-
公开(公告)号：US20220092355A1
公开(公告)日：2022-03-24
申请号：US17027351
申请日：2020-09-21
Applicant: KYOCERA DOCUMENT SOLUTIONS INC.
Inventor： Dongpei Su
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 can provide instances of the first image to a plurality of image filtering modules and determine respective filtered representations of the first image using the plurality of image filtering modules. The computing device can indirectly train an adaptor ANN by applying the adaptor ANN on the respective filtered representations to produce an adapted representation; determining, using a trained colorization ANN, a colorized image from the adapted representation; and updating weights of the adaptor ANN based on a loss function that comprises a difference between the colorized image and the second image of the image pair.
-
12.发明申请公开(公告)号：US20200320289A1
公开(公告)日：2020-10-08
申请号：US16378470
申请日：2019-04-08
Applicant: KYOCERA Document Solutions Inc.
Inventor： Dongpei Su
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.
-
13.发明申请公开(公告)号：US20200210122A1
公开(公告)日：2020-07-02
申请号：US16237666
申请日：2018-12-31
Applicant: Kyocera Document Solutions Inc.
Inventor： Masayoshi Nakamura , Dongpei Su
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.
-
公开(公告)号：US10649789B2
公开(公告)日：2020-05-12
申请号：US16043073
申请日：2018-07-23
Applicant: KYOCERA Document Solutions Inc.
Inventor： Dongpei Su , Thien-Phuc Nguyen Do , Alex Horvath , Kenneth A. Schmidt , Masayoshi Nakamura
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.
-
公开(公告)号：US10540811B2
公开(公告)日：2020-01-21
申请号：US16000852
申请日：2018-06-05
Applicant: KYOCERA Document Solutions Inc.
Inventor： Dongpei Su , Christa Neil , Yuzuru Naganuma , Kendrick Wong , Donald Han , Kenneth A. Schmidt
IPC: G06T15/50
Abstract: Methods and apparatus for radial gradient rendering are provided. A graphics computing device can include a radial gradient module (RGM), which can include circuitry for radial gradient rendering. The RGM can receive one or more parameters associated with rendering at least a portion of an image utilizing radial gradient rendering. The RGM can map one or more input coordinates of the image to one or more source domain coordinates. The RGM can determine a t-value for the source domain coordinates, the t-value specifying an ellipse in the source domain whose edge includes the source domain coordinates. The RGM can determine a color value for the input coordinates based on the specified ellipse. The RGM can generate an output that is based on the color value.
-
Patent Agency Ranking
公开(公告)号：US20190371048A1
公开(公告)日：2019-12-05
申请号：US16000852
申请日：2018-06-05
Applicant: KYOCERA Document Solutions Inc.
Inventor： Dongpei Su , Christa Neil , Yuzuru Naganuma , Kendrick Wong , Donald Han , Kenneth A. Schmidt
IPC: G06T15/50
Abstract: Methods and apparatus for radial gradient rendering are provided. A graphics computing device can include a radial gradient module (RGM), which can include circuitry for radial gradient rendering. The RGM can receive one or more parameters associated with rendering at least a portion of an image utilizing radial gradient rendering. The RGM can map one or more input coordinates of the image to one or more source domain coordinates. The RGM can determine a t-value for the source domain coordinates, the t-value specifying an ellipse in the source domain whose edge includes the source domain coordinates. The RGM can determine a color value for the input coordinates based on the specified ellipse. The RGM can generate an output that is based on the color value.
-
公开(公告)号：US09538044B2
公开(公告)日：2017-01-03
申请号：US14664335
申请日：2015-03-20
Applicant: KYOCERA Document Solutions Inc.
Inventor： Dongpei Su , Kenneth A. Schmidt , Thien-Phuc Nguyen Do , Sheng Li
IPC: H03M7/40 , H04N1/411 , H04N19/129 , H04N19/124 , H04N19/176 , H04N19/91
CPC classification number: H04N1/4115 , H04N19/124 , H04N19/129 , H04N19/176 , H04N19/91 , H04N2201/0094
Abstract: A computer-implemented method comprises receiving a data stream that includes a series of code words that encodes a respective series of pixel data according to a first entropy coding lookup table, and processing the data stream to determine if there is a match between a first code word and a consecutive second code word, and a code word entry in a second entropy coding lookup table. The method also includes, if there is a match, decoding the first code word and the second code word using the second entropy coding lookup table. Further, the method includes, if there is not a match, decoding the first code word using the first entropy coding lookup table.
Abstract translation: 计算机实现的方法包括：接收包括根据第一熵编码查找表对各个像素数据序列进行编码的一系列码字的数据流，并处理数据流以确定第一代码 字和连续的第二码字，以及第二熵编码查找表中的码字条目。 该方法还包括如果存在匹配，则使用第二熵编码查找表对第一码字和第二码字进行解码。 此外，该方法包括如果不匹配，则使用第一熵编码查找表对第一码字进行解码。
-
公开(公告)号：US20160284042A1
公开(公告)日：2016-09-29
申请号：US14671332
申请日：2015-03-27
Applicant: KYOCERA Document Solutions Inc.
Inventor： Dongpei Su , Masayoshi Nakamura , Christa Neil , Kenneth A. Schmidt
IPC: G06T1/20
CPC classification number: G06T1/20 , G06K15/1805
Abstract: A system and method for implementing a real-time state machine with a microcontroller is disclosed. The method includes using a two-stage process, including a configuration stage and a run-time stage, for processing objects for a printing device. The configuration stage is executed prior to the run-time stage, which operates in real-time. During the configuration stage, the system predetermines a state transition list, devices that need to be monitored, devices that need to be controlled, and other variables used during the run-time stage. Once the configuration stage is complete, the system executes the run-time stage in real-time to complete processing of an object for a printing device. By pre-calculating items during the configuration stage, the system reduces the execution time of the run-time stage in real-time. As a result, the performance of the microcontroller in real-time is enhanced.
Abstract translation: 公开了一种用于实现具有微控制器的实时状态机的系统和方法。 该方法包括使用包括配置阶段和运行时阶段的两阶段过程来处理打印设备的对象。 配置阶段在运行时间段之前执行，运行时阶段是实时运行的。 在配置阶段，系统预先确定状态转换列表，需要监视的设备，需要控制的设备以及在运行时阶段使用的其他变量。 配置阶段完成后，系统实时执行运行时阶段，完成打印设备对象的处理。 通过在配置阶段预先计算项目，系统实时减少运行时阶段的执行时间。 结果，实时地提高了微控制器的性能。
-
19.发明授权公开(公告)号：US11989916B2
公开(公告)日：2024-05-21
申请号：US17498269
申请日：2021-10-11
Applicant: KYOCERA Document Solutions, Inc.
Inventor： Kilho Shin , Dongpei Su
CPC classification number: G06T7/90 , G06N20/00 , G06T11/001 , G06T2207/20076 , G06T2207/20081 , G06T2207/20084
Abstract: Embodiments provide an automated approach for generating unbiased synthesized image-label pairs for colorization training of retro photographs. Modern grayscale images with corresponding color images are translated to images with the characteristics of retro photographs, thereby producing training data that pairs images with the characteristics of retro paragraphs with corresponding color images. This training data can then be employed to train a deep learning model to colorize retro photographs more effectively.
-
公开(公告)号：US11909934B1
公开(公告)日：2024-02-20
申请号：US18055770
申请日：2022-11-15
Applicant: KYOCERA Document Solutions, Inc.
Inventor： Waqas Rasheed , Dongpei Su , Kilho Shin , Sheng Li
IPC: H04N1/00 , G06V30/413
CPC classification number: H04N1/00859 , G06V30/413
Abstract: A digital image processor includes a region proposal network configured to transform digital image inputs into region proposals and bounding box refinement logic configured to transform the region proposals by determining a first set of the region proposals exhibiting dense spacing, determining a second set of the region proposals exhibiting sparse spacing, executing a first transformation to merge at least some of the region proposals exhibiting dense spacing to generate refined region proposals, executing a second transformation to join at least some of the region proposals exhibiting sparse spacing to generate additional ones of the refined region proposals, and applying an expansion transformation to the refined region proposals.
-
-
-
-
-
-
-
-
-
Search Results
69
records
(took 0.027 seconds)
