Abstract: Segmenting scalp and facial hair of a human subject depicted in an image by identifying from metadata associated with the image or semantic information extracted from the image information indicating a possible distribution of the scalp hair or the facial hair, identifying from hair distribution information an expected-hair region within the image wherein the expected-hair region includes at least a portion of a head area of the subject, and identifying a hair region within the expected hair region

Abstract: A method of finding an object in an image that consists of describing an object shape by one or more sets of feature points (220); estimating positions of the feature points (310); finding new locations for each feature point based on an appearance model of an aggregate appearance of the object in local neighborhoods of all features points (320); and constraining the positions of the feature points based on a shape model (330).

Abstract: A method of identifying at least one particular person of interest in a collection of digital images taken over time, includes providing the collection of digital images with each digital image containing one or more persons; storing in a digital database an appearance model having a set of features that are distance measurements associated with facial features of the particular person of interest at an associated time; and providing an individual recognition classifier that uses the appearance model and the associated time to identify the particular person of interest in images from the collection of digital images.

Abstract: A method of characterizing images taken during a event into one or more sub-events is disclosed. The method includes; acquiring a collection of images taken during the event; identifying one or more particular person(s) in the collection and the apparel associated with the identified person; searching the collection to identify if the apparel associated with identified particular person(s) has been changed during the event; identifying one or more sub-events for those images in which the particular person(s) have changed apparel.

Abstract: A method and device for adapting a display image on a hand-held portable wireless display and digital capture device. The device includes a camera for capturing a digital video and/or still image of a user, means for adjusting the captured digital image in response to poor image capture angle of said image capture device so as to create a modified captured digital image; and means for transmitting said modified captured digital image over a wireless communication network to a second hand-held portable wireless display and digital capture device.

Abstract: A method of improving recognition of a particular person in images by constructing a composite model of at least the portion of the head of that particular person, includes acquiring a collection of images taken during a particular event; identifying image(s) having a particular person in the collection; identifying one or more features in the identified image(s) associated with that particular person; searching the collection using the identified features to identify the particular person in other images of the collection; and constructing a composite model of at least a portion of the particular person's head using identified images of the particular person.

Abstract: A method is disclosed for retrieving images relevant to an example image from among a plurality of stored images, each of the stored images being associated with metadata of different types, including retrieving set(s) of images from the stored image(s) for each different type of metadata that are based on similarities of the metadata of each different type with the example image; displaying the retrieved set(s) of image(s) organized according to each different type of metadata; and the user selecting one or more particular set(s) of retrieved image(s).

Abstract: A method of organizing an image collection includes detecting faces in the image collection, extracting features from the detected faces, determining a set of unique faces by analyzing the extracted features, wherein each face in the set of unique faces is believed to be from a different person than the other faces in the set; and displaying the unique faces to a user.

Abstract: A method of finding an object in an image that consists of describing an object shape by one or more sets of feature points (220); estimating positions of the feature points (310); finding new locations for each feature point based on an appearance model of an aggregate appearance of the object in local neighborhoods of all features points (320); and constraining the positions of the feature points based on a shape model (330).

Abstract: A method for detecting a geometrically transformed copy of content in at least a portion of an image, comprises the steps of: (a) providing first and second digital images; (b) searching for objects of interest within each digital image; (c) identifying pairs of corresponding objects of interest in the digital images, wherein each pair of corresponding objects of interest comprises a located object of interest in the first digital image and a corresponding located object of interest in the second digital image that corresponds to the located object of interest in the first image; (d) locating feature points on each located object of interest in each digital image; (e) matching feature points on the located object of interest in the first digital image to the feature points on the corresponding object of interest in the second digital image, thereby generating a set of correspondence points for each image; (f) determining parameters of a geometric transformation that maps the set of correspondence points in th

Abstract: A method of generating captions or semantic labels for an acquired image is based upon similarity between the acquired image and one or more stored images that are maintained in an image database environment, where the stored images have preexisting captions or labels associated with them. The method includes the steps of: a) acquiring an image for evaluation with respect to the stored images; b) automatically extracting metadata from the acquired image without requiring user interaction in the image database environment; c) automatically selecting one or more stored images having metadata similar to the extracted metadata, thereby providing selected stored images with metadata similar to the acquired image; and d) generating captions or labels for the acquired image from the preexisting captions or labels associated with the selected stored images.

Abstract: A method for detecting a geometrically transformed copy of content in at least a portion of an image, comprises the steps of: (a) providing first and second digital images; (b) searching for objects of interest within each digital image; (c) identifying pairs of corresponding objects of interest in the digital images, wherein each pair of corresponding objects of interest comprises a located object of interest in the first digital image and a corresponding located object of interest in the second digital image that corresponds to the located object of interest in the first image; (d) locating feature points on each located object of interest in each digital image; (e) matching feature points on the located object of interest in the first digital image to the feature points on the corresponding object of interest in the second digital image, thereby generating a set of correspondence points for each image; (f) determining parameters of a geometric transformation that maps the set of correspondence points in th

Abstract: A method for placing a human understandable item, such as a caption, text or a figurative element, in a digital image includes the steps of (a) digitally processing the digital image to recognize and identify an optimal location in the digital image for placing the item and (b) modifying the placement of the item in relation to human understandable image content so as to minimally obscure such human understandable image content in the digital image. The recognition and identification of an optimal location further includes the identification of an optimal open space region and then finding an optimal location for the item within the open space region. The placement of the item may be done so as to minimally obscure human understandable image content either in other locations of the optimal open space region, or in regions of the digital image adjoining the optimal open space region.

Abstract: A method for automatically detecting a segment where a mosaic fade, formed by a plurality of tiles, occurs in a digital video, the method comprising the steps of: locating the segment of the digital video containing the plurality of tiles in each frame; detecting whether the tiles, within the located segment, have a predetermined increase or decrease in size from one frame to a next frame; identifying a boundary of the mosaic fade based on the previous step.

Abstract: A method of generating captions or semantic labels for an acquired image is based upon similarity between the acquired image and one or more stored images that are maintained in an image database environment, where the stored images have preexisting captions or labels associated with them. The method includes the steps of: a) acquiring an image for evaluation with respect to the stored images; b) automatically extracting metadata from the acquired image without requiring user interaction in the image database environment; c) automatically selecting one or more stored images having metadata similar to the extracted metadata, thereby providing selected stored images with metadata similar to the acquired image; and d) generating captions or labels for the acquired image from the preexisting captions or labels associated with the selected stored images.

Abstract: An image forming apparatus is disclosed that provide a selective erase feature that enables an operator to block or erase a portion of an original image to be reproduced. The apparatus includes a control unit that generates a set of erase characters based on erase coordinate signals provided by an input unit. The bit map representations of the erase characters are stored in a font memory and are used by the control unit to generate an output data stream that is supplied to an erase unit.