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: Method and apparatus for segmenting a first region and a second region. A method for defining a boundary separating a first region and a second region of a digital image includes determining using a learning machine, based on one or more of the color arrangements, which pixels of the image satisfy criteria for classification as associated with the first region and which pixels of the image satisfy criteria for classification as associated with the second region. The digital image includes one or more color arrangements characteristic of the first region and one or more color arrangements characteristic of the second region. The method includes identifying pixels of the image that are determined not to satisfy the criteria for classification as being associated either with the first region or the second region. The method includes decontaminating the identified pixels to define a boundary between the first and second regions.

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 processing a digital image. The digital image is modified at a location within the image. The modification causes a change of a first local attribute of the image at the location. The change of the first attribute is measured at the location. A second attribute of the image is adjusted at the location based on the measured change of the first local attribute, where the second attribute is different from the first attribute.

Abstract: The invention provides 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 image. In the method, a first input defining a first border region is received, which includes at least a part of the foreground portion and at least a part of the background portion in a first digital image. A second input defining a second border region is received, which includes at least a part of the foreground portion and at least a part of the background portion in a second digital image. An intermediary border region is interpolated for an image intermediary in time to the first and second digital images and the first, second, and intermediary border regions are used for masking the foreground portion from the background portion in the digital video.

Abstract: Methods and apparatus, including computer program products, for detecting an object in an image. The techniques include scanning a sequence of pixels in the image, each pixel having one or more property values associated with properties of the pixel, and generating a dynamic probability value for each of one or more pixels in the sequence. The dynamic probability value for a given pixel represents a probability that the given pixel has neighboring pixels in the sequence that correspond to one or more features of the object. The dynamic probability value is generated by identifying a dynamic probability value associated with a pixel that immediately precedes the given pixel in the sequence; updating the identified dynamic probability value based on the property values of the immediately preceding pixel; and associating the updated probability value with the given pixel.

Abstract: A user identifies an area of a digital canvas. Color gradients are determined based on a corresponding area on a reference. Brush strokes are applied in the area of the digital canvas, the brush strokes having trajectories based on the color gradients.

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 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, implementing and using techniques for locally modifying a stylistic property of at least one path in an electronic document. All or a portion of an electronic document and at least one brush tool is displayed to a user. The electronic document has paths defined by parametric vector curves, and the brush tool is indicated by a cursor and having a region of influence. A user input selecting a brush tool and positioning the selected brush tool on the electronic document is received and a stylistic property of paths that pass within the region of influence of the selected brush tool is changed in response to a continuous user-controlled gesture of the brush tool. The stylistic property is a vector-based appearance property that varies along a path. Methods and apparatus, including computer program products, for editing a digital movie is also described.

Abstract: An apparatus, method, and computer program product for manipulating an edge in an image. The method includes selecting a portion of the image in response to user manipulation of a brush having two or more regions, the portion including an edge; orienting the brush so that a first region lies on a first side of the edge and a second region lies on a second side of the edge; performing a first effect in the portion of the image covered by the first region; and performing a second effect in the portion of the image covered by the second region. The edge can be an edge of a mask. The image can include a mask channel defining the mask, and the method can include performing the first and second effects on the mask channel. The first side of the extraction mask edge is of greater opacity than the second side of the extraction mask edge, and the method includes increasing the opacity of the mask in the first region and decreasing the opacity of the mask in the second region.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for locally modifying a stylistic property of at least one path in an electronic document. All or a portion of an electronic document and at least one brush tool is displayed to a user. The electronic document has paths defined by parametric vector curves, and the brush tool is indicated by a cursor and having a region of influence. A user input selecting a brush tool and positioning the selected brush tool on the electronic document is received and a stylistic property of paths that pass within the region of influence of the selected brush tool is changed in response to a continuous user-controlled gesture of the brush tool. The stylistic property is a vector-based appearance property that varies along a path. Methods and apparatus, including computer program products, for editing a digital movie is also described.

Abstract: The invention provides 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 image. In the method, a first input defining a first border region is received, which includes at least a part of the foreground portion and at least a part of the background portion in a first digital image. A second input defining a second border region is received, which includes at least a part of the foreground portion and at least a part of the background portion in a second digital image. An intermediary border region is interpolated for an image intermediary in time to the first and second digital images and the first, second, and intermediary border regions are used for masking the foreground portion from the background portion in the digital video.

Abstract: Apparatus and methods useful to automate the task of locating a photograph or other image that is embedded within a larger image. An edge curve is found that approximates the perimeter of the embedded image and from the edge curve the rectangle of the embedded image, or a rectangle covering the embedded image, is calculated by processing density profiles of the edge curve taken along two axes. Both location and orientation of an embedded image can be calculated. The location of the four corners of a rectangular embedded image can be calculated, which enables automatic cropping and rotation of the embedded image, even if fewer than all four corners are visible. A rectangle covering the image can be calculated, including a rectangle aligned with the axes of a larger embedding image such as is created when scanning a small photograph on a flatbed scanner.

Abstract: A caries detection system and method for quantifying a probability of lesions existing in tissues are presented. Digital X-ray images are segmented and further processed to generate feature statistics inputs for a neural network. The feature statistics include colinearity measurements of candidate lesions in different tissue segments. The neural network is trained by back propagation with an extensive data set of radiographs and histologic examinations and processes the statistics to determine the probability of lesions existing in the tissues.

Abstract: A data processing system and method for solving pattern classification problems and function-fitting problems includes a neural network in which N-dimensional input vectors are augmented with at least one element to form an N+j-dimensional projected input vector, whose magnitude is then preferably normalized to lie on the surface of a hypersphere. Weight vectors of at least a lowest intermediate layer of network nodes are preferably also constrained to lie on the N+j-dimensional surface.To train the network, the system compares network output values with known goal vectors, and an error function (which depends on all weights and threshold values of the intermediate and output nodes) is then minimized. In order to decrease the network's learning time even further, the weight vectors for the intermediate nodes are initially preferably set equal to known prototypes for the various classes of input vectors.