Abstract: A method is disclosed for generating a three-dimensional (3D) model of a target object. The method includes obtaining one or more image capture settings and capturing, using the one or more image capture settings, a plurality of two-dimensional (2D) images each including at least a portion of a coded target and at least a portion of the target object. The method further includes transmitting the plurality of 2D images to a model generation server and generating, by the model generation server based on the plurality of 2D images, the 3D model of the target object and one or more model characteristics of the 3D model.

Abstract: A method is provided for detecting faults in a conductive circuitry. The method includes: printing the conductive circuitry on top of a substrate using a printing head; heating the conductive circuitry with a heat source; scanning the heated conductive circuitry with a non-contact thermal detector; detecting, with the non-contact thermal detector and concurrently with the printing of the conductive circuitry, the faults where the printing head failed to print; and reprinting the faults with the printing head.

Abstract: An apparatus and method are disclosed for improving power savings by accelerating suspend and resume operations. The apparatus having a main integrated circuit, the integrated circuit having a context area, a context snooper, and a context cache, the context area configured to store context change information, the context snooper configured to monitor the context change information, and the context cache configured to store at least a portion of the context change information being monitored by the context snooper; and a memory, the memory configured to receive the at least a portion of the context change information from the context cache upon a suspend process signal to the main integrated circuit, to retain contents during the main integrated circuit suspend, and restore the at least a portion of the context change information to the context cache and/or the context area upon a resume process signal to the main integrated circuit.

Abstract: A method is provided for generating a status report including risk assessment based on Natural Language Processing (NLP). The method includes: receiving a task status that includes a line of text; parsing the line of text to generate a mark-up version of the line of text; calculating a sentence score of the mark-up version of the line of text; calculating an overall score of the task status based on the sentence score; storing the task status including the mark-up version of the line of text and the sentence and overall score; receiving a status report generation request that includes a search criteria; retrieving the task status and the sentence and overall scores associated with the search criteria; calculating a highlighting color of the task status based on the sentence score; and generating the status report including a highlighted task status based on the highlighting color and the task status.

Abstract: A method is disclosed for training a machine learning model to process electronic documents (EDs). The method includes obtaining a structured ED (SED) from a document repository, where the SED includes a first metadata. The method further generates, based on the SED, a bitmap and a second metadata. The method also determines whether the second metadata is within a predetermined threshold of the first metadata and generates, based on the SED and in response to determining that the second metadata is not within the predetermined threshold of the first metadata, a third metadata. The method additionally determines whether the third metadata is within the predetermined threshold of the first metadata and stores, in response to determining that the third metadata is within the predetermined threshold of the first metadata, a second SED comprising the bitmap and the third metadata.

Abstract: A method is provided for manufacturing a three-dimensional printed (3D-printed) object. The method includes: depositing first threads separated by gaps in a first run of a first layer; depositing second threads in a second run of the first layer, and the second threads fill the gaps between the first threads and create a plurality of first-layer vertical interfaces along a length of each of the first threads; depositing third threads separated by gaps in a first run of a second layer; and depositing fourth threads in a second run of the second layer, and the fourth threads fill the gaps between the third threads and create a plurality of second-layer vertical interfaces along a length of each of the third threads. The second layer is deposited on top of the first layer so that one or more of the first-layer vertical interfaces do not overlap with the second-layer vertical interfaces.

Abstract: In an intelligent character recognition (ICR) method for recognizing hand-written text images using a long-short term memory (LSTM) recurrent neural network (RNN), text images are segmented into text line images, and the text lines images are pre-processed to normalize the line height and to equalize the word spacings in each text line. Both training images used to train the RNN network and test images containing text to be recognized by the trained RNN network are pre-processed to have identical heights and identical word spacings between words. This method improves character recognition accuracy.

Abstract: A method, a computer readable recording medium, and a system are disclosed for image segmentation using controlled feedback in a neural network. The method includes extracting image data from an image; performing one or more semantic segmentations on the extracted image data; introducing one or more classifiers to each of the one or more semantic segmentations, each of the one or more classifiers assigning a probability to one or more classes of objects within the image; and generating a segmentation mask from the one or more semantic segmentations.

Abstract: A wound assessment method which can estimate a moisture level of the wound, and related image capture device. The wound area is imaged at least twice where the wound is illuminated under different illumination light intensities. The first image captured using a relatively low illumination light intensity is analyzed to assess the wound, for example measuring its size, color and texture. The second image captures using a relatively high illumination light intensity (e.g. using a flash) is analyzed to estimate the moisture level of the wound. The moisture level estimation method extracts white connected components from the second image, and estimates the moisture level based on the number, sizes, and centroid distribution of the white connected components. A 3D image of the wound may also be captured, e.g. using a structured-light 3D scanner of the image capture device.

Abstract: Print shop operations may be visualized graphically to show relationships between a stream of incoming print jobs and a group of available print production devices, such as printing and finishing machines. A visualization process is performed with microservices to generate UI device panes, which form elements of a graphic user interface from which print shop operation can be monitored or controlled. Each microservice corresponds a different one of the print production devices. This can allow for rapid adjustments and customization of the UI, as may be needed due to user feedback, change in user requirements, and introduction of new print production devices to the print shop. Information may be added to the graphic user interface in combination with the UI device panes to facilitate assignment of print jobs to particular print production devices and/or to show which devices can be used sequentially or in parallel to complete the print jobs.

Abstract: In an intelligent character recognition (ICR) method for recognizing hand-written text images using a long-short term memory (LSTM) recurrent neural network (RNN), text images are segmented into text line images, and the text lines images are pre-processed to normalize the line height and to equalize the word spacings in each text line. Both training images used to train the RNN network and test images containing text to be recognized by the trained RNN network are pre-processed to have identical heights and identical word spacings between words. This method improves character recognition accuracy.

Abstract: Speed and accuracy of character recognition can be improved by isolating text orientation during an early stage of processing an image containing a mixture of horizontal and vertical text. Vertical and horizontal line bounding boxes are defined from characters in the image. In a section of the image containing horizontal text, vertical line bounding boxes may tend to be larger and/or spaced close together due to misalignment of characters. For the same reason, horizontal line bounding boxes may tend to be larger and/or spaced closed together in a section of the image containing vertical text. Such variations in size and/or spacing may be used to identify a division between the horizontal and vertical text. A subsequent character recognition process may take advantage of a known division to conserve computing resources.

Abstract: A combination of surface plasmon field enhanced fluorescence spectroscopy (SPFS) and isotachophoresis (ITP) technologies for detecting biomolecules is disclosed. It uses ITP to preconcentrate the reactants and accelerate the reaction, and then delivers the reacted sample to an SPFS sensor for detection. A microfluidic device with a T-junction is provided, which has two reservoirs respectively containing a low-mobility trailing electrolyte buffer and a high-mobility leading electrolyte buffer, and a main fluid channel between the two reservoirs, where the SPFS sensor is located on a side channel joined to the main channel. A two-step technique is employed, including a step of sample loading and ITP extraction, and a step of delivery of concentrated sample to the detector chamber by pressure-driven flow. In another embodiment, the SPFS sensor is located on the main fluid channel between the two reservoirs. In a particular example, the technique is used in a DNAzyme assay.

Abstract: A method for processing a stroke in an image is provided. The stroke includes a plurality of pixels and the method includes: executing a modified 4-way stroke width transform (SWT) on a mask of the stroke; determining a plurality of certain centerline points among the pixels based on the modified SWT; generating a plurality of polylines within the stroke based on the certain centerline points; determining a plurality of regions of certainty based on the polylines; removing the regions of certainty from the mask and leaving a plurality of regions of uncertainty in the mask; calculating a plurality of joints and end caps for each of the polylines based on the polylines and the regions of uncertainty; generating a completed polyline path by connecting the polylines based on the joints and end caps; and generating a description of the stroke based on the completed polyline path.

Abstract: A method for processing an image that includes a table is provided. The method includes: obtaining a set of edges associated with a cell candidate of the table; determining a longest edge in the set of edges and a first orientation of the longest edge; determining, in the set of edges, an initial edge for a first cell border comprising the first orientation and the longest edge; building the first cell border based on the initial edge, the first orientation, and the set of edges; calculating a second orientation for a second cell border by rotating the first orientation; building the second cell border based on an initial edge for the second cell border and the second orientation; and validating the cell candidate as a cell of the table in response to building the first cell border and building the second cell border.

Abstract: A digital rights management system includes two digital rights management servers (RMS servers) connected to a client computer. The two RMS servers implement different but related digital rights management (DRM) policies, with the first RMS server implementing conventional DRM policies and the second RMS server implementing extended DRM policies. An application program on the client computer interacts with a document on the client computer, and communicates with the first RMS server to obtain access authorization for the document. A plug-in program in the client computer cooperates with the application program, and communicates with the second RMS server to obtain additional access authorization for the document. Access to the document is granted when both RMS servers grant access to the document. This achieves extended digital rights management control which can provide a more flexible access control than that provided by existing DRM systems.

Abstract: A method is disclosed of using IPv6 Neighbor Discovery to discover application services in an IPv6 network, the method including hosting a list of application services on a first host device; creating an application service Neighbor Discovery option for the list of application services hosted on the first host device; attaching the application service Neighbor Discovery option to a Neighbor Discovery solicitation response, a Neighbor Discovery advertisement, or a Neighbor Discovery solicitation request; and sending the Neighbor Discovery solicitation response, the Neighbor Discovery advertisement, or the Neighbor Discovery solicitation request with the application service Neighbor Discovery option from the first host device to one or more second host devices on a IPv6 network connection, wherein the application service Neighbor Discovery option provides the one or more second host devices with the list of application services hosted on the first host device.

Abstract: A display method includes reading from a memory a language setting representing an original language and a first target language; detecting a first set of one or more characters input in the original language; recognizing the first set of one or more characters as first text; translating the first text from the original language to the first target language; displaying the translated first text on one or more display areas; translating the translated first text back to the original language; and displaying the first text translated back to the original language on the one or more display areas.

Abstract: RFID tags are combined in increase their range. A first RFID tag comprises a first chip and a first antenna configured to transmit data from the chip. The first RFID tag has a first initial range by which data may be obtained by an RFID reader from the first chip. A second RFID tag comprises a second chip and a second antenna configured to transmit data from the chip. The second RFID tag has a second initial range by which data may be obtained by an RFID reader from the second chip. A conductive path from first antenna to the second antenna is established to change initial ranges to modified ranges which are greater than the initial ranges.

Abstract: A biosensor using a decoupled microfluidic device, which has a capture chamber and a detection chamber separate from and in fluid communication with each other. The sensing method is based on particle aggregation via homogeneous reactions, by employing microparticles having antibodies on their surfaces which can form aggregates through antigen mediation. Either size-separation or magnetic based separation is used to separate aggregates from single microparticles; the aggregates are later dissociated and the resulting single microparticles are counted to measure the amount of the antigen. Another biosensor uses a decoupled microfluidic device with a capture chamber and a detection chamber, and a 3-D structure in the capture camber to increase immobilized antibody concentration. Immunoreaction efficiency is improved by increasing the number of antibody per reaction volume in the capture chamber.