Adobe, Inc.

Lubomir D Bourdev

Stephen N Schiller

Jonathan Worthen Brandt

Martin E Newell

Alexandre S Parenteau

Elya Shechtman

Jue Wang

Amy Casillas

Fei Yang

Zhe Lin

Shmuel Avidan

Claire E Schendel

Vuong Le

Gregg Darryl Wilensky

Paul John Asente

Lubomira A Dontcheva

Wilmot Wei-Mau Li

Michael D Schuster

Teri Pettit

Pierre Louveaux

Jeffery Scott Heileson

Kevin T Dale

Jiang Xu

Suporn Pongnumkul

Various embodiments of methods and apparatus for feature point localization are disclosed. A profile model and a shape model may be applied to an object in an image to determine locations of feature points for each object component. Input may be received to move one of the feature points to a fixed location. Other ones of the feature points may be automatically adjusted to different locations based on the moved feature point.

Adjusting a contour by a shape model

Various embodiments of methods and apparatus for feature point localization are disclosed. An object in an input image may be detected. A profile model may be applied to determine feature point locations for each object component of the detected object. Applying the profile model may include globally optimizing the feature points for each object component to find a global energy minimum. A component-based shape model may be applied to update the respective feature point locations for each object component.

Fitting contours to features

Methods and systems, including computer program products, implementing techniques for reviewing and editing word processing documents. The techniques include receiving from a reviewer a plurality of comments about a word processing document. The comments include a first and second comment. The techniques further include associating the comments with the word processing document; and assigning the comments to one or more editors. The first comment is assigned to a first editor, and the second comment is assigned to a second editor.

Reviewing and editing word processing documents

Various embodiments of methods and apparatus for face fitting are disclosed. In one embodiment, sets of two-dimensional local feature points on a face in each image of a set of images are identified. The set of images includes a sequence of frames a video stream. A three-dimensional face model for the face in the each image is generated as a combination of a set of predefined three-dimensional face models. In some embodiments, the generating includes reducing an error between a projection of vertices of the set of predefined three-dimensional face models and the two-dimensional local feature points of the each image, and constraining facial expression of the three-dimensional face model to change smoothly from image to image in the sequence of video frames.

Methods and apparatus for face fitting and editing applications

A plurality of segment transitions in a video data stream is identified. The identifying the plurality of segment transitions includes recognizing an interface feature of a first application interface displayed in the video data stream and generating metadata associating a selected segment transition with a particular point in the video data stream. The interface feature indicates the selected segment transition among the plurality of segment transitions in the video data stream. A navigation system for navigating among the plurality of segment transitions in the video data stream is provided. Responsive to input, navigation to the selected segment transition is performed and the video data stream is displayed from the particular point.

Methods and apparatus for tutorial video enhancement

Three dimensional models corresponding to a target image and a reference image are selected based on a set of feature points defining facial features in the target image and the reference image. The set of feature points defining the facial features in the target image and the reference image are associated with corresponding 3-dimensional models. A 3D motion flow between the 3-dimensional models is computed. The 3D motion flow is projected onto a 2D image plane to create a 2D optical field flow. The target image and the reference image are warped using the 2D optical field flow. A selected feature from the reference image is copied to the target image.

Methods and apparatus for facial feature replacement

Various embodiments of a system and methods for labeling images are described. An image labeling system may receive multiple images. A subset of the images may be labeled to identify image content or elements, such as faces. The system may display some of the labeled image elements in different portions of a display area. Unlabeled image elements may be displayed in the same display area. The display size and position of each unlabeled image element may be dependent on similarities between the unlabeled image element and the displayed, labeled image elements. The system may receive input which indicates that one or more of the displayed, unlabeled image elements should receive the same label as one of the displayed, labeled image elements. Similarities between image elements may be re-analyzed, dependent on the assigned labels, and the display of unlabeled images may be updated.

System and method for labeling a collection of images

Indicating an object is disclosed. Indicating an object includes receiving an indication associated with selecting an image and providing a second indication that a set of one or more objects correspond to the image, wherein the objects have been detected from the image. Indicating an image is disclosed. Indicating an image includes receiving an indication associated with selecting an object, wherein the object has been detected from an image and displaying the image such that a correspondence between the selected object and the image is conveyed.

Indicating a correspondence between an image and an object

A digital image is obtained. A face depicted in the digital image is detected. A set of characteristics is obtained, where the set of characteristics are associated with at least some portion of a face. An attractiveness score is generated based at least in part on the detected face and the set of characteristics.

Generation and usage of attractiveness scores

Various embodiments of a system and methods for using contextual features to improve face recognition in digital images are described. A face recognition system may semi-automatically label faces and/or search for faces in images. Faces may be detected in the images and visual and non-visual features may be determined for each face. The determined features may be facial and/or contextual features. Features may also be determined from labels assigned to the faces. Pair-wise comparisons of the faces, using the determined features, may determine distances between pairs of faces. Some features may be used to determine the relevance of other features. Dependent on the calculated distances, similar faces may be grouped and suggested labels for faces may be provided. The system may be scalable, processing faces in groups to limit the use of system resources to a certain amount, regardless of the size of a digital image collection.

System and method for using contextual features to improve face recognition in digital images

A set of feature points for defining features of a face is detected in a target image and a reference image. The target image is warped to accommodate a selected feature from the reference image using the set of feature points and a set of three-dimensional models. The reference image is warped to a pose of the target image using the set of feature points and the set of three-dimensional models. The selected feature is copied from the reference image to the target image.

Methods and systems, including computer program products, implementing techniques for reviewing and editing word processing documents. The techniques include receiving from a reviewer a first comment about a word processing document receiving from the reviewer a second comment about the word processing document, sending the first comment to one or more editors and independently sending the second comment to one or more editors. The first comment can be sent before the second comment is received.

Face detection is performed on a plurality of images to identify a plurality of faces. A subset of the plurality of faces is activated, including by loading into memory the subset of faces and/or data corresponding to the subset of faces. At least one of the plurality of faces is left un-activated. A distance for each pair of activated faces is calculated, wherein the distance is associated with a measure of a similarity between a first face and a second face. The activated faces are clustered into a plurality of groups based at least in part on the distances. A representative face is selected from each group resulting from the clustering and the representative faces are displayed.

Efficient and scalable face recognition in photo albums

Methods and systems, including computer program products, implementing techniques for reviewing and editing word processing documents. The techniques include receiving from a reviewer one or more comments about a word processing document, receiving from an editor one or more changes to the word processing document, and classifying each change under one of the comments. The techniques can further include selecting a subset of the comments and presenting the word processing document so that the changes that are classified under the selected comments are distinguishable from the changes that are not classified under the selected comments.

Displaying a tag icon is disclosed. Displaying includes receiving a tag for an object that has been detected from an image, designating the object as the tag icon, and displaying the tag icon, wherein the tag icon is a graphical representation of the tag.

Growing community of inventors

San Jose, CA, United States of America

Lubomir D Bourdev