Abstract: A method for improving scene classification of a sequence of digital images is disclosed herein. Such a method may include providing a sequence of images captured in temporal succession; (b) classifying each of the images individually based on information contained in the image alone to generate a first image classification; and (c) imposing a pre-determined temporal context model on the sequence of images to generate a final image classification for each image in the sequence.

Abstract: A method for scene classification of a digital image includes extracting pre-determined camera metadata tags from the digital image. The method also includes obtaining estimates of image class based on the extracted metadata tags. In addition, the method includes obtaining estimates of image class based on image and producing a final estimate of image class based on a combination of metadata-based estimates and image content-based estimates.

Abstract: An electronic camera includes a sensor for capturing an image, an electronic image display for displaying the captured image, and a user interface for selectively enabling a quick view feature in which the image display is automatically turned on for a set period of time after an image is captured, and then automatically turned off, in order to quickly review the captured image. The camera further includes a processor for performing processing on the captured image and generating a processed image file therefrom, and a memory for storing the processed image file. When an erase command is provided to the processor, the processing of the image file is terminated and the partially completed image file is deleted from the second memory.

Abstract: A digital image processing method for detecting faces in a digital color image comprises the steps of: providing a distributed face detection system having complementary classifiers, wherein the classifiers are complementary in a frequency domain; selecting classifier parameters for the complementary classifiers from a plurality of different parameter generating sources, at least one of which is controllable by human input; reconfiguring the complementary classifiers in the distributed face detection system according to the selected classifier parameters; and detecting faces using the distributed face detection system.

Abstract: A method for selecting an emphasis image from a collection of images based on facial identification comprises the steps of: (a) obtaining a collection of digital images; (b) detecting image patterns indicative of the presence of one or more faces in the digital images, thereby identifying one or more detected faces for each image in which a face is detected; (c) recognizing one or more faces from the detected faces for each of the images in which a face is detected; and (d) scoring an image based on the relative frequency of occurrence of a recognized face within the collection of images, thereby producing an emphasis image characteristic of the most frequently occurring face in the collection of images.

Abstract: A method for generating customized photo album pages for a collection of digital images comprises the steps of: (a) obtaining a plurality of digital images; (b) automatically grouping the images into one or more image sets based on at least one of grouping by events and grouping by people present in the images; (c) automatically profiling the images within each image set according to image content, thereby relating a particular image set to one or more design themes; (d) providing a database of design elements that may be used to generate customized photo album pages; (e) utilizing the design themes generated by the profiling step to automatically suggest one or more design elements from the database of design elements; and (f) automatically generating a customized photo album page layout for each image set by applying one or more of the suggested design elements to the page layout.

Abstract: A method is described for detecting the clipped pixels of a digital color image. The method includes the steps of: (a) producing a uniformity map from the digital color image, where the uniformity map indicates locations within the digital color image that are substantially uniform; (b) providing a threshold value; and (c) using the uniformity map, the threshold value, and the digital color image to produce a map indicating the location of clipped pixels within the digital color image.

Abstract: A method for correlating tracking data associated with an activity occurring in a three-dimensional space with images captured within the space comprises the steps of: (a) locating a camera with respect to the three-dimensional space, wherein the camera at a given location has a determinable orientation and field of view that encompasses at least a portion of the space; (b) capturing a plurality of images with the camera and storing data corresponding to the images, including a capture time for each image; (c) capturing tracking data from identification tags attached to the people and/or objects within the space and storing the tracking data, including a tag capture time for each time that a tag is remotely accessed; (d) correlating each image and the tracking data by interrelating tracking data having a tag capture time in substantial correspondence with the capture time of each image, thereby generating track data corresponding to each image; (e) utilizing the track data to determine positions of the people

Abstract: In order to reduce image degradation due to image capture problems, a method utilizes image data corresponding to a captured image and image capture metadata that refers specifically to information that is associated with capture of the image. A database of correction parameters is provided in order to reduce degradation present in the captured image, whereby each correction parameter is associated with particular image capture metadata. The method involves using the image capture metadata to determine whether the database contains one or more correction parameters associated with that image capture metadata, and then producing correction parameters from the database of correction parameters when the database contains correction parameters associated with the image capture metadata. One or more new correction parameters are produced when the database does not contain correction parameters associated with the image capture metadata. The database then may be updated with the new correction parameters.

Abstract: A system and method for automatically altering an image having pixels is disclosed. An image is segmented into regions and various features of the regions are extracted and used to calculate a confidence factor, or belief value, that a particular region is a main subject of the image. The belief values are assembled into a belief map that is used to define how pixel values are to be altered. Various color and appearance values of the pixel are altered in a predetermined way to emphasize the main subject of the image. The emphasis is applied in a binary fashion or as in a gradient of values. Either the main subject can be emphasized, or the secondary or background subjects can be de-emphasized. The system can be implement on a variety of computer systems.

Abstract: A JPEG2000 compressed image is transcoded to a lower bit-rate or lower resolution, or both, without having to decompress the initial JPEG2000 image and then recompress it to a lower bit-rate and/or resolution. Instead, arithmetic decoding is performed only to the nearest higher bit-rate layer, up to the desired resolution, before performing rate-distortion optimization to produce the transcoded image.

Abstract: Deriving a three-dimensional panorama from a plurality of images of a scene generated by a range imaging camera of the type that produces ambiguities in range information includes the steps of: (a) acquiring a plurality of adjacent images of the scene, wherein there is an overlap region between the adjacent images and at least some of the adjacent images are range images; (b) providing offset data for the range images in order to recover corrected relative scene spatial information and provide a corrected range image, and (c) deriving a three-dimensional panorama from the corrected range image. In order to provide offset data, a relative range difference is detected between adjacent range images as a constant offset between the adjacent images; and the constant offset is applied to at least one of adjacent range images to correct for ambiguities in the relative ranges of the range images.

Abstract: A method for reducing the visibility of sub-Nyquist aliasing artifacts in an image, where the image is produced in a scene-to-output imaging system that is represented by a modulation transfer function, includes the steps of: (a) providing a source image signal as an input image having sub-Nyquist aliasing artifacts, where image content is represented by an image frequency response and a frequency response amplitude; (b) determining a preferred aliasing ratio by utilizing an aliasing equation that depends on image frequency and pixel count of the imaging system; and (c) adjusting the frequency response amplitude of the image signal for image frequencies corresponding to the preferred aliasing ratio so as to correspondingly adjust the modulation transfer function of the scene to output system to maintain the preferred aliasing ratio while reducing the frequency response amplitude, thereby providing an image with reduced visibility artifacts.

Abstract: An electronic still imaging system employs an image sensor comprised of discrete light sensitive picture elements overlaid with a color filter array (CFA) pattern to produce color image data corresponding to the CFA pattern, an A/D converter for producing digital CFA image data from the color image data, and a memory for storing the digital CFA image data from the picture elements. A processor enables the processing of the digital CFA image data to produce finished image data, and the digital CFA image data and the finished image data are both stored together in an image file. This enables image processing from raw camera data to final output data to be completed in a single, integrated process to provide improved image quality when printing.

Abstract: A method for producing a new image of a desired aspect ratio from an original digital image comprises the steps of: (a) determining a cropping window of the desired aspect ratio and a predetermined size; (b) obtaining a main subject belief map including an array of belief values indicating the location and relative importance of subject matter in the original digital image; (c) using the main subject belief map, determining a location of the cropping window in the original digital image that satisfies a predetermined set of criteria; and (d) producing a cropped image of the desired aspect ratio.

Abstract: Artifacts in an image introduced by sub-Nyquist aliasing are reduced below a visually perceptible level by a method comprising the steps of: providing an input image having sub-Nyquist aliasing artifacts; using a visual perception algorithm to identify the location and characteristics of the sub-Nyquist aliasing artifacts, thereby generating artifact coordinates and parameters; and processing the sub-Nyquist aliasing artifacts by reference to the artifact coordinates and parameters to reduce their visibility, thereby providing an artifact corrected image.

Abstract: A method for determining motion vectors from one point in one image frame of a scene to corresponding points in at least two other image frames of the scene, wherein the frames are obtained in a capture process utilizing one or more cameras, wherein the method employs an iterative and hierarchical dense motion estimation that computes the geometry-consistent and appearance-consistent motion fields between three images simultaneously by enforcing both a trilinear constraint and a constant-brightness constraint.

Abstract: A transition in an MPEG sequence including anchor pictures and bidirectionally predicted (B) pictures is encoded by a) coding first and second anchor pictures and b) coding a transition in the sequence by inserting B pictures into the bitstream to create the transition from the first anchor picture to the second anchor picture.

Abstract: In a method for removing artifacts in a digital image that has been decoded from a compressed representation of the image, the pixels of the digital image are segmented into low detail pixels, high detail pixels, and boundary pixels, and then a single non-linear filtering method, such as a sigma filtering method, is applied to each pixel in the digital image. By selecting separate filter parameters for the low detail, high detail, and boundary pixels, the removal of artifacts is improved over prior methods.

Abstract: An electronic camera captures images representing a variety of subjects and categorizes the image according to subject matter. The camera comprises an image sensor for capturing an image, a converter stage for converting the image into digital image data, and a memory for storing a plurality of categories providing classification of the images by subject. A processor in the camera has the capability of assigning the plurality of categories to the images captured by the camera, with each category providing a subject classification for the images. A user selects one or more categories for a plurality of images prior to capture, and an output image signal is then generated including the digital image data corresponding to a captured image and the particular category selected by the user. The categories can be default identifiers stored in the memory, or can be names, text (i.e., account number), and/or graphics overlays (i.e.