Abstract: Described is system for object recognition from moving platforms. The system receives a video captured from a moving platform as input. The video is processed with a static object detection module to detect static objects in the video, resulting in a set of static object detections. The video is also processed with a moving object detection module to detect moving objects in the video, resulting in a set of moving object detections. The set of static object detections and the set of moving object detections are fused, resulting in a set of detected objects. The set of detected objects are classified with an object classification module, resulting in a set of recognized objects that are then output.

Abstract: System and techniques for an image filter based on row identification are described herein. A crop row center represented in an image of a crop row can be calculated. A filter corresponding to a set of expected crop characteristics of the crop row can be obtained. Elements in the image can then be categorized based on applying the filter to the image when the filter anchored on the crop row.

Abstract: A method for capturing hyperspectral images using a regular color camera. In the method, the camera takes multiple images of a scene, with the camera oriented differently for each image. For a camera carried by an aircraft or spacecraft, this allows hyperspectral imaging without the cost or weight of a hyperspectral camera.

Abstract: A method for visual recognition of an object in an electronic image includes extracting unique points of an object to be learned and/or a target object. The unique points are obtained by cross-correlating the image with a structure. Generally, the structure and/or the size of the structure may vary to detect extremum information associated with the learned object and/or target object. An icon corresponding to each of the unique points is extracted. The size of the icon corresponds to the scale of the unique point. After extraction of the various icons, an object becomes a collection of icons. Each of these icons is un-rotated and normalized or resized to a constant size so it can be compared with other icons. One of the unique properties of these icons is their stability over scale and angle. Thus, this invention allows the recognition of an image(s) or object(s) from large number of trained images or objects very quickly.

Abstract: SIFT features are selected from an input image. A SIFT procedure is applied to the input image to obtain candidate keypoints. For each candidate keypoint, there is calculation of a first Laplacian value (Lu) for pixels in an upper Scale Space and a second Laplacian value (Ll) for pixels in a lower Scale Space, based on the position of the candidate keypoint. A candidate keypoint is discarded if a Laplacian value Lc of the keypoint position is less than or equal to either of Lu or Ll. In the case that the candidate keypoint is not discarded, the candidate keypoint's Laplacian strength (Ls) is calculated, based on a relative change in Laplacian value from Lc to Lu and from Lc to Ll. One or more candidate keypoints are selected as SIFT features based on the corresponding Laplacian strength.

Abstract: A method for automated detection of illegal substances smuggled inside internal cavities of a passenger, e.g., as capsules. The method provides for an automated detection of narcotics hidden in a passenger's stomach area using pictures produced by an X-ray scanner. According to an exemplary embodiment, throughput of the scanner is increased by an automated detection algorithm, which takes less time than visual analysis by an operator. The operator is only involved in cases when narcotics are detected. The automated detection method has a consistent precision, because the effects of tiredness of the operator are eliminated. Efficiency and costs of the process are improved, since fewer qualified operators can service several scanners.

Abstract: A computer-implemented method and apparatus are described for deblurring an image. The method may include accessing the image that has at least one blurred region and, automatically, without user input, determining a first value for a first size for a blur kernel for the at least one blurred region. Thereafter, automatically, without user input, a second value for a second size for the blur kernel is determined for the at least one blurred region. A suggested size for the blur kernel is then determined based on the first value and the second value.

Abstract: An image matching technique locates feature points in a template image such as a logo and then does the same in a test image. Classifiers are trained for multiple template images and the classifiers are used to evaluate a match between a template image and a test image.

Abstract: An image retrieval apparatus comprises: a memory unit that stores image feature values; an acquisition unit that acquires a first image feature value for a retrieval target image; a retrieval unit that retrieves an image feature value that is similar to the first image feature value from the image feature values, based on the first image feature value; a determining unit that determines a linear conversion parameter to be used for linear conversion out of a group of linear conversion parameters based on image feature values for images of the same photographic subject obtained under conditions, based on the first image feature value and image feature values for said photographic subject; a conversion unit that converts the first image feature value by the linear conversion parameter, and converts the image feature value using said linear conversion parameter; and an output unit that outputs the conversion results.

Abstract: A method and a system for evaluating the class of a test datum in a data space of dimension D where D?3, each datum belonging to at least one class grouping together several data, comprising: projecting a suite of reference data of the data space into a space of dimension Q where Q<D, the class of each reference datum being known, calculating a measurement of similarity of the test datum to each of the reference data, partitioning the projection space into a plurality of disjoint regions each containing the projection of one and only one reference datum, and finally evaluating the class of the test datum, this class being evaluated as being the same class as one of the reference data contained in one of the regions containing the reference data closest to the test datum in the sense of the similarity measurement.

Abstract: The present invention provides a face recognition method on a computing device, comprising: storing a plurality of training face images, each training face image corresponding to a face class; obtaining one or more face test samples; applying a representation model to represent the face test sample as a combination of the training face images and error terms, wherein a coefficient vector is corresponded to the training face images; estimating the coefficient vector and the error terms by solving a constrained optimization problem; computing a residual error for each face class, the residual error for a face class being an error between the face test sample and the face test sample's representation model represented by the training samples in the face class; classifying the face test sample by selecting the face class that yields the minimal residual error; and presenting the face class of the face test sample.

Abstract: An electronic card connector (100) includes an insulative housing (1), a plurality of terminals (2) retained in the insulative housing, a tray (5) movable between an original position and a final position and having a notch (51) and a stepping part (52), a shielding shell (4) having an elastic part (43), and an ejecting mechanism (6). The elastic part has a holding part (432) for latching with the stepping part at a final position. The ejecting mechanism has a lever (62) including a buckling portion (624) and a spring (61) cooperated with the lever. The lever is movable forwardly against with the spring to disengage the holding part from the stepping part and to plunge the buckling portion into the notch, thereby permitting the tray together with the lever to return to the original position under a restoring force provided by the spring.

Abstract: An image processing device includes a controller. The controller is configured to perform: acquiring image data having a plurality of objects; calculating an amount of characteristic of each of the objects, the amount of characteristic indicating a degree of change in pixel values; setting a process order based on the amount of the characteristic of each of the objects; setting a target value, the target value being a reference value to reduce a data size of the image data; reducing an object data size of at least one of the plurality of objects based on the process order in such a way that the data size of the image data becomes smaller than or equal to the target value, thereby generating a reduced object; and generating reduced image data having a data size smaller than the data size of the image data by using the reduced object.

Abstract: A document processing apparatus includes: a reception unit that receives a designation of cover pages of an electronic document having the cover pages and document body pages; and an instruction unit that gives an instruction to respectively print the cover pages and the document body pages on the basis of the designation received by the reception unit.

Abstract: An image processing apparatus includes an input unit that inputs printing information containing image data and a conversion unit that, when the pixel value of the top pixel from among successive N pixels (N is an integer equal to or larger than 2) of the image data is a specific value, sets a pixel having a pixel value that is not the specific value as a new top pixel from among pixels from a pixel adjacent to the to pixel to the N-th pixel, refers to data of the new top pixel to the N-th pixel, and performs a conversion into pixel values that are calculated with coefficient values according to the magnitude of the pixel values.

Abstract: An image forming apparatus includes a detector for detecting one of position and density information of a detection image based on a signal corresponding to a difference between a value of a detection signal corresponding to a first position of one of the detection image on an image carrier and a surface of the image carrier and an average value of a value of the detection signal corresponding to a second position on a downstream side with respect to the first position in a moving direction of the detection image and a value of the detection signal corresponding to a third position on an upstream side with respect to the first position in the moving direction during a time when the detection image formed on the image carrier passes through an irradiation region of an irradiation device.

Abstract: A manufacture for encoding information from which a position of an optical pen tip can be derived, said manufacture includes a display medium having a supporting base and upon which is encoded a two dimensional code pattern that is continuously arranged on an entire surface of the supporting base; wherein the pattern is formed by a sequence of narrow parallel bands, including at least two parallel lines, of which one line is a base line the remaining lines are secondary lines; wherein each narrow parallel band includes a sequence of dots, the dots being arranged in a pre-determined position in order to represent a number at a selected number base.

Abstract: In an approach for interpreting a matrix code with increased information density, a processor identifies a first portion of an extended matrix code and a second portion of the extended matrix code, where each portion of the extended matrix code has a different combination of at least one positioning marker and at least one location marker. A processor locates at least one location marker of the first portion of the extended matrix code and at least one location marker of the second portion of the extended matrix code. A processor concatenates the first portion of the extended matrix code and the second portion of the extended matrix code based on at least one location marker of the first portion of the extended matrix code and at least one location marker of the second portion of the extended matrix code. A processor generates the extended matrix code.

Abstract: A structure, a decoding method and a decoding device of a barcode are disclosed. One data code of the barcode of the present invention has 8-bit information quantity. Therefore, based on the same print length of the Code 128 barcode, the information density of the barcode of the present invention can be increased and the encoding and the following operation of the barcode can be simplified. In addition, the barcode of the present invention can be configured on a plane of an object, around a plane of a disc, or around a circular side of a cylinder, enabling the decoding device of the present invention to identify the data code, indicating 8-bit information of the barcode, scanned through a corresponding linear motion, disc rotation, or cylinder rotation.

Abstract: Techniques for checking into a retail establishment are provided. A retailer provides a substrate having a magnetic-field encoded tag. A consumer waves the consumer's device over the tag to electronically capture the magnetic-field encoded tag. The consumer's device is used to communicate the tag to a retailer to validate that the consumer is physically present and now checked into the retail establishment of the retailer.

Abstract: There is system for power management for radio frequency identification (RFID) tag asset tracking systems where the tag has a transceiver, configured to control RFID communication of the RFID tag, an accelerometer, configured to determine and communicate whether the tag is in motion and a microcontroller unit (MCU), to control operation of the RFID tag and operably connected to, and in communication with, the accelerometer and the transceiver, wherein the MCU awakens, based on a trigger and receives, from the accelerometer, whether the accelerometer is moving, and if it is moving then provide power to other parts of the tag, otherwise transition to a sleep mode to conserve power.

Abstract: Disclosed is a wireless transceiver for a vehicle and a method of manufacturing the same. In a wireless transceiver manufacturing process according to the present disclosure and a method of manufacturing the same, both of the top and bottom sides of a circuit board, on which components are mounted, are encapsulated using a resin material in a state where the circuit board floats in a cavity. A pin configured to support the circuit board is installed and a decoration flat member is fixed to the surface of the circuit board opposite to the side where the pin is installed using double-sided tape. As a result, it is possible to prevent the resin case from being warped by heat generated from the circuit board. In addition, it is possible to omit an existing post-processing process for preventing the damage to the circuit board which may be caused when one side of the circuit board is exposed to the outside as it is. Thus, steps of the manufacturing process and the manufacturing costs can be reduced.

Abstract: A wearable device includes a wearable device structure. The wearable device has a first end and a second end each with a plurality of magnets. The first and second ends are coupled by overlapping of at least a portion of the first end magnets to at least a portion of the second end magnets. The wearable device structure includes an undercut structure for receiving at least a portion of the magnets. ID circuitry is provided at a surface or an interior of the wearable device.

Abstract: An RFID transponder device has antenna terminals for coupling an antenna system to the device. A transmitter and a receiver are coupled to the antenna terminals. The device has at least one damping resistance connected to at least one of the antenna terminals. The at least one damping resistance is connected, depending on a voltage swing at the antenna terminals during a transmission burst period, either together with a serially connected switch in parallel to the antenna terminals that are coupled to the receiver, or together with a parallel connected switch between one of the antenna terminals and a terminal of the transmitter. A damping control is configured to activate the at least one damping resistance during a damping period after the transmission burst period by controlling the respective switch.

Abstract: An antenna device includes a planar conductor, a coiled antenna element, and a feed coil. The feed coil includes a coil conductor wound around a magnetic core. The planar conductor includes a ground conductor provided with a printed wiring substrate. In a portion of a circumferential portion of the planar conductor, a coupling portion is provided and defined by an aperture and a slit. In a planar view of the antenna element, at least a portion of the coil aperture of the feed coil and a portion of the aperture overlap with each other. In addition, at least a portion of the coil aperture of the feed coil and a portion of the coil aperture of the antenna element overlap with each other.

Abstract: A computer-implemented system and method for identifying tasks using temporal footprints is provided. A database of temporal footprints is maintained. Each temporal footprint is representative of a different task and includes one or more significant patterns of two or more sequential events. Events performed by one or more users are tracked. At least one pattern including sequential occurrences of two or more of the tracked events is identified. The identified pattern is compared to each of the significant patterns of the temporal footprints. A footprint score for the identified pattern is determined with respect to each temporal footprint. The task associated with the temporal footprint having the highest footprint score is assigned to the identified pattern.

Abstract: Techniques for allocating individually executable portions of executable code for execution in an Elastic computing environment are disclosed. In an Elastic computing environment, scalable and dynamic external computing resources can be used in order to effectively extend the computing capabilities beyond that which can be provided by internal computing resources of a computing system or environment. Machine learning can be used to automatically determine whether to allocate each individual portion of executable code (e.g., a Weblet) for execution to either internal computing resources of a computing system (e.g., a computing device) or external resources of an dynamically scalable computing resource (e.g., a Cloud). By way of example, status and preference data can be used to train a supervised learning mechanism to allow a computing device to automatically allocate executable code to internal and external computing resources of an Elastic computing environment.

Abstract: Techniques for customizing knowledge representation systems including identifying, based on a plurality of concepts in a knowledge representation (KR), a group of one or more concepts relevant to user context information, and providing the identified group of one more concepts to a user. The KR may include a combination of modules. The modules may include a kernel and a customized module customized for the user. The kernel may accessible via a second KR.

Abstract: A reasoning engine is disclosed. Contemplated reasoning engines acquire data relating to one or more aspects of various environments. Inference engines within the reasoning engines review the acquire data, historical or current, to generate one or more hypotheses about how the aspects of the environments might be correlated, if at all. The reasoning engine can attempt to validate the hypotheses through controlling acquisition of the environment data.

Abstract: An advanced intelligence engine (AIE) for use in identifying what may be complex events or developments on one or more data platforms or networks from various types of structured or normalized data generated by one or more disparate data sources. The AIE may conduct one or more types of quantitative, correlative, behavioral and corroborative analyses to detect events from what may otherwise be considered unimportant or non-relevant information spanning one or more time periods. Events generated by the AIE may be passed to an event manager to determine whether further action is required such as reporting, remediation, and the like.

Abstract: A system for the dynamic encoding in a semantic network of both syntactic and semantic information into a common four valued logical notation. The encoding of new information being benign to prior syntactic constructions, tests for N conditionals in time O(C) and allows for the proper quantification of variables at each recursive step. The query/inference engine constructed from such an implementation is able to optimize short term memory for maximizing long term storage in the automaton. In a parallel context this can be viewed as optimizing communication and memory allocation between processes. Disclosed embodiments of a four valued encoding achieve efficiencies in minimizing the run time stack and maximizing heap size especially in a parallel architecture. Disclosed embodiments are useful in simulation and search engine implementations.

Abstract: The subject disclosure relates to methods and systems for identifying and classifying electric-vehicle (EV) owners. Methods of the subject technology can include steps for generating an initial model based on a plurality of load-curve characteristics, and training the initial model using a training data set to produce a configured model. In some implementations, the methods can also include steps for determining a probabilistic classification for each of a second plurality of users by analyzing load-curve data associated with the second plurality of users using the configured model. Systems and computer readable media are also provided.

Abstract: A system and method enables users to selectively expose and optionally monetize their data resources, for example on a web site. Data assets such as datasets and models can be exposed by the proprietor on a public gallery for use by others. Fees may be charged, for example, per new model, or per prediction using a model. Users may selectively expose public datasets or public models while keeping their raw data private.

Abstract: Methods, systems, and products adapt recommender systems with pairwise feedback. A pairwise question is posed to a user. A response is received that selects a preference for a pair of items in the pairwise question. A latent factor model is adapted to incorporate the response, and an item is recommended to the user based on the response.

Abstract: Herein disclosed is a system and method for record linkage that uses machine learning to link records, so that many users can contribute their training data to a shared repository and employ the accumulated training data without any user having to share their actual data. The system includes a record linkage server, which further includes a record linkage repository, a domain classifier, and a domain classification trainer. The record linkage server is connected with a record linkage client, which includes a field comparator and a manual label prompter.

Abstract: In accordance with the teachings described herein, systems and methods are provided for measuring a user's comprehension of subject matter of a text. A summary generated by the user is received, where the summary summarizes the text. The summary is processed to determine a first numerical measure indicative of a similarity between the summary and a reference summary. The summary is processed to determine a second numerical measure indicative of a degree to which a single sentence of the summary summarizes an entirety of the text. The summary is processed to determine a third numerical measure indicative of a degree of copying in the summary of multi-word sequences present in the text. A numerical model is applied to the first numerical measure, the second numerical measure and the third numerical measure to determine a score for the summary indicative of the user's comprehension of the subject matter of the text.

Abstract: Methods and systems for modeling user arrival and choice in the context of off-street parking solutions. A first component models the arrival and duration of stay of users as a function of time, taking into account different user profiles (or “clusters”), captured by a latent variable. A second component provides a ranking function (for each user cluster), wherein the input features describing the “choice” constitute status variables associated different car park(s), and the output constitutes a preferred car park and a pricing scheme. The system simulates different user behaviors by assuming some standard groups of users will behave similarly. Groups of users or user profiles are learned automatically. The profiles are then employed as a key element for automatically learning a decision function of parking users, and automatically learning one decision function per profile.

Abstract: The present disclosure provides a computer-implemented method of processing Web activity data. The method includes obtaining a collection of Web activity data generated by a plurality of users at a plurality of Webpages, wherein the Webpages are from a plurality of unaffiliated Websites. The method also includes extracting a plurality of search terms from the Web activity data and associating each of the plurality of search terms with a corresponding Webpage. The method also includes generating statistical data from the Web activity data based, at least in part, on the search terms, the statistical data corresponding to the online activity at one or more Webpages.

Abstract: A test operation and reporting system is operable to evaluate testing of a system under test (SUT). The test operation and reporting system includes a testing metrics selection engine to identify core metrics and one or more optional metrics to evaluate a testing service level of one or more tests performed on the SUT. A metrics compilation module determines measurements for the core metrics and optional metrics. A trend evaluation module determines whether a trend determined from the metrics meets an associated target, and identifies a metric indicator to explain the trend if the associated target is not met. A dashboard engine generates a plurality of views based on selections. The views are operable to include the trend, an associated target, the core metrics and optional metrics, the metric indicator and other metrics.

Abstract: A network device, system, and method are directed towards detecting trusted reporters and/or abusive users in an online community using reputation event inputs, such as abuse reports. When an abuse report is received for a content item, the combined trust (reputation) of previous reporters on the reported content item and the trust (reputation) of the content author are compared to determine whether to trust the content item. If the content item is un-trusted, the content item may be hidden from public view. In one embodiment, the content item might still be visible to the content author, and/or members in the author's contact list, or the like, while being hidden from another user in the community. In one embodiment, the author may appeal the determined trust, and results of the appeal may be used to modify a trust of at least one reporter.

Abstract: A method of providing reservation status relating to a group of objects includes providing a database for containing (i) availability data describing availability of at least one of the group of objects, and (ii) reservation data describing allocation of at least one of the group of objects. The availability data and the reservation data are stored in sparse form. The method further includes extracting, from the database, availability data and reservation data corresponding to a predetermined period of time, and combining the extracted availability data and reservation data to form windowed data in a dense format. The method also includes receiving the windowed data and providing the windowed data in a bit-vector view, and sampling the windowed data in the bit-vector view to produce sampled data. The sampled data provides the reservation status as a static view of the windowed data in the bit-vector view.

Abstract: The system provides a method and apparatus for providing controlled access to events, premises, transportation, and the like. In one embodiment, the system provides a ticket that is tied to a user and/or a device. The ticket in one embodiment comprises a dynamic link whose privileges and permissions can be controlled by a system controller so that use, re-use, and re-sale of the ticket can be controlled by the issuer and not by a purchaser or user. The system in one embodiment uses a reader/scanner associated with a controlled entrance that can receive tickets via scanning or some other form of electronic communication. In one embodiment, the system uses radio signals, such as Wi-Fi, Bluetooth, NFC (Near Field Communication) from a mobile device to determine if access should be granted.

Abstract: An automated kiosk and related apparatus provide check-in and boarding services to energy sector passengers, such as helicopter passengers. Preferably, the kiosk and related apparatus can take and store a picture of the passenger, calculate and/or measure the weight of the passenger and the passenger's luggage, print luggage tags and boarding printouts, check third parties' databases (such as a no-fly list (NFL)) for approval for the passenger's flight and can transmit data to another location (server, third party employer, pilot).

Abstract: A method and system for integrating data-handling policies into a computer-implemented workflow model is provided. In one embodiment, a workflow editor implemented using one or more processors may include a privacy manager module configured to permit a business process designer to integrate data handling policies into a workflow model. A privacy manager module, or simply a privacy manager, may also be configured to execute a consistency check with respect to newly-created and existing data handling policies to determine whether there is a conflict among any of the data-handling policies associated with tasks and data objects of the workflow model.

Abstract: A method comprises receiving a set of variable parameters, determining at least one computer executable service based on the set of variable parameters, determining if there are more than one computer executable services based on the set of variable parameters, and if there are more than one computer executable services, resolving any conditional attributes between the more than one computer executable services. Each of the at least one computer executable service is characteristically dependent on at least one variable parameter of the set of variable parameters.

Abstract: Embodiments of the invention provide systems, methods, and apparatus for receiving input information including at least one of generator parameters, energy output requirements, fuel cost, fuel availability, and a maintenance schedule; creating a resource model based on the input information wherein creating the resource model includes linearizing a quadratic objective function and linearizing a quadratic gas constraints function; generating an optimized operating schedule, fuel mix, and allocation plan from the resource model based on the input information; and controlling the generator resources to optimally meet energy output requirements using the operating schedule fuel mix, and allocation plan. Numerous other aspects are provided.

Abstract: A method of managing a supply chain comprises providing at a customer interface module a plurality of order fulfillment options to a customer, and receiving from the customer a selection of a particular order fulfillment option. The method also includes receiving a first order from the customer, and receiving a first inventory status from a first distribution center. A first distribution center sends a first product to the customer in response to determining that the particular order fulfillment option comprises a fill-partial order fulfillment option, and a duration between the time that the first product is directed to be sent and the time when the first product is actually sent is determined. An alert is generated if the duration is greater than a predetermined duration.

Abstract: Techniques disclosed herein facilitate the use of the primary work queue within an information management application as a centralized access point for creating and viewing multiple types of new draft items such as a note, to-do, or message item. An information management application can receive a new item request through its user interface and initiate a new draft item in response to the new item request. A view of new draft item can then be surfaced in a primary work queue of the information management application. The item type of the new draft item may be different than other item types in the primary work queue.

Abstract: Self-learning and adaptive modeling is employed with respect to predictive analytics. A hierarchical model structure can be employed comprising a set of predictive models automatically built from accumulated data and distributed across multiple levels. For a given input type, a set of candidate models can be identified across varying levels of granularity, and a best model selected based on a comparison of performance metrics of the models. The best model can then be activated for use in making predictions. Of course, the best model can change based on most recent training performance results, since as more data becomes available more specific models can be developed.

Abstract: A system and method for facilitating rendering a user interface display screen or portion thereof. An example method includes determining context information associated with a user, wherein the context information includes use job role information; and employing the context information to select one or more visualization types from a set of available visualization types. The method may further include using the context information to provide one or more first user options to select one or more categories of data pertaining to a business task; referencing the one or more categories to facilitate determining one or more data attributes, dimensions, or measures associated with the context information; utilizing the one or more data attributes and the context information to select the one or more visualization types from the set of available visualization types; and providing a second user option to choose a visualization type from among selected visualization types.