Abstract: A computing device can receive an image pair, where a first image of the image pair includes a training image and a second image of the image pair includes a ground truth image. The computing device can indirectly train a de-noise ANN by at least: applying the de-noise ANN on the first image to produce a de-noised version of the first image; determining, using a trained super resolution ANN, an extracted feature map for of the de-noised version of the first image; determining, using the trained super resolution ANN, an extracted feature map for the second image, and computationally updating weights of the de-noise ANN based on: (i) a difference between the second image and the de-noised version of the first image and (ii) a difference between the extracted feature map for of the de-noised version of the first image and the extracted feature map for the second image.

Abstract: Methods and systems for training and utilizing an artificial neural network (ANN) are provided. In an example method, a computing device can receive an image pair, where a first image of the image pair includes a training image and a second image of the image pair includes a ground truth image. The computing device could utilize a trained de-noise ANN to determine a de-noised representation of the first image. The computing device could then indirectly training an adaptor ANN by at least applying the adaptor ANN on the de-noised representation to produce an adapted representation for the first image; determining, using a trained super resolution ANN, a high resolution image from the adapted representation, and computationally updating weights of the adaptor ANN based on a loss function that comprises a difference between the high resolution image and the second image.

Abstract: An example system includes a processor and a non-transitory computer-readable medium having stored therein instructions that are executable to cause the system to perform various functions. The functions include obtaining an image associated with a print job, and providing the image as input to a convolutional neural network. The convolutional neural network includes a residual network, upscaling layers, and classification layers configured to detect whether the image is an artificial image having a computer-generated image gradient. The functions also include determining, based on an output of the classification layers, that the image is an artificial image having a computer-generated image gradient. Further, the functions include, based on determining that the image is an artificial image having a computer-generated image gradient, providing the image to an upscaling module of a print pipeline for upscaling rather than using an output of the upscaling layers for the upscaling.

Abstract: A memory control method generates write control data by predetermined areas by attaching processing priority data and a transfer ID, generates read control data for respective predetermined areas by attaching processing priority data and a transfer ID, stores the write control data and the read control data in an arbitration queue, executes an arbitration that determines a priority order of processing taking the write control data and the read control data that are stored in the arbitration queue as targets, and changes the processing priority data every time a predetermined time elapses. The arbitration raises a priority order taking the write control data or the read control data that includes the processing priority data as a timeout request when the processing priority data has passed a preliminarily set threshold by the change.

Abstract: Methods and apparatus for training and utilizing an artificial neural network (ANN) are provided. A computing device can receive training documents including text. The computing device can parse the training documents to determine training data items. Each training data item can include a training label related to text within the training documents and location information indicating a location of text related to the training label. An ANN can be trained to recognize text using the training data items and training input that includes the training documents. After training the ANN, a request to predict text in application documents that differ from the training documents can be received. The application documents can include second text. A prediction of the second text can be determined by applying the trained ANN to the application documents. After determining the prediction of the second text, information related to the second text can be provided.

Abstract: Example systems and related methods relate to rendering using smooth shading. A computing device can receive information about an image, the information including one or more patches, where a particular patch of the one or more patches is specified using a plurality of non-linear equations. The computing device can determine one or more linear approximations to a particular non-linear equation of the plurality of non-linear equations. The computing device can update the particular patch to replace the particular non-linear equation with at least one linear approximation of the one or more linear approximations. The computing device can render at least part of the image by at least rendering the updated particular patch. The computing device can generate an output that includes the rendered at least part of the image.

Abstract: A memory control method receives a read request data set including a management ID and requesting reading of data from a memory, transmits read data that is read corresponding to the read request, stores write data temporarily in a write buffer, stores the read data read from the memory temporarily in a read buffer, stores write control data and read control data in an arbitration queue, executes an arbitration that determines a priority order of processing taking the write control data and the read control data that are stored in the arbitration queue as targets, and matches an order of transmitting a plurality of pieces of read data that are read from the memory corresponding to the read control data selected based on the determined priority order and are associated with an identical management ID to an order of receiving the read request data set.

Abstract: Methods and apparatus for utilizing a machine learning system are provided. A printing device can receive images associated with a page printed by a printer engine of the printing device. The printing device can then provide, to a trained machine learning system configured to predict potential defects associated with the printer engine, the images. The printing device can obtain, from the trained machine learning system, outputs indicating at least one potential defect associated with the printer engine. The printing device can determine, using a solutions database, whether one or more solutions to resolve the at least one potential defect are available. After determining that one or more solutions are available, the printing device can provide, by way of a graphical interface, information about the one or more solutions.

Abstract: Methods and apparatus for utilizing a machine learning system are provided. A printing device can receive a source image and provide, to a trained machine learning configured to provide predict potential quality issues associated with images, the source image. The printing device can then obtain, from the trained machine learning system, one or more outputs indicating at least one potential quality issue associated with the source image. The printing device can then determine, using a solutions database, one or more image enhancements to resolve the at least one potential quality issue. The printing device can then provide, by way of a graphical interface, information about the one or more image enhancements.

Abstract: Methods and apparatus for training and utilizing an artificial neural network (ANN) are provided. A computing device can receive training documents including text. The computing device can parse the training documents to determine training data items. Each training data item can include a training label related to text within the training documents and location information indicating a location of text related to the training label. An ANN can be trained to recognize text using the training data items and training input that includes the training documents. After training the ANN, a request to predict text in application documents that differ from the training documents can be received. The application documents can include second text. A prediction of the second text can be determined by applying the trained ANN to the application documents. After determining the prediction of the second text, information related to the second text can be provided.

Abstract: A memory control method uses a memory including a plurality of bank groups each having a plurality of banks. The memory control method includes masking write control data and read control data based on an inside-bank group constraint period that is a command to command interval during which a processing is restricted inside an identical bank group and an inter-bank group constraint period that is a command to command interval during which a processing is restricted inside different bank groups, and storing an unmasked command in an arbitration queue. An arbitration raises a priority order of control data requesting a processing on the bank group that has been accessed last among the plurality of bank groups.

Abstract: A memory control method uses a memory including a plurality of bank groups each having a plurality of banks. The memory control method includes masking write control data and read control data based on an inside-bank group constraint period that is a command to command interval during which a processing is restricted inside an identical bank group and an inter-bank group constraint period that is a command to command interval during which a processing is restricted inside different bank groups, and storing an unmasked command in an arbitration queue. An arbitration raises a priority order of control data requesting a processing on the bank group that has been accessed last among the plurality of bank groups.

Abstract: A memory control method receives a read request data set including a management ID and requesting reading of data from a memory, transmits read data that is read corresponding to the read request, stores write data temporarily in a write buffer, stores the read data read from the memory temporarily in a read buffer, stores write control data and read control data in an arbitration queue, executes an arbitration that determines a priority order of processing taking the write control data and the read control data that are stored in the arbitration queue as targets, and matches an order of transmitting a plurality of pieces of read data that are read from the memory corresponding to the read control data selected based on the determined priority order and are associated with an identical management ID to an order of receiving the read request data set.

Abstract: A memory control method generates write control data by predetermined areas by attaching processing priority data and a transfer ID, generates read control data for respective predetermined areas by attaching processing priority data and a transfer ID, stores the write control data and the read control data in an arbitration queue, executes an arbitration that determines a priority order of processing taking the write control data and the read control data that are stored in the arbitration queue as targets, and changes the processing priority data every time a predetermined time elapses. The arbitration raises a priority order taking the write control data or the read control data that includes the processing priority data as a timeout request when the processing priority data has passed a preliminarily set threshold by the change.

Abstract: Methods and apparatus for rendering using smooth shading are provided. A computing device can receive information about an image, the information including one or more patches, where a particular patch of the one or more patches is specified using a plurality of non-linear equations. The computing device can determine one or more linear approximations to a particular non-linear equation of the plurality of non-linear equations. The computing device can update the particular patch to replace the particular non-linear equation with at least one linear approximation of the one or more linear approximations. The computing device can render at least part of the image by at least rendering the updated particular patch. The computing device can generate an output that includes the rendered at least part of the image.

Abstract: An example embodiment may involve causing a page of a document to be printed on a printing device, wherein the printing device is in an AM halftoning mode and prints the page using an AM halftone; displaying, on the display unit, a graphical user interface, wherein the graphical user interface includes a selectable option to switch the printing device from the AM halftoning mode to an FM halftoning mode; receiving an indication that the selectable option has been selected; possibly in response to receiving the indication that the selectable option has been selected, causing the printing device to switch from the AM halftoning mode to the FM halftoning mode; and causing the page of the document to be printed again on the printing device, wherein the printing device is in the FM halftoning mode and prints the page using an FM halftone.

Abstract: Techniques and computing devices related to modifying images are provided. A computing device can receive an order to modify pixels of an image. The computing device can include at least a pixel processor and software snippets that are executable on the pixel processor. The computing device can determine parameter values based on the order. The computing device can select a set of software snippets from the software snippets based on the parameter values. The computing device can load the set of software snippets onto the pixel processor. The pixel processor can execute the loaded set of software snippets to modify the pixels. The computing device can generate an output that includes a depiction of the image that includes at least one of the modified pixels.

Abstract: An image forming method uses a memory, forms an image on a print medium using color materials of L colors, and includes: setting N groups associated for respective N objects including a plurality of scanning lines and reproduced with the color materials of the L colors; calculating a relative address that stores tone data representing a tone of one color material among the color materials of the L colors based on coordinates of a plurality of pixels forming the plurality of scanning lines to calculate L addresses separated by shifting the relative address using a predetermined offset address; and transmitting and receiving L tone data representing tones of respective L color materials for reproducing colors of the plurality of pixels forming the scanning lines by using the L addresses to/from the memory via L channels among M (M is an integer larger than N) communication channels.

Abstract: A memory control method includes: attaching transfer IDs to generate write control data and attaching transfer IDs to generate read control data for respective predetermined areas; executing an arbitration that determines a priority order of processing taking the write control data and the read control data that are stored in an arbitration queue as targets; and adding a burst number of a Read command or a Write command to complete a transaction in response to an execution of an Activate command to execute the transaction while decrementing a burst number in response to an execution of the Read command or the Write command, so as to update a remaining burst number as a remaining number of bursts. The arbitration raises a priority order of the Activate command to execute a transaction having a large burst number when the remaining burst number is less than a preliminarily set threshold.

Abstract: A memory control method includes: dividing write data for respective predetermined areas in a memory and attaching transfer IDs to generate write control data for the respective predetermined areas, and dividing read request data set for the respective predetermined areas and attaching transfer IDs to generate read control data for the respective predetermined areas; storing the write control data and the read control data in an arbitration queue; and detecting overlap access request data as a write request data set or a read request data set. The overlap access request data requests an access to an address that is at least partially overlapping an address of received write request data set or read request data set. The arbitration is executed such that the received write request data set or read request data set is processed after the overlap access request data is processed.