公开(公告)号：US20220288920A1

公开(公告)日：2022-09-15

申请号：US17196161

申请日：2021-03-09

申请人： Scott R. Johnson ,  Ziling Zhang

发明人： Scott R. Johnson ,  Ziling Zhang

IPC分类号： B41J2/045

摘要： A printing system is disclosed. The printing system includes at least one physical memory device to store uniformity compensation logic and one or more processors coupled with the at least one physical memory device to execute the uniformity compensation logic to receive print image measurement data corresponding with each of a plurality of pel forming elements, generate a first set of intermediate images based on the print image measurement data, determine whether historical sets of intermediate images are available, generate first transfer functions corresponding to each of the pel forming elements based on the first set of intermediate images and the historical sets of intermediate images upon a determination that the historical sets of intermediate images are available and transmit the first transfer functions for each of the pel forming elements.

公开(公告)号：US20240294012A1

公开(公告)日：2024-09-05

申请号：US18116932

申请日：2023-03-03

申请人： Farnaz HajiahmadiFoomani ,  Ziling Zhang ,  Scott R. Johnson ,  William Edward Manchester

发明人： Farnaz HajiahmadiFoomani ,  Ziling Zhang ,  Scott R. Johnson ,  William Edward Manchester

IPC分类号： B41J2/165 ,  B41J2/045 ,  G06N3/08

CPC分类号： B41J2/16579 ,  B41J2/0451 ,  G06N3/08

摘要： Systems and methods of recommending replacement of printheads. In an embodiment, a system trains a first neural network to generate anomaly scores for printheads using an unsupervised learning algorithm based on first training samples of conforming printhead data from a pool of conforming printheads. The system generates a training dataset for a recurrent second neural network by identifying training printhead data for a pool of training printheads, inputting second training samples of the training printhead data into the first neural network to generate training anomaly scores for the training printheads over a plurality of time units, and formatting third training samples for the training printheads. The system trains the recurrent second neural network to generate scaled anomaly scores for printheads using a supervised learning algorithm based on the second training dataset.

公开(公告)号：US11310379B1

公开(公告)日：2022-04-19

申请号：US17195110

申请日：2021-03-08

申请人： Nathan Young ,  Ziling Zhang ,  Kara Larsen ,  Scott R. Johnson

发明人： Nathan Young ,  Ziling Zhang ,  Kara Larsen ,  Scott R. Johnson

IPC分类号： H04N1/00 ,  B41J2/045 ,  G06F3/12 ,  H04N1/60

摘要： Systems and methods are provided for reviewing printed jobs. On embodiment is a system comprising a print review device. The print review device includes a memory that stores an image of a test pattern printed by printheads of a printer, and a controller that generates a Graphical User Interface (GUI), for presentation at a display, depicting states of the printheads based on the image, receives input from a user selecting one of the printheads, correlates the printhead with a portion of the image, and presents the portion of the image for review at the GUI. The controller also identifies locations on the portion that are correlated with nozzles of the printhead, and selectively highlights the locations based on state information for the nozzles.