Abstract: According to some example embodiments of the present invention, in a system for managing interactive media, the system includes: a processor; and a memory coupled to the processor, wherein the memory stores instructions that, when executed by the processor, cause the processor to: monitor a broadcast of a live media content production; receive, from a plurality of user devices, preference data indicating preferences for modifying content of the live media content production; aggregate the preference data; and transmit the preference data to a media production device for modifying the live media content product in real time during the broadcast.

Abstract: A hand held imaging device for measuring characteristics of hair and scalp, comprising a housing with a high magnification optic for obtaining magnified images of surface characteristics of hair fibers, said high magnification optic comprising a first lens and a first light source, and a low magnification optic for obtaining magnified images of the scalp and hair, said low magnification optic comprising a second lens and a second light source, wherein the high magnification optic has a fixed focal length and a slot for locating hair fibers in frame such that the hair fibers are in focus and wherein the device further comprises a viewing means, selected from an integral viewing means, an external viewing means and a combination thereof.

Abstract: Embodiments of the invention provide a method for scene understanding based on a sequence of image frames. The method comprises converting each pixel of each image frame to neural spikes, and extracting features from the sequence of image frames by processing neural spikes corresponding to pixels of the sequence of image frames. The method further comprises encoding the extracted features as neural spikes, and classifying the extracted features.

Abstract: Described, is a system for object detection via multi-scale attentional mechanisms. The system receives a multi-band image as input. Anti-aliasing and downsampling processes are performed to reduce the size of the multi-band image. Targeted contrast enhancement is performed on the multi-band image to enhance a target color of interest. A response map for each target color of interest is generated, and each response map is independently processed to generate a saliency map. The saliency map is converted into a set of detections representing potential objects of interest, wherein each detection is associated with parameters, such as position parameters, size parameters, an orientation parameter, and a score parameter. A post-processing step is applied to filter out false alarm detections in the set of detections, resulting in a final set of detections. Finally, the final set of detections and their associated parameters representing objects of interest is output.

Abstract: An in-vehicle running-environment recognition apparatus including an input unit for inputting an image signal from in-vehicle imaging devices for photographing external environment of a vehicle, an image processing unit for detecting a first image area by processing the image signal, the first image area having a factor which prevents recognition of the external environment, an image determination unit for determining a second image area based on at least any one of size of the first image area, position thereof, and set-up positions of the in-vehicle imaging devices having the first image area, an environment recognition processing being performed in the second image area, the first image area being detected by the image processing unit, and an environment recognition unit for recognizing the external environment of the vehicle based on the second image area.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selectively providing images. In one aspect, a method includes receiving image data that specify feature values for a plurality of images. The image data include, for each image, location data that specify a geographic location for the image. A group of images in which each image has location data specifying a geographic location that is within a threshold distance of a reference location are selected. Pairs of matching images are selected from the group of images. A reference image for the geographic location is selected from the pairs of matching images. Data that cause presentation in a map space of a photo collection image that includes a visual representation of the reference image are provided. The photo collection image is presented in the map space and at a map position for the geographic location.

Abstract: A system for generating an image of contoured surface includes a light source that is configured to project an electromagnetic radiation beam onto the contoured surface, wherein the projected beam generates first radiation reflected from a first portion of the contoured surface to form a speckle pattern, and second radiation reflected from a second portion of the contoured surface which is substantially uniform in intensity. The reflected first and second reflected radiation is received by an optical detector, and may be processed. The processing is configured to (1) generate a plurality of images from the first and second reflected radiation, with each image being generated using different coherence length electromagnetic radiation from the light source, and (2) generate a 3-D image of the contoured surface from the plurality of images. Methods for generating a 3-D image of a contoured surface are also disclosed.

Abstract: Methods, systems, and products are disclosed for indexing a digital scene in digital media. The digital media is stored in memory and a uniform resource locator is assigned to a digital scene within the digital media. The uniform resource locator uniquely identifies a resource from which the digital scene may be retrieved, and the uniform resource locator also uniquely identifies the digital scene from other scenes in the digital media. When a query is received for the uniform resource locator, then the digital scene is retrieved from the memory.

Abstract: A system for imaging a textured surface includes a light source that is configured to project an electromagnetic radiation beam onto the textured surface, wherein the projected beam generates first radiation reflected from a first portion of the textured surface to form a speckle pattern, and second radiation reflected from a second portion of the textured surface which is substantially uniform in intensity. The reflected first and second reflected radiation is received by an optical detector, and may be processed to generate an image of the textured surface from the first and second reflected radiation. Methods for textured surface sensing are also disclosed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selectively providing images. In one aspect, a method includes receiving image data that specify feature values for a plurality of images. The image data include, for each image, location data that specify a geographic location for the image. A group of images in which each image has location data specifying a geographic location that is within a threshold distance of a reference location are selected. Pairs of matching images are selected from the group of images. A reference image for the geographic location is selected from the pairs of matching images. Data that cause presentation in a map space of a photo collection image that includes a visual representation of the reference image are provided. The photo collection image is presented in the map space and at a map position for the geographic location.

Abstract: A method for calculating an image quality metric for evaluating the quality of a digital image including the steps of denoising the data of the image, identifying edges in the denoised data, determining an edge profile of the edges, determining a grayscale angle for each identified edge in the edge profile that is associated with the edge, and calculating the image quality metric based on a weighted average of the grayscale angles for all the edges.

Abstract: Certain embodiments of the invention may include systems, methods, and apparatus for sensing flight direction of a spacecraft. According to an example embodiment of the invention, a method is provided for determining flight direction of a spacecraft. The method includes providing at least one imaging detector associated with a spacecraft; imaging at least a portion of a celestial body onto the at least one imaging detector; acquiring, by the at least one imaging detector, sequential images of at least a portion of the celestial body; and determining the spacecraft flight direction relative to the celestial body based at least in part on processing the sequential images, wherein the processing is performed by one or more computer processors.

Abstract: A method of navigating a space vehicle. An image of a planet surface is received. The received image is processed to identify edge pixels and angle data. The edge pixels and angle data are used to identify planetary features by shape, size, and spacing relative to other planetary features. At least some of the planetary features are compared with a predefined planet surface description including sizes and locations of planet landmarks. One or more matches are determined between the planetary feature(s) and the planet surface description. Based on the match(es), a location of the space vehicle relative to the planet is determined.

Abstract: An image processing system provides faster than real-time skin detection and localization. The system uses the highly optimized architecture of a graphics processing unit to quickly and efficiently detect and locate skin in an image. By performing skin detection and localization on the graphics processing unit, the image processing system frees the main system processor to perform other important tasks, including running general purpose applications. The speed with which the image processing system detects and localizes skin also facilitates subsequent processing steps such as face detection and motion tracking.

Abstract: It is difficult to reproduce an input image more faithfully while enlarging a dynamic range and color gamut, in a reproduced image obtained by overlapping output images by a projector and printer. An image processing apparatus (102) transforms an input signal (101) into an RGB signal for a projector (103) and a CMY signal for a printer (104). In this case, the image processing apparatus (102) uses a transformation LUT, which is generated based on the spectral distribution characteristics of the projector (103) and the spectral reflectivity characteristics of the printer (104). By overlapping images formed by the projector (103) and printer (104) based on the transformed image signals, an input image can be reproduced more faithfully while enlarging the dynamic range and color gamut.

Abstract: A system and method for triggering a radio frequency identification, RFID, scan using image recognition includes; storing (300) image attributes of inventoried RFID-tagged items in a database along with information associated with the RFID-tagged items, capturing (302) an image of an item from an imaging device, determining (304) if there is a match between attributes of the captured image compared with the stored image attributes in the database indicating that the item is RFID-tagged, and upon a match determination (304) attempting to read (306) an RFID tag of the item.

Abstract: A mirror system includes an image sensor coupled to a mirror, and gathers consumer shopping preferences for merchandise items. During operation, the system gathers one or more sequential images, from the image sensor, of a consumer wearing a first wearable merchandise item in front of the image sensor. Next, the system identifies in the one or more sequential images a first merchandise item being worn by the consumer. Then, the system determines a demographic group associated with the consumer, and detects behavior patterns for the consumer, wherein the behavior pattern indicates an interest level of the consumer for the identified merchandise item. The system then determines a mapping between the identified consumer demographic group and an interest level for the identified merchandise item, and produces a model which encodes the mapping.

Abstract: A method for customizing a presentation of a set of digital images provided by a user is disclosed, comprising the steps of selecting an initial presentation format criteria for the set of digital images by the user; analyzing the digital images for additional information; providing to the user a first portable electronic storage medium having the set of digital images stored thereon, the images capable of being presented to the user on a display device in accordance with a first presentation format based upon the initial selected presentation format criteria and the analysis of the additional information; and providing a software program to the user enabling the user to select additional presentation format criteria.

Abstract: An apparatus for providing sound effects according to an input image and a method thereof capable of conveying details of the input image lively and effectively by recognizing the shape of the image and outputting a sound suitable for the recognized shape of the image. The apparatus for providing the sound effects according to the image includes an image input unit for receiving an input of an image, a sound effect providing unit for recognizing the image inputted through the image input unit and providing the sound effects according to the input image, and an image output unit for outputting the image inputted through the image input unit and the sound provided from the sound effect providing unit.

Abstract: The invention is generally related to the systems and methods through which household appliances can provide intuitive and enhanced interactivity through visual inputs. In particular, the disclosure presents methods relating to control of a household appliance, such as a microwave or a refrigerator, via recognition of visual indicia, such as graphics, text, and the like, using a visual sensor such as a camera.

Abstract: A façade rendering system is described. In various embodiments, the façade rendering system identifies horizontal waveforms and vertical waveforms from an image of a structure, combines the identified horizontal and vertical waveforms to generate façade waveforms that model a façade of the structure, and renders the façade waveforms as a façade for the structure. The façade rendering system can include or employ information about the structure from which to create waveform information, waveform information to create a façade waveform for modeling the structure, and a component that renders the structure based on the waveform information.

Abstract: Multi-scale processing may be used to reduce the memory and computational requirements of optimization algorithms for image labeling, for example, for object segmentation, 3D reconstruction, stereo correspondence, optical flow and other applications. For example, in order to label a large image (or 3D volume) a multi-scale process first solves the problem at a low resolution, obtaining a coarse labeling of an original high resolution problem. This labeling is refined by solving another optimization on a subset of the image elements. In examples, an energy function for a coarse level version of an input image is formed directly from an energy function of the input image. In examples, the subset of image elements may be selected using a measure of confidence in the labeling.

Abstract: An in-vehicle running-environment recognition apparatus including an input unit for inputting an image signal from in-vehicle imaging devices for photographing external environment of a vehicle, an image processing unit for detecting a first image area by processing the image signal, the first image area having a factor which prevents recognition of the external environment, an image determination unit for determining a second image area based on at least any one of size of the first image area, position thereof, and set-up positions of the in-vehicle imaging devices having the first image area, an environment recognition processing being performed in the second image area, the first image area being detected by the image processing unit, and an environment recognition unit for recognizing the external environment of the vehicle based on the second image area.

Abstract: Embodiments of the present invention enable fault detection in a printed dot-pattern image. Certain applications of the present invention are its use in various embodiments of a system for inspection of a printed circuit board (“PCB”) substrate. In embodiments, a generated distortion map is based on a comparison of a reconstructed dot-pattern image, a simulated reference bitmap, and an error map representing differences between the reconstructed dot-pattern image and the reference bitmap. In embodiments, the pixels of the distortion map are color coded to identify the locations and types of aberrations that were discovered as a result of the comparison.

Abstract: A refined autofocus method provides optimized lighting between iterative autofocus operations, to reliably provide the best possible autofocus Z-height precision. The method includes a quantitative initial focus Z-height determination based on initial focus curve data from initial autofocus images acquired using initial light control parameters. Then, the camera is set at that initial focus Z-height such that well focused images are provided. Refined (optimized) light control parameters are then determined based on at least one respective image acquired using respective light control parameters at that Z-height, such that an image acquired using the refined light control parameters provides a near-optimum value for a contrast-related metric (e.g., a focus metric) at that Z-height. Then, refined autofocus images are acquired using the refined light control parameters and a refined precise Z-height is quantitatively determined base on the resulting focus curve.

Abstract: Described are a method and an apparatus for color-corrected underwater imaging. A range to an underwater object to be imaged is determined and control values are selected according to the range. Control values are predetermined for a number of ranges according to an optimization of a color quality factor for each range based on the spectra of the optical sources used for illumination and the wavelength-dependent optical transmission of the water for the range. The optical power of each optical source is controlled according to a respective one of the selected control values. Advantageously, an acquired image requires no color correction as the adaptive illumination compensates for the wavelength-dependent losses in the light propagation path from the optical sources to the object and from the object to the imaging device.

Abstract: A system and method for supporting augmented reality in an ocean scene is provided. According to the system and method, camera rotation information is extracted from horizontal line information of a sea extracted from an original image including a focal length and at least two first natural feature point tracking data existing on a sea plane and a plane parallel to the sea plane, using long-distance background features; camera movement is sequentially calculated from the camera rotation information and at least two natural feature point tracking data existing on the sea plane of the original image; and a computer graphics object is placed on a ground plane by importing camera position data, and a rendering is performed as moving the camera.

Abstract: An image processing system provides faster than real-time skin detection and localization. The system uses the highly optimized architecture of a graphics processing unit to quickly and efficiently detect and locate skin in an image. By performing skin detection and localization on the graphics processing unit, the image processing system frees the main system processor to perform other important tasks, including running general purpose applications. The speed with which the image processing system detects and localizes skin also facilitates subsequent processing steps such as face detection and motion tracking.

Abstract: A method for providing access to information related to a digital image record on a data processing device. The digital image record is displayed with a tab emanating from an edge of the digital image record. The tab includes an access point that allows a user to access a category of information related to content contained within the digital image record.

Abstract: Infrared face image data is obtained (11) on a person (P) who is a subject of discrimination using an image signal (VDA) from a television camera (2A); the cheek region and jaw region temperatures of the subject (P) are sampled based on the infrared face image data; the averages of the temperatures are calculated (15, 16); cheek data/jaw data is calculated (17); and a cheek emphasized variance value is calculated (18). The cheek data/jaw data and cheek emphasized variance value are mapped on an XY plane (19), and gender discrimination of the person (P) is conducted based on the result. In addition, gender discrimination is conducted using the cheek data/jaw data (21) and gender discrimination is conducted using the cheek emphasized variance value (22), and gender identification is conducted in accordance with agreement between two or more of the multiple gender discrimination results (24).

Abstract: A spin-injection magnetoresistance effect element that can avoid use of a large writing current and allows use of a large reading current. The spin-injection magnetoresistance effect element includes layers that may exhibit a tunnel magnetoresistance effect and layers that may exhibit a giant magnetoresistance effect.

Abstract: The present invention provides a method and system for optimizing the time required for scanning a document with any conventional scanner. More specifically, the present invention will utilize calibration information from the initial power-up calibration or any other calibration, and the information from any previous scans to expedite or eliminate the need for future calibration requests. This process will save time for the user to obtain an optimal scan and increase the operable life span of the scanner by eliminating many repetitive scan cycles.

Abstract: The invention provides a face-based automatic demographics classification system that is robust to pose changes of the target faces and to accidental scene variables, by using a pose-independent facial image representation which comprises multiple pose-dependent facial appearance models. Given a sequence of people's faces in a scene, the two-dimensional variations are estimated and corrected using a novel machine learning based method. We estimate the three-dimensional pose of the people, using a machine learning based approach. The face tracking module keeps the identity of the person using geometric and appearance cues, where multiple appearance models are built based on the poses of the faces. Each separately built pose-dependent facial appearance model is fed to the demographics classifier, which is trained using only the faces having the corresponding pose.

Abstract: Provided is a method for processing dump data packets in a low earth orbital (LEO) satellite. The method includes the steps of: a) extracting table identification (ID) information from a header of high-resolution camera (HRC) dump data transmitted from the LEO satellite; b) searching a HRC dump table from a HRC dump table list based on the extracted table ID information; c) extracting sequence information from the transmitted HRC dump data; d) completing and storing an complete table based on the sequence information searched in the HRC dump table and the extracted sequence information; and e) reading and displaying the HRC dump table upon request of an operator.

Abstract: A computer-implemented method of font identification includes receiving a first document, the first document including the first text set in a proportional font. Test text, corresponding to the first text of the first document, is received. The test text is set in a test font. A first fingerprint is generated, based on relative line widths of the first text of the first document. A second fingerprint is generated based on relative line widths of the test text, as set in the test font. The test font is then accepted as being consistent with a font of the first text, based on a predetermined strength of relationship between the first and second fingerprints.

Abstract: An apparatus providing a search service, a search service method, and a program providing the search service method are provided. The apparatus providing the search service includes a display unit which displays a map image; and a control unit which, if a certain spot is selected on the map image, searches for a photographic image having a photographic range in which the selected spot is included and controls the display unit to display the photographic image.

Abstract: A fault detection system designed to evaluate the structural integrity of a material employs an array of sensors disposed over the material being evaluated. The sensors detect vibrations in the material and the sensor signals are fed to a data processor. The processor employs a method to analyze the linear and nonlinear characteristics of the sensor signals and then determines whether to proceed with a linear signal processing analysis or a nonlinear signal processing analysis of the sensor signals. Once the analysis is completed, the results are compared to baseline results to determine what if any divergence exists between the results and the baseline results. A significant divergence indicates a potential material failure. The fault detection system will indicate such a potential failure through a visual alarm on a graphical user interface.

Abstract: Increased recognizance of caricatured images is provided for the level of caricaturing to be applied to an image to be set in dependence on the intended size of the caricature image. Preferably, the caricature level is set as a generally inverse function of the image size, such that the smaller the image the greater the level of the caricaturing that is applied. In such a case increased recognizance of subjects represented in smaller images may result.

Abstract: A method and apparatus for determining camera pose characterized by six degrees of freedom (e.g., for use in computer vision systems) is disclosed. In one embodiment an image captured by the camera is received, and at least two constraints on the potential pose are enforced in accordance with known relations of the image to the camera, such that the potential pose is constrained to two remaining degrees of freedom. At least one potential pose is then determined in accordance with the remaining two degrees of freedom.

Abstract: A image processing system reduces the memory and computational requirements needed to process graphics operations. The system combines otherwise individual operations to apply filters to images. The resulting filter operation that emerges from the combination of individual operations spares the processor time required to apply the filter, and the resulting filter operation eliminates the need to create any intermediary image. The system can be implemented in many contexts, such as in situations where the individual operations are fragment programs of a programmable Graphics Processing Unit (GPU).

Abstract: A system and method for providing multiple levels of verification of content displayed on an electronic display. A verification code signal representative of a verification code may be displayed with the visual content. The verification code may be sensed and determined to verify that the visual content was displayed. A timestamp may be generated to indicate time of day that the visual content is displayed. In one embodiment, the verification code signal may be displayed in one or more colors and sensed. Verification that the visual content was displayed with correct colors may be made based on the sensed visual verification code signal. Verification that the visual content was displayed at a certain time and with the correct colors may be provided to an owner of the visual content, such as an advertiser.

Abstract: A method for remotely directing a fishing tournament makes use of a data network over which participants transmit submissions indicating sizes of fish caught. The submissions may include digital images of fish, and size may be determined from a scale established using a reference object depicted in the image. The data network may also be used to register participants and provide them with tournament results. Participants may register for a fishing period, or multiple fishing periods of the tournament, and may be issued a code to be displayed in images of fish. Validation of entries may include an examination of metadata in submitted digital images.

Abstract: A method for customizing a presentation of a set of digital images provided by a user is disclosed, comprising the steps of selecting an initial presentation format criteria for the set of digital images by the user; analyzing the digital images for additional information; providing to the user a first portable electronic storage medium having the set of digital images stored thereon, the images capable of being presented to the user on a display device in accordance with a first presentation format based upon the initial selected presentation format criteria and the analysis of the additional information; and providing a software program to the user enabling the user to select additional presentation format criteria.

Abstract: A method and apparatus for reducing the magnitude and edge clarity of the luminosity of an undesired image of a external object reflected from a portion of a surface of a visual display into the eye of a user includes placing a cover in the path of the reflected image. The cover has a surface portion which is not parallel to the portion of the surface of the display. As result the reflections from the cover and from the display surface portions provide multiple images of the external object to the user each having a luminosity magnitude which is less than the magnitude of the luminosity of the undesired image that would occur if the cover was parallel to the display surface portion thereby resulting in super-imposed images.

Abstract: A processor executes a document rendering application for an open document. When the open document is unedited and a predetermined portion of the processor is available, the document is rendered to an output buffer. The rendering is suspended when a predetermined interrupt is received and is resumed after the predetermined interrupt has been serviced. When the document has been edited, any rendered portion of the document is removed from the output buffer and the document is reset as being unedited.

Abstract: A pattern matching engine supports high speed (up to at least 2.4. Gbits per second line rate speeds) parallel pattern matching operations in an unanchored fashion. The engine is preferably implemented as a hardware device. A shift register serially receives a string of data stream bytes which are partitioned into a plurality of multi-byte overlapping adjacent stream chunks. Library patterns of bytes to be searched for are similarly partitioned into multi-byte overlapping adjacent table chunks for storage in a look-up table. The plurality of multi-byte overlapping adjacent stream chunks are applied by the register in parallel to the look-up table, with a result being returned which is indicative of whether each stream chunk matches one of the look-up table stored table chunks. The results of the parallel look-up operation are then logically combined to make a match determination.

Abstract: A system and method for generating information based on decoded embedded data from a substrate is implemented by reading embedded data from a substrate, decoding the embedded data to determine registration of the substrate relative to a reference in an apparatus, and developing and presenting human-sensible information based on the registration information. In one embodiment, the human-sensible information is visual information registered with the substrate. The human-sensible information may also comprise, for example, tactile, audible, or other sensory information.

Abstract: The invention relates to an apparatus for examination of images having an image storage device (10) which is designed to store image data for images to be evaluated, a display device (22) which is designed to display the image data, an input device (23) for a subject, which is designed to interrogate visualization data, a control device (21) which connects the abovementioned devices to one another, a data matching device (30) for matching image data and visualization data, as well as an evaluation device (41) for calculation of a visualization profile, with the visualization data comprising position data which is transmitted from the input device (23).

Abstract: A method and apparatus for reducing the magnitude and edge clarity of the luminosity of an undesired image of a external object reflected from a portion of a surface of a visual display into the eye of a user includes placing a cover in the path of the reflected image. The cover has a surface portion which is not parallel to the portion of the surface of the display. As result the reflections from the cover and from the display surface portions provide multiple images of the external object to the user each having a luminosity magnitude which is less than the magnitude of the luminosity of the undesired image that would occur if the cover was parallel to the display surface portion thereby resulting in super-imposed images.

Abstract: Systems and methods are provided for automatically determining the font of text in a captured document image. Sequences of turns (left, right, straight) around the boundaries of connected components of black pixels in the captured document image are determined. The probabilities of the sequences of turns have come from a particular font within a library of known fonts can be determined using training set statistics. Using these probabilities, the most probable source font is selected.