. In general, in one implementation, the techniques include blending a first image and a second image to form a blended image including a blended image component formed by a non-affine interpolation of components from the first and second images. The techniques also include blending a first image component corresponding to a first image region with a second image component corresponding to a second image region to produce a first blended component, blending a third image component corresponding to the first image region with a fourth image component corresponding to the second image region using blend coefficients, which sum to a value other than one, to produce a second blended component, and merging the first blended component with the second blended component to produce a blended image region.

Abstract: Methods and apparatus, including computer program products, for determining parameter values for adjusting an image. A first function of a local attribute is specified based on values of the local attribute in the image. A second function of the local attribute is specified based on an image adjustment depending upon an adjustment parameter. An object function value is calculated for each of two or more values of the adjustment parameter, each object function value including accumulated differences, between the first and second function at multiple values of the local attribute. Based on the calculated object function values, a value of the adjustment parameter is determined for adjusting the image.

Abstract: Systems and techniques for blending image data such that noise, texture and/or high-frequency data may be better preserved in a resulting blended image. In general, in one implementation, the techniques include combining a first image region and a second image region to form a blended image region having a neighborhood mean and a neighborhood variance, at each of multiple points in the blended image region, that are linear blends of corresponding neighborhood means and variances from the first and second image regions using a common blending parameter.

Abstract: Methods, systems and apparatus, including computer program products, for processing an image. A first tone value is determined for a location within the image based upon attributes of pixels within a first neighborhood surrounding the location. The first tone value specifies a local weight for a first tone adjustment in the image. A second tone value is determined for the location based upon attributes of pixels within a second neighborhood surrounding the location. The second tone value specifies a local weight for a second tone adjustment in the image. The image is adjusted at the location using the first and second tone adjustments according to the local weights specified by the first and second tone values, respectively.

Abstract: A method, system, and computer-readable storage medium are disclosed for editing a digital image with automatic conversion of region modalities. Input comprising an instruction to perform an operation on a first portion of the digital image may be received. The first portion of the digital image may comprise data defined by a first region modality. The operation may be applicable to data defined by a second region modality. In response to receiving the input, the first portion of the digital image may be automatically converted from the first region modality to the second region modality. The operation may be automatically performed on the converted first portion of the digital image (i.e., as defined by the second region modality).

Abstract: A method, system, and computer-readable storage medium are disclosed for combining raster image masks in a digital image. A first raster image mask may be generated that comprises a first set of one or more pixels having a first intermediate value for membership in the first raster image mask. A second raster image mask may be generated that comprises the first set of one or more pixels having a second intermediate value for membership in the second raster image mask. The first raster image mask and the second raster image mask may be combined to generate a third raster image mask, wherein a boundary of the third raster image mask is not greater than a combined boundary of the first raster image mask and the second raster image mask.

Abstract: An example method includes receiving a first selection location and at least one selection parameter with respect to digital data. A portion of the digital data is selected relative to the first selection location. The selecting of the portion includes assigning an energy value to each pixel within a selection proximity of the selection location. The selection proximity is determined based on the selection parameter and the energy value being a function of distance from the selection location. The selecting of the portion further includes generating a selection value for each pixel within the selection proximity, based on the assigned energy value and on a pixel characteristic difference between the relevant pixel and at least one neighboring pixel. The selection value determines whether the relevant pixel is included in the selected portion of the digital data.

Abstract: Methods, systems, and apparatus, including computer program products, feature receiving an image mask where the image mask identifies a first opacity value of pixels in a raster image. The first opacity value ranges between a value representing foreground and a value representing background. Each pixel in the image has a color. A first boundary pixel is identified in the image. A second opacity value for the first boundary pixel is determined using a first local color model of opacity. The first local color model of opacity is determined based on the colors of the pixels in the image within a local neighborhood of the first boundary pixel.

Abstract: Methods, systems, and apparatus, including computer program products feature identifying a first plurality of pixels in a raster image as foreground pixels and a distinct second plurality of pixels in the raster image as background pixels. Each of the foreground and background pixels have a respective color value. The color values of the foreground pixels and the color values of the background pixels are used to solve for a color model of opacity. The color model of opacity is used to determine an opacity value for a pixel in the raster image.

Abstract: Methods, systems, and apparatus, including computer program products, featuring receiving user input defining a sample of pixels from an image, the image being defined by a raster of pixels. While receiving the user input, the following actions are performed one or more times: pixels are coherently classified in the raster of pixels as being foreground or background based on the sample of pixels; and a rendering of the image is updated on a display to depict classified foreground pixels and background pixels as the sample is being defined.