Abstract: A similarity search may be performed on the image of a person, using visual characteristics and information that is known about the person. The search identifies images of other persons that are similar in appearance to the person in the image.

Abstract: A system, medium, and method providing a thumbnail visualizing a plurality of features representing an event to facilitate a search of images. In the system, medium, and method, photographs may be classified into groups based on metadata, e.g., embedded in a photograph file, and a thumbnail may be generated by combining object images extracted from individual representative photographs of the respective groups. The generation of the thumbnail may include extracting metadata from photograph files stored in a photograph folder, classifying the photograph files into groups based on the metadata, selecting representative photographs from the groups using color information included in the metadata, and combining object images extracted from the representative photographs into a thumbnail.

Abstract: An information processing system includes a business-card described information acquiring unit and an association unit. The business-card described information acquiring unit acquires business-card described information that is to be extracted from an image in which a document identification image with which a document is identifiable and an image of a business card are arranged and that is at least part of information described on the business card. The association unit associates the document identified by the document identification image with the business-card described information.

Abstract: One embodiment described herein may take the form of a system or method for dynamically recognizing an Internet address within a video or audio component of a multimedia presentation on a distribution system or network such as, but not limited to, a satellite, cable or Internet network. In general, the embodiment may analyze the audio portion of the presentation or one or more frames of a video component to detect the presence of a web address within the one or more frames. In the embodiment where the audio portion is analyzed, the system may perform a voice recognition or a similar analysis on the audio portion to detect the utterance of a web address. Similarly, one embodiment analyzing the one or more frames of the video component may comprise performing an optical character recognition (OCR) of the frame.

Abstract: A robotic system that includes a mobile robot and a remote input device. The input device may be a joystick that is used to move a camera and a mobile platform of the robot. The system may operate in a mode where the mobile platform moves in a camera reference coordinate system. The camera reference coordinate system is fixed to a viewing image provided by the camera so that movement of the robot corresponds to a direction viewed on a screen. This prevents disorientation during movement of the robot if the camera is panned across a viewing area.

Abstract: A method is described that includes producing an audio spectrogram from a target sample, generating a number of fingerprints based on the audio spectrogram, comparing the series of fingerprints to samples in a data repository using wavelet coefficients, and identifying the target sample based on the matches found in the data repository.

Abstract: An apparatus for discriminating a disguised face includes a face area detector configured to detect a face area in an input image provided from an external source. The apparatus includes a skin color modeling module configured to separate a skin color area from the face area and a disguised face discriminator configured to determine whether signals in the skin color area have a pulse component to discriminate whether a face in the input image is the disguised face.

Abstract: Systems and methods are disclosed for correcting for artificial deformations in anatomical modeling. One method includes obtaining an anatomic model; obtaining information indicating a presence of an artificial deformation of the anatomic model; identifying a portion of the anatomic model associated with the artificial deformation; estimating a non-deformed local area corresponding to the portion of the anatomic model; and modifying the portion of the anatomic model associated with the artificial deformation, based on the estimated non-deformed local area.

Abstract: A system and method for obtaining biometric imagery such as iris imagery from large capture volumes is disclosed wherein a substantially rotationally symmetric mirror such as a cone or sphere is rotated at a constant velocity about a central axis.

Abstract: A system has an aerial image database containing sensor data representing a plurality of aerial images of an area having multiple sub-areas. A processor applies a classifier to the sensor values to identify a label for each sub-area in each aerial image and to thereby generate an initial label sequence for each sub-area. The processor identifies a most likely land cover state for each sub-area based on the initial label sequence, a confusion matrix and a transition matrix. For each sub-area, the processor stores the most likely land cover state sequence for the sub-area.

Abstract: To authenticate a user, fingerprint data for multiple fingers of the user fingers is sensed by a fingerprint sensor (504). Each of these multiple fingers is situated adjacent to at least one other of these multiple fingers while the fingerprint data is being sensed by the fingerprint sensor. Various characteristics of the user's fingers can be analyzed (506) as part of the user authentication, such as the length of the user's fingers relative to one another, the width of the user's fingers relative to one another, the locations of minutiae of one of the user's fingerprints relative to the locations of minutiae of other of the user's fingerprints, and so forth.

Abstract: A transferring system for huge and high quality images on network and a method thereof are disclosed, wherein various individual image data are converted into high quality image data to be converted into layered image data, and classified into a plurality of sub cells, then stored in database as a compressed form. A client system connected to a server requires information, immediately downloads the required information, releases the compression, and then displays on a screen real time. In the present invention, a user can fast see only his wanted part since images of a newspaper and a magazine are converted as they were. Also, various additional information is provided with image, thereby providing multimedia digital publication services on wire or wireless network.

Abstract: An efficient image retrieval method utilizing topological order distance (TOD) algorithm is disclosed. In one aspect, an image recognition method may include steps of receiving one or more input images; extracting one or more key features on the input images; determining an origin and one or more feature points on the key features on the input images; establishing a topological relationship in each dimension between the feature points on the key features; and utilizing the topological relationship in each dimension between the feature points to identify the input images in an image database. Comparing with the conventional image retrieval techniques, the TOD algorithm is advantageous because it is more efficient, scale and rotation invariant, and tolerant to affine and perspective transformation.

Abstract: Proprietary rights logos are detected in a video. The video is divided into a plurality of regions that are analyzed for generic proprietary rights logo features. A confidence mask is generated that comprises a plurality of scaling factors, each scaling factor corresponding to a region of the video and indicating a likelihood that the corresponding region of the video includes a proprietary rights logo. The scaling factors of the confidence mask are applied to the video data to generate an altered video. The altered video is analyzed to determine a confidence measure that the video includes a reference proprietary rights logo.

Abstract: Detection of a target object or a characteristic of that object, e.g. temperature or movement in an image of a scene at a focal plane of the image and with processing of signals representative of the image occurring at that focal plane with a sensor and an integrated circuit processor on an imaging circuit chip used to record the scene. Moreover, processing of the signals representative of the image and the object or characteristic of the object can all be processed in parallel. This arrangement allows for filtering of objects with the ability to distinguish the object generating signals from background clutter. The incorporation of the entire circuit in this integrated circuit chip increases the compactness and efficiency. Moreover, all signal processing will occur at the focal plane eliminates the need for external processing electronics thereby increasing compactness and efficiency while reducing spatial noise.

Abstract: The present invention provides software, methods, and systems for characterizing an actual scan pattern of a scanning beam device. The characterization of the actual scan pattern may be used in an image remapping method and/or a drive signal remapping method to reduce distortions in an image.

Abstract: Provided is a method of receiving multiview camera parameters for a stereoscopic image. The method includes: extracting multiview camera parameter information for a predetermined data section from a received stereoscopic image data stream; extracting matrix information including at least one of translation matrix information and rotation matrix information for the predetermined data section from the multiview camera parameter information; and restoring coordinate systems of multiview cameras by using the extracted matrix information.

Abstract: Methods and apparatus for identifying primary media content in a post-production media content presentation are disclosed. An example computer-implemented method to detect primary media content included in a secondary media content presentation disclosed herein comprises determining a first image corresponding to the secondary media content presentation, the first image comprising a plurality of image subregions, each image subregion representative of an inter-frame variation associated with a corresponding subregion of the secondary media content presentation, selecting a region of the first image comprising a plurality of connected image subregions of the first image together exhibiting a first type of inter-frame variation, and when a shape of the selected region of the first image corresponds to a predefined shape, processing a region of the first captured image corresponding to the selected region of the first synthetic image to identify the primary media content.

Abstract: According to one embodiment, an electronic apparatus comprises (i) an image extraction module configured to extract representative images from a plurality of frames which constitute video content data, and to output time stamp information indicative of time points at which the extracted representative images appear, and (ii) an image list display process module configured to display a list of the extracted representative images on a two-dimensional display area. The area includes image display areas which are divided by columns, a plurality of time zones, and the image list display process module is configured to display, based on the time stamp information corresponding to each of the extracted representative images, the representative images, which belong to the time zone allocated to each column.

Abstract: The present invention relates to an electronic device that comprises a display and a method for such an electronic device. The method includes displaying a map that illustrates a plurality of streets and establishments that are situated on the streets. The method also includes receiving a character input in a character input area of the display and a gesture input outside the character input area of the display. One or more establishments associated with the character input is displayed on the map.