Abstract: A method for extracting an iris from an image is presented. Edges of an iris are detected in an image. Texture from the image is acquired. The edges and texture are combined to generate an inner boundary and an outer boundary of the iris. Also, to improve the accuracy of the iris boundary detection, a method to select between ellipse and circle models is provided. Finally, a dome model is used to determine mask images and remove eyelid occlusions in unwrapped images.

Abstract: A method detects a moving object in a temporal sequence of images. Images are selected from the temporally ordered sequence of images. A set of functions is applied to the selected images to generate a set of combined images. A linear combination of filters is applied to a detection window in the set of combined images to determine motion and appearance features of the detection window. The motion and appearance features are summed to determine a cumulative score, which enables a classification of the detection window as including the moving object.

Abstract: A method for detects a specific object in an image. An orientation of an arbitrary object with respect to an image plane is determined and one of a plurality orientation and object specific classifiers is selected according to the orientation. The arbitrary object is classified as a specific object with the selected orientation and object specific classifier.

Abstract: There is disclosed a digital video recorder that uses a circular file management system to efficiently manage time-shifted viewing a live video broadcast television program. There is provided for use in the digital video recorder, an apparatus for performing time-shifted viewing of an incoming television program being received by the digital video recorder. The apparatus comprises a controller capable of creating a data file having a defined maximum size on a storage disk of the digital video recorder and capable of causing video data associated with the incoming television program to be stored sequentially in the data file from a first location to an Nth location. The controller, in response to a determination that the video data has been stored in the Nth location, causes a next received video data to be stored in the first location.

Abstract: An object detection system for detecting instances of an object in a digital image includes an image integrator and an object detector, which includes a classifier (classification function) and image scanner. The image integrator receives an input image and calculates an integral image representation of the input image. The image scanner scans the image in same sized subwindows. The object detector uses a cascade of homogenous classification functions or classifiers to classify the subwindows as to whether each subwindow is likely to contain an instance of the object. Each classifier evaluates one or more features of the object to determine the presence of such features in a subwindow that would indicate the likelihood of an instance of the object in the subwindow.

Abstract: A method of, and apparatus for, printing information on a hardcopy medium includes the acceptance of data representing a first information and the acceptance of data representing a second information. Second information is printed in regions on the medium where first information data is not printed. Second information data is encoded into a grayscale or color data representation such that necessary or maximum data density is achieved. First information is printed using black (K) ink (or alternatively using a different color gamut than that used for printing the second information) such that first information can be filtered out in a straightforward manner upon scanning of the printed medium by a digital scanning apparatus, and second information can then be recovered and utilized to advantage.

Abstract: A method of printing a plurality of documents includes generating a page file for each page of each document, generating a control file for each page file, and operating a number of printers to generate printed pages based on the page files. The method includes scanning the printed pages to generate a scan file for each page, and identifying the corresponding control file to permit the printed pages to be segregated into properly sequenced separate documents.

Abstract: A method recognizes an object in an image. Gallery images include identified objects, and a probe image includes an unidentified object. The probe image is paired with each gallery image to generate pairs of images. First filters are applied to the probe image of each pair to obtain a first feature value for each application of each filter. Second filters are applied to the each gallery image of each pair to obtain a second feature value for each application of each filter. The feature values are summed for each application of each filter, and for each application, a score is set to an acceptance weight if the sum is greater than a predetermined threshold, and otherwise setting the score to a rejection weight. The scores are summed for all of the application, and the probe image is identified with any gallery image when the score is greater than zero.

Abstract: A method detects an object, such a face, in an image. The image is first partitioned into patches of various sizes using either an integral image or a Gaussian pyramid. Features in each patch are evaluated to determine a cumulative score. The evaluating is repeated while the cumulative score is within a range of an acceptance threshold and a rejection threshold, and otherwise the image is rejected when the accumulated score is less than the rejection threshold and accepted as including the object when the cumulative score is greater than the acceptance threshold.

Abstract: The complexity of image stitching into a panoramic image is simplified with the use of one or more projectable fiducial marks that ease the establishment of a relationship between adjacent scenes of an image without leaving undesirable fiducial vestiges in the final image. A fiducial generator, having a controllable source of illumination, is positionable to project the fiducial into adjacent and overlapping scenes.

Abstract: A method detects a moving object in a temporal sequence of images. Images are selected from the temporally ordered sequence of images. A set of functions is applied to the selected images to generate a set of combined images. A linear combination of filters is applied to a detection window in the set of combined images to determine motion and appearance features of the detection window. The motion and appearance features are summed to determine a cumulative score, which enables a classification of the detection window as including the moving object.

Abstract: A method for detects a specific object in an image. An orientation of an arbitrary object with respect to an image plane is determined and one of a plurality orientation and object specific classifiers is selected according to the orientation. The arbitrary object is classified as a specific object with the selected orientation and object specific classifier.

Abstract: A method detects an object, such a face, in an image. The image is first partitioned into patches of various sizes using either an integral image or a Gaussian pyramid. Features in each patch are evaluated to determine a cumulative score. The evaluating is repeated while the cumulative score is within a range of an acceptance threshold and a rejection threshold, and otherwise the image is rejected when the accumulated score is less than the rejection threshold and accepted as including the object when the cumulative score is greater than the acceptance threshold.

Abstract: A method recognizes an object in an image. Gallery images include identified objects, and a probe image includes an unidentified object. The probe image is paired with each gallery image to generate pairs of images. First filters are applied to the probe image of each pair to obtain a first feature value for each application of each filter. Second filters are applied to the each gallery image of each pair to obtain a second feature value for each application of each filter. The feature values are summed for each application of each filter, and for each application, a score is set to an acceptance weight if the sum is greater than a predetermined threshold, and otherwise setting the score to a rejection weight. The scores are summed for all of the application, and the probe image is identified with any gallery image when the score is greater than zero.

Abstract: The complexity of image stitching into a panoramic image is simplified with the use of one or more projectable fiducial marks that ease the establishment of a relationship between adjacent scenes of an image without leaving undesirable fiducial vestiges in the final image. A fiducial generator, having a controllable source of illumination, is positionable to project the fiducial into adjacent and overlapping scenes.

Abstract: A camera having a digital image transducer and a film transport mechanism operable to advance film across a film focal plane. An imaging system generates an image on the image transducer, and generates an image on the film focal plane. A triggering system may operate to generate the images simultaneously, and the imaging system may include separate lenses having optical properties selected to generate images of essentially the same scene.

Abstract: There is disclosed a digital video recorder that uses a circular file management system to efficiently manage time-shifted viewing a live video broadcast television program. There is provided for use in the digital video recorder, an apparatus for performing time-shifted viewing of an incoming television program being received by the digital video recorder. The apparatus comprises a controller capable of creating a data file having a defined maximum size on a storage disk of the digital video recorder and capable of causing video data associated with the incoming television program to be stored sequentially in the data file from a first location to an Nth location. The controller, in response to a determination that the video data has been stored in the Nth location, causes a next received video data to be stored in the first location.

Abstract: A pictorial tour process acquires material for producing pictorial tours from given amusement venues and then publishes those pictorial tours on an Internet website so the web users can get a “you are there” perspective of the given amusement venue. In particular as applied to the game of golf, a golf website presents pictorial tours of various golf courses by means of shot-by-shot teachings from a player's perspective of the recommended play of a given hole. Such a shot-by-shot teaching tour entertains, teaches as well as allows a web user to judge whether the given course is attractive or suitable to that user. The web users get to see not just the beauty and skill-challenge of the course, but also check such factors as whether the course will adversely challenge to their health if they have conditions of, eg., weak heart or impaired walking mobility, or otherwise cause discomfort because of eg., desert heat or mountain coolness, and so on. Some course allow carts, others don't.

Abstract: A hardcopy medium is produced having an image or graphic printed on one side of the medium and an encoded digital file printed on the other side to provide enhanced communication between users.

Abstract: A CD containing still images, video, audio, or data files unique to a person is created and packaged in a postcard-like medium, greeting card, or the like. The card is printed upon with a personalized image derived from the stored files or selected from an appropriate library of images.