Abstract: Techniques for object detection are provided that employ limited learned attribute ranges. One or more objects are initially detected for a full range of one or more attributes at each location of an image. Thereafter, a set of positional constraints are generated indicating an expected range of values for each position in the image for one or more of the attributes based on the detected objects employing a geometric model of a scene in the image. Objects are then detected in the image using the expected range of values for each position in the image for the one or more the attributes. The attributes comprise, for example, one or more of size, pose and rotation of the objects. A best fit is computed to the geometric model to generate the set of positional constraints, for example, using a least squares approach.

Abstract: Disclosed is a surveillance system and method based on accumulated features of objects. The surveillance system ensures and accumulatively stores a plurality of data about feature information corresponding to an object picked up by a plurality of cameras and easily identifies the same object in an image taken by another camera having a surveillance area different from those of the plurality of cameras on the basis of the data, thereby allowing for continuous tracing.

Abstract: A method for training a vehicle detection system used in a street occupancy estimation of stationary vehicles. The method includes defining first and second areas on an image plane of an image capture device associated with monitoring for detection of vehicles. The method includes receiving video-data from a sequence of frames captured from the image capture device. The method includes determining candidate frames that include objects relevant to a classification task in the second area. The method includes extracting the objects from the candidate frames, extracting features of each extracted object, and assigning labels to the each extracted object. The method includes training at least one classifier using the labels and extracted features. The method includes using the at least one trained classifier to classify a stationary vehicle detected in the first area.

Abstract: A positioning system for a vehicle includes a camera, a processor unit and a data storage device. A length relating to a feature of the vehicle is stored in the data storage device. The vehicle is positioned for an inductive charging process in that the vehicle is recorded by a camera and a feature of the vehicle is detected. The position relating to a feature is calculated.

Abstract: An overhead clearance system for a vehicle is configured to receive signals from wireless transceivers attached to objects that are towed or carried by the vehicle and extend above a top of the vehicle. A controller is programmed to receive the signals from the wireless transceivers and transmit a request to a remote device to send height data associated with the object and the vehicle. The controller outputs an alert when combined object and vehicle heights exceed a sensed vertical clearance.

Abstract: A method detects events in an accoustic signal subject to cyclostationary background noise by first segmenting the signal into cycles. Features with a fixed dimension are derived from the cycles, such that the timing of the features is relative to a cycle time. The features are normalized using an estimate of the cyclostationary background noise. Then, after the normalizing, a classifier is applied to the features to detect the events.

Abstract: Currency bills are received, transported, and imaged to produce image data from which a visually readable image of each currency bill can be reproduced. Each of the currency bills includes a denomination, a serial number, and a set of secondary identifiers. One of the currency bills is determined to be a suspect bill. The suspect bill serial number is attempted to be extracted from the image data associated with the suspect bill. In response to failing to extract a complete serial number of the suspect bill, a serial number field in a suspect report is populated with a serial number snippet image.

Abstract: The disclosed embodiments illustrate methods and systems for encoding an image. The method includes identifying one or more objects, having an associated first tag value, in the image. The first tag value is deterministic of at least a type of the one or more objects. The number of the one or more objects in the image is less than a predetermined number of objects. The method further includes assigning a second tag value to each pixel in the image to create an encoded image. The second tag value is assigned based on the type of object represented by each pixel. The size of the second tag value is less than the size of the first tag value. The method further includes defining a header field for the encoded image. The header field includes the first tag value associated with each of the one or more objects.

Abstract: Methods for correcting distortions in an image including text, or an image of a page that includes text, are disclosed. The methods include identifying reliable and substantially straight lines from elements in the image. Vanishing points are determined from the lines. Parameters associated with a rectangle are determined. A coordinate conversion is performed.

Abstract: A computer system is programmed to analyze data from aerial images and LiDAR data obtained from a region of interest in order to determine whether a group of LiDAR data points representing an individual item of vegetation (i.e. a blob) is a particular type of vegetation. Infrared data from aerial images of the region of interest is stretched and divided by red spectral data to compute an objective-stretched vegetation index value (OVI) for a pixel. The mean LiDAR intensity and the mean OVI for the LiDAR data points and the pixels in the area of a blob are used to predict what type of vegetation is represented in the area of the blob.

Abstract: According to one embodiment, a medical image processing apparatus includes an acquisition unit, an analysis unit, and a display controller. The acquisition unit acquires volume data of a morphological image and volume data of a functional image which are obtained by imaging an object. The analysis unit analyzes the volume data of the morphological image. The display controller controls to display a reference point on volume data of the morphological image and to decide a slice of the volume data of the functional image which passes through the reference point, based on an analysis result obtained by the analysis unit.

Abstract: An approach to detecting objects in an image dataset may combine texture/color detection, shape/contour detection, and/or motion detection using sparse, generative, hierarchical models with lateral and top-down connections. A first independent representation of objects in an image dataset may be produced using a color/texture detection algorithm. A second independent representation of objects in the image dataset may be produced using a shape/contour detection algorithm. A third independent representation of objects in the image dataset may be produced using a motion detection algorithm. The first, second, and third independent representations may then be combined into a single coherent output using a combinatorial algorithm.

Abstract: A game apparatus includes a CPU, and in a mode of examining a flower based on an imaged image, the CPU activates two outward cameras to allow a user to image a flower. The CPU obtains color information, shape information and a size of the imaged flower from the imaged image. A shape category is obtained from the shape information, and with the shape category, data for search included in a database for search is filtered. Then, by comparing color information, shape information, and the size of the imaged flower with the data for search to be used, a score of a degree of approximation of the color information and scores of the degree of matching of the shape information and size, etc. are obtained. Then, images of flowers as candidates are presented in the descending order of the score (similarity level).

Abstract: The present invention discloses a grid data record processing method. The method comprising: acquiring influence parameters of lag time of an insulator on which flashover is occurred, the lag time being a time interval from the insulator flashover to tripping of a corresponding breaker in a substation is caused; determining the lag time according to the acquired influence parameters of the lag time and a lag time evaluation model; and determining trip-up records caused by the insulator flashover from grid data records according to the lag time. With the method and apparatus according to embodiments of the present invention, trip-up records caused by insulator flashover can be efficiently determined from grid data records.

Abstract: Systems, apparatuses, and methods are provided for refining building alignment in an aerial image. At least one candidate shifting vector and matching score value are determined for a local building. At least one dominant shifting vector is determined for at least one random group of neighboring buildings of the local building. At least one optimized matching score is calculated using the at least one candidate shifting vector for the local building and the at least one dominant shifting vector for the at least one random group of the neighboring buildings. A final shifting vector for the local building is found using the at least one optimized matching score.

Abstract: A novel technique for unsupervised feature selection is disclosed. The disclosed methods include automatically selecting a subset of a feature of an image. Additionally, the selection of the subset of features may be incorporated with a congealing algorithm, such as a least-square-based congealing algorithm. By selecting a subset of the feature representation of an image, redundant and/or irrelevant features may be reduced or removed, and the efficiency and accuracy of least-square-based congealing may be improved.

Abstract: A method for classifier generation includes a step of obtaining data for classification of a multitude of samples, the data for each of the samples consisting of a multitude of physical measurement feature values and a class label. Individual mini-classifiers are generated using sets of features from the samples. The performance of the mini-classifiers is tested, and those that meet a performance threshold are retained. A master classifier is generated by conducting a regularized ensemble training of the retained/filtered set of mini-classifiers to the classification labels for the samples, e.g., by randomly selecting a small fraction of the filtered mini-classifiers (drop out regularization) and conducting logistical training on such selected mini-classifiers. The set of samples are randomly separated into a test set and a training set.

Abstract: An industrial safety system is provided that integrates optical safety monitoring with machine control. The safety system includes an imaging sensor device supporting pixel array processing functions that allow time-of-flight (TOF) analysis to be performed on selected portions of the pixel array, while two-dimensional imaging analysis is performed on the remaining portions of the array, reducing processing load and response time relative to performing TOF analysis for all pixels of the array. The portion of the pixel array designated for TOF analysis can be pre-defined through configuration of the imaging sensor device, or can be dynamically selected based on object detection and classification by the two-dimensional imaging analysis. The imaging sensor device can also implement a number of safety and redundancy functions to achieve a high degree of safety integrity.

Abstract: The disclosure provides an approach for detecting objects in images. An object detection application receives a set of training images with object annotations. Given these training images, the object detection application generates semantic labeling for object detections, where the labeling includes lower-level subcategories and higher-level visual composites. In one embodiment, the object detection application identifies subcategories using an exemplar support vector machine (SVM) based clustering approach. Identified subcategories are used to initialize mixture components in mixture models which the object detection application trains in a latent SVM framework, thereby learning a number of subcategory classifiers that produce, for any given image, a set of candidate windows and associated subcategory labels.

Abstract: An object investigation and classification system may include an object test system, a data storage system, and a data processing system. The object test system may receive a command to perform at least one action with a test object, perform the at least one action with the test object, and return test information indicative of at least one percept resulting from the at least one action. The data storage system may contain an experience database containing data indicative of multiple classifications and, for each classification, at least one action that was performed with at least one previously-observed reference object having this classification, and at least one percept value that is based in whole or in part on the test information resulting from the at least one action.

Abstract: An imposing apparatus searches for a layout of objects whose profile shapes (profile lines) do not overlap each other with respect to each of cells that make up an imposition area. The imposing apparatus then adjusts an interval between the objects that have been laid out according to the search result, by a unit smaller than the unit length of the cells, thereby bringing the profile lines of adjacent ones of the objects into partial agreement with each other.

Abstract: Disclosed is an image forming apparatus, including: n laser elements arranged in the sub-scanning direction and configured to simultaneously scan an image; a pixel selection unit configured to execute a thinning process in which the pixels are thinned by selecting m pixels among n pixels arranged in the sub-scanning direction, by changing positions of the pixels to be selected according to positions in the main scanning direction; a pulse width modulation processing unit configured to sequentially convert image data corresponding to the m pixels into m pulse width modulation signals; a transmission unit configured to transmit the m pulse width modulation signals in parallel; an assignment unit configured to assign the m pulse width modulation signals to m laser elements corresponding to the positions of the m pixels; and a driving unit configured to drive the laser elements in accordance with the assigned pulse width modulation signals.

Abstract: A printing apparatus 100 performs print processing for a PDF file received via a communication unit 105. The printing apparatus 100 includes a CPU 101 and a HDD 104 storing the PDF file. The CPU 101 controls the HDD 104, secures a storage area corresponding to a maximum size of the PDF file that can be processed by the printing apparatus 100 each time reception of the PDF file is started, and sequentially stores PDF files received for each secured storage area. The CPU 101 updates a size of the secured storage area from the maximum size of the PDF file that can be processed by the printing apparatus 100 to an actual size of the PDF file having been received completely. The CPU 101 performs control so that the PDF files stored in the HDD 104 are processed in an order of reception start.

Abstract: Disclosed is a method and system of differential processing a print job including one or more original documents to render an obfuscated version of the print job. According to an exemplary method, the differential process replaces letters of an original document with randomly selected characters of substantially the same size and location as the original document and objects such as images/graphics are replaced with blurred versions of substantially the same size and locations as the objects in the original document. The differential process creates an obfuscated version of the print job which is illegible and useful for further processing where privacy of documents included in the print job is required.

Abstract: An image processing apparatus including a memory includes a first conversion method configured to perform conversion processing for converting an image represented by span information in page line sequence into span information in tile sequence, using the memory; a second conversion unit configured to perform conversion processing for converting an image represented by pixel information in page line sequence into pixel information in tile sequence, using the memory; and a control unit configured to control a conversion unit employing a less usage amount of the memory used in a case that a process target image is converted into tiles, of the first conversion unit and the second conversion unit, to perform the conversion processing on the process target image.

Abstract: There are provided a print control apparatus in which a load on a user can be lightened by reporting information on necessary processing, a method for controlling a print apparatus, and a print medium. A print control apparatus for controlling a print apparatus to print an image based on print data, the print control apparatus includes: a determination unit configured to determine whether a size of a sheet set in the print apparatus and a size of the print data match; an acquisition unit configured to acquire information on processing needed to adjust the size of the print data to be closer to the size of the sheet in a case where it is determined that the size of the sheet and the size of the print data do not match; and a notifying unit configured to notify a user of information acquired by the acquisition unit.

Abstract: A barcode device including a barcode scanner to scan barcode labels and provide raw barcode data signals, a processor to receive and process the raw barcode data signals to provide processed barcode data signals and compare at least two of the processed barcode data signals, an indicator to notify a user of barcode data information based on the receipt of barcode data and comparison performed by the processor, and a housing to contain the barcode scanner, the processor, and the indicator, the housing comprising a first end, an opposing second end, and a body extending between the first end and the second end, the housing configured to couple to a back of a glove.

Abstract: An electronic device. The device comprises a rewritable radio-frequency identification (RFID) tag to store an identification number and to transmit the identification number via a radio transmitter, an RFID writer, configured to write an identification number into the RFID tag based on selection by a controller, and a memory storing identification selection rules and a list of identities of RFID interrogators. The device further comprises a controller, configured to read the identity of the RFID interrogator from the RFID reader, analyze the identification selection rules and the list of identities of the RFID interrogators in the memory, select an identification number for the RFID tag based on the list of identities of the RFID interrogators, the identification selection rules stored in the memory, and the identity of the RFID interrogator, and command the RFID writer to write the selected identification number into the RFID tag.

Abstract: A casino chip according to one embodiment includes an RFID circuit on or within a substrate; and an antenna coupled to the RFID circuit; wherein the casino chip is configured such that a signal associated with the casino chip is capable of being read by at least one RF reader. An RFID system according to one embodiment includes at least one RF reader; and a plurality of casino chips. Each of the plurality of casino chips includes an RFID circuit on or within a substrate; and an antenna coupled to the RFID circuit. Each of the plurality of casino chips are configured such that a signal associated with each of the casino chips is capable of being read by the at least one RF reader.

Abstract: The present invention is an apparatus and method for generating a barcode with a human readable interpretation (HRI). The method includes receiving a data set comprising an application identifier and a data portion. The data set further includes a first special character before the application identifier and a second special character after the application identifier and before the data portion. The application identifier and data in the data portion have a one to one correspondence with an HRI. The method further includes generating a barcode encoding data set based on the data set, including stripping the first special character and the second special character from the data set; generating an HRI data set based on the data set; and generating the barcode with the HRI based on the barcode encoding data set and the HRI data set.

Abstract: A disclosed RFID tag includes: a base member; a semiconductor chip mounted on the base member; and an island-shaped reinforcing member covering the semiconductor chip and being configured to reinforce the base member. The reinforcing member has a side portion to which a recess is provided. The recess serves as an originating point of a fold line such that the fold line is formed away from the semiconductor chip when the reinforcing member is folded.

Abstract: A disadvantage of the prior art consists in the fact that the RFID transponders attached to plug-in connectors have a range that is insufficient for many applications. The present disclosure provides a design for a plug-in connector housing with an RFID transponder integrated therein, which allows a range that is greater than the one possible in the prior art. This object is achieved as a result of the fact that the antenna of the RFID transponder includes a slot, so that the antenna is a slot antenna.

Abstract: A radio frequency identification wristband for attaching to a patient that has a band, a wristband housing attached to or integral with said band, one or more radio frequency identification tag(s) or tag inlay(s), an insulator material, wherein said wristband housing is adhered to said radio frequency identification tag or tag inlay, said radio frequency identification tag or tag inlay is adhered to an isolator material, and wherein said insulator material is nearest to the skin of the patient and insulates the radio frequency identification tag or tag inlay from the patient's skin.

Abstract: An RF tag has an inlay with an IC chip and an antenna, a planar auxiliary antenna laminated on the inlay in an insulating state, a dielectric constant regulation plate which becomes a base on which the inlay including the auxiliary antenna laminated thereon is mounted, and functions as a dielectric constant regulation layer for the mounted inlay, and a case which receives the dielectric constant regulation plate in a state where the inlay including the auxiliary antenna laminated thereon is mounted. The dielectric constant regulation plate is formed into a shape which allows the dielectric constant regulation plate to be attachably/detachably and non-movably engaged in the case and which allows the dielectric constant regulation plate to have a predetermined dielectric constant which regulates communication characteristics of the inlay including the auxiliary antenna laminated thereon.

Abstract: An electronic neuronal circuit system to model the interaction between the postsynaptic terminal of a first synapse between two neurons and the postsynaptic terminal of a second synapse between two neurons includes comparators to model the presynaptic neurons of the synapses, plurality of three diodes connected to the comparators to model synapses, an AND gate and latch to model the formation of functional link between the postsynaptic terminals, and timer-controlled latches for controlling the life-span of the inter-postsynaptic functional link, durations of re-activation of inter-postsynaptic functional link and flow of activity through the output postsynaptic dendritic terminals.

Abstract: The use of a pipelined algorithm that performs parallelized computations to train deep neural networks (DNNs) for performing data analysis may reduce training time. The DNNs may be one of context-independent DNNs or context-dependent DNNs. The training may include partitioning training data into sample batches of a specific batch size. The partitioning may be performed based on rates of data transfers between processors that execute the pipelined algorithm, considerations of accuracy and convergence, and the execution speed of each processor. Other techniques for training may include grouping layers of the DNNs for processing on a single processor, distributing a layer of the DNNs to multiple processors for processing, or modifying an execution order of steps in the pipelined algorithm.

Abstract: Methods and apparatus for piecewise linear neuron modeling and implementing artificial neurons in an artificial nervous system based on linearized neuron models. One example method for operating an artificial neuron generally includes determining that a first state of the artificial neuron is within a first region; determining a second state of the artificial neuron based at least in part on a first set of linear equations, wherein the first set of linear equations is based at least in part on a first set of parameters corresponding to the first region; determining that the second state of the artificial neuron is within a second region; and determining a third state of the artificial neuron based at least in part on a second set of linear equations, wherein the second set of linear equations is based at least in part on a second set of parameters corresponding to the second region.

Abstract: Systems and methods are disclosed for testing decision table-based rules. In an embodiment, a memory device may store instructions that cause a processor to perform a method comprising receiving one or more constraints for a set of data attributes, generating a structured data set of the data attributes having values based on the one or more constraints, and providing the structured data set to a decision table-based rule set.

Abstract: In one embodiment, a method may include symbolically executing application code on a first framework. The method may also include creating a first model based on the symbolic execution of the first framework. The method may additionally include symbolically executing the application code on a second framework. The method may further include creating a second model based on the symbolic execution of the first framework. The method may also include determining one or more parameters associated with the first framework based on the first model. The method may additionally include determining one or more parameters associated with the second framework based on the second model. The method may also include selecting one of the first framework and the second framework as a desired framework for execution of the application code based on a comparison of the one or more parameters associated with the first framework and the one or more parameters associated with the second framework.

Abstract: Transfer learning is the task of leveraging the information from labeled examples in some domains to predict the labels for examples in another domain. It finds abundant practical applications, such as sentiment prediction, image classification and network intrusion detection. A graph-based transfer learning framework propagates label information from a source domain to a target domain via the example-feature-example tripartite graph, and puts more emphasis on the labeled examples from the target domain via the example-example bipartite graph. An iterative algorithm renders the framework scalable to large-scale applications. The framework propagates the label information to both features irrelevant to the source domain and unlabeled examples in the target domain via common features in a principled way.

Abstract: The inventive subject matter is generally directed to a cross channel optimization system, methods, and related software which provide for the conducting of experiments and/or optimization of digital content across a plurality of external content systems to user of the external content systems.

Abstract: A system for predicting the thickness of a battery is disclosed. In one aspect, the battery thickness predicting system includes a learning data input unit for receiving data on a previously manufactured battery. The thickness predicting system further includes an object data input unit for receiving data on a battery whose thickness is to be predicted. The system further comprises a mechanical learning unit connected to the learning data input unit to obtain a predicting function based on learning factors input to the learning data input unit and to provide weight values to the learning factors, respectively. The system further includes a thickness predicting unit connected to the object data input unit and the mechanical learning unit and using the weight values provided by the mechanical learning unit in order to predict the thickness of the battery whose thickness is to be predicted.

Abstract: A method of displaying a representation of a power distribution network and a representation of a parameter of the power distribution network on a display device includes displaying the representation of a power distribution network on the display device as an expandable tree structure in a first region, the expandable tree structure having branches that can be expanded and collapsed; displaying the representation of the parameter on the display device during a time period that the representation of the power distribution network is displayed; and collapsing or expanding a portion of the representation of the parameter when a branch is expanded or collapsed.

Abstract: A system and method to graphically represent historical product structures. When a computer extracts all change states for a data set corresponding to a first product structure having a plurality of items. The change states associated with each item are concatenated. The concatenated change states relative to each item and to the parametric constraint effective for the data set are displayed on an electronic display. In this way it is possible to visualize the historical product structure.

Abstract: The present disclosure describes methods, systems, and computer program products for providing enterprise collaboration content governance. One computer-implemented method includes receiving a content creation request associated with particular content and a context, transmitting the particular content and context for validation of the content creation request. comparing, by operation of a computer, at least one rule and at least one pattern to the transmitted content and context to generate a rule result, determining at least one action result based on the generated rule result, and performing at least one application action based on the determined at least one action result.

Abstract: An embodiment of the invention includes a computer implemented method for monitoring construction. The method may include receiving information about a construction project. The received information may include information about construction milestones and schedule information about the construction milestones. The information may include graphical data related to the construction milestones and the schedule information. Information about the location of a computing device may be received. Based on the location information and the information about the construction project, a graphical display user-interface may be prepared. In an embodiment of the invention, the display may include a visual representation of expected progress of the project. The display may include information about expected activity related to the project for a period of time.

Abstract: A cloud-based operator interface system is provided that runs as a cloud service on a cloud platform. The cloud-based operator interface system collects industrial data from one or more industrial systems via respective cloud gateway devices. A set of predefined operator interface screens are stored on cloud storage associated with the operator interface system, and delivered to authorized Internet-capable client devices upon request. The industrial data received from the cloud gateways can be delivered to the client devices from the cloud platform via the operator interface screens. Additional cloud-side services can correlate and analyzes the industrial data on the cloud platform to facilitate additional reporting, alarming, and notification features.

Abstract: A new technique to analyze the control-flow, i.e., the workflow graph of a business process model, which is called symbolic execution, is provided. Acyclic workflow graphs that may contain inclusive OR-gateways are considered; a symbolic execution for them is defined, which runs in quadratic time. In particular, this symbolic execution essentially comprises labeling edges of nodes of the graph such that a label assigned to a first edge comprises a set of one or more edge identifiers, each identifying a second edge that is an outgoing edge of an XOR-split or an IOR-split node in the graph, whereby executing the second edge ensures that the first edge will be executed. Such a scheme may permit a decision for any pair of control-flow edges or tasks of the workflow graph whether they are sometimes, never, or always reached concurrently. This has different applications in finding control- and data-flow errors.

Abstract: In some examples, an autonomous mobile reading device is provided. The autonomous mobile reading device may include an autonomous movement device and a radio-frequency identification (RFID) reader. The RFID reader may be configured to read, via one or more antennas, RFID tags associated with inventory items. The one or more antennas may be included as part of the autonomous mobile reading device, within an inventory holder, or in some other structure or device.

Abstract: A modular self-care health monitoring system which employs a compact microprocessor-based unit such as a video game system of the type that includes switches for controlling device operation and a program cartridge. In accordance with the invention, the program cartridge adapts the microprocessor-based unit for operation with a glucose monitor (or, another type of health monitor). The microprocessor-based unit processes data supplied by the glucose monitor to supply signals for displaying relevant information on a display unit that may be included in the microprocessor-based unit or may be a separate unit such as a television or video display monitor. The system provides for transmission of signals to a remote clearinghouse or a healthcare facility via telephone lines or other transmission media. The clearinghouse includes signal processing capability for transmission of reports to a remotely located healthcare professional via facsimile transmission.