-
21.发明申请公开(公告)号：US20190065817A1
公开(公告)日：2019-02-28
申请号：US15690037
申请日：2017-08-29
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Maral Mesmakhosroshahi , Shubham Agarwal , Yongmian Zhang
Abstract: An artificial neural network system implemented on a computer for cell segmentation and classification of biological images. It includes a deep convolutional neural network as a feature extraction network, a first branch network connected to the feature extraction network to perform cell segmentation, and a second branch network connected to the feature extraction network to perform cell classification using the cell segmentation map generated by the first branch network. The feature extraction network is a modified VGG network where each convolutional layer uses multiple kernels of different sizes. The second branch network takes feature maps from two levels of the feature extraction network, and has multiple fully connected layers to independently process multiple cropped patches of the feature maps, the cropped patches being located at a centered and multiple shifted positions relative to the cell being classified; a voting method is used to determine the final cell classification.
-
22.发明授权公开(公告)号：US10201306B2
公开(公告)日：2019-02-12
申请号：US15251968
申请日：2016-08-30
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Wei Ming
IPC: H04N13/257 , G06T7/00 , A61B5/00 , H04N13/204 , A61B5/103 , G06F17/30 , G06K9/62 , G16H50/00
Abstract: A wound image capture method that uses self color compensation to improve color consistency of the captured image and reliability of color-based wound detection. The method uses the skin tone of parts of the patient's own body for color calibration and compensation. In a data registration process, multiple parts of a new patient's body are imaged as baseline images and color data of the baseline images are registered in the system as reference color data. During subsequent wound image capture and wound assessment process, the same parts of the patient's body are imaged again as baseline images, and the wound and its surrounding areas are also imaged. Color data of the newly capture baseline images are compared to the registered reference color data and used to perform color compensation for the wound image.
-
公开(公告)号：US10180425B2
公开(公告)日：2019-01-15
申请号：US15504004
申请日：2015-09-01
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Noriaki Yamamoto
IPC: G01N33/542 , G01N21/64 , C12Q1/6804 , G01N33/543
Abstract: A DNA ligand capable of structural changes upon binding to a target is used as a molecular switch with a SPFS (surface plasmon field-enhanced fluorescence spectroscopy) biosensor to realize one-step SPFS biosensing with rapid turnaround time. The SPFS biosensor has a thin metal film on a prism; when a light of a certain wavelength irradiates on the prism at a certain angle, a strong electrical field is generated at the surface of the metal film. The DNA is immobilized on the metal film surface with its free terminal modified with a fluorescent marker. Without the target, the DNA is folded and the fluorescent marker is located in the region of metal quenching near the metal surface. Upon binding to the target, the DNA is extended and the fluorescent marker is located in the region of enhanced electric field near the metal surface and emits a strong fluorescent signal.
-
公开(公告)号：US20180373999A1
公开(公告)日：2018-12-27
申请号：US15633288
申请日：2017-06-26
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Ting XU
Abstract: A method for training a deep neural network (DNN) to perform a specified task with respect to images captured by a target camera, including: using an image captured by the target camera as a style target image, training a style transformer network to perform a style transformation that transforms any photorealistic input image into a transformed image that has contents of the input image, maintains photorealistic quality of the input image, and has a style that matches a style of the style target image; using the trained style transformer network to transform training image of an original training dataset into transformed training images; labeling the transformed training images with the training labels of the corresponding training image of the original training dataset, to form an augmented training dataset; and using the augmented training dataset to train the DNN to perform the specified task.
-
公开(公告)号：US20180373967A1
公开(公告)日：2018-12-27
申请号：US15633255
申请日：2017-06-26
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Kazuto Yamamoto
Abstract: A color test pattern comprising color patches can be printed together with an image (text and/or a pictures, for example) of a print job. After printing, reflections, known as flare, from the image may adversely affect measurements taken of the color patches. To help reduce the effects of flare, a determination is made prior to printing as to the layout of the color patches. The determination involves comparing the color properties of the color patches with those of the image.
-
Patent Agency Ranking
公开(公告)号：US20180285637A1
公开(公告)日：2018-10-04
申请号：US15474512
申请日：2017-03-30
Applicant: Konica Minolta Laboratory U.S.A., Inc.
Inventor： Stuart Guarnieri , Jason James Grams
CPC classification number: G06K9/00416 , G06K9/00429 , G06K9/00442 , G06K9/222 , G06K9/344 , G06K2209/01
Abstract: A method for character recognition. The method includes: obtaining a plurality of character segments extracted from an image; determining a first character bounding box including a first set of the plurality of character segments and a second character bounding box including a second set of the plurality of character segments; determining an ordering for the first set based on a plurality of texture properties for the first set; determining a plurality of directions of the first set based on a plurality of brush widths and a plurality of intensities for the first set; and executing character recognition for the first character bounding box by sending the first set, the plurality of directions for the first set, and the ordering for the first set to an intelligent character recognition (ICR) engine.
-
公开(公告)号：US20180285031A1
公开(公告)日：2018-10-04
申请号：US15475872
申请日：2017-03-31
Applicant: Konica Minolta Laboratory U.S.A., Inc.
Inventor： Sanjay Dalvi , Hidetaka Yoshida , Ryoichi Yokoohji
IPC: G06F3/12
CPC classification number: G06F3/127 , G06F3/1206 , G06F3/1288
Abstract: A method for creating local hot folders is provided. The method includes: receiving, by a print server that includes a first network hot folder and a second network hot folder, a request to create at least one local hot folder on a user computing device; determining, by the print server, that the request corresponds to the first network hot folder; and transmitting, by the print server to the user computing device, a first instruction set comprising an instruction to create a first local hot folder that implements a first transfer protocol. The first network hot folder executes a predetermined process and requires the first transfer protocol in response to executing the predetermined process, and the second network hot folder executes another process and requires a second transfer protocol.
-
28.发明授权公开(公告)号：US10089766B2
公开(公告)日：2018-10-02
申请号：US15128224
申请日：2015-03-26
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： John Randall Christ , Po-Chieh Hung
Abstract: A method, a computer program product, and a system are disclosed for stitching aerial data using information from at least one previous image. The method includes capturing a plurality of images of the landscape; obtaining, image metadata for each of the captured images; generating, for each of the captured images, a set of transformed images based on the image metadata, comprises: setting a variable for each of the parameters; preparing a plurality of sets of transformed image metadata by applying the variables to the parameters; and preparing the set of transformed images from the captured image based on the plurality of sets of transformed image metadata, respectively; identifying, for each set of transformed images, one of the transformed images by calculating quality of fit to the top level image for each of the transformed images; and assembling a new aerial image based on the plurality of the identified transformed images.
-
公开(公告)号：US10089556B1
公开(公告)日：2018-10-02
申请号：US15620492
申请日：2017-06-12
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Ting Xu
Abstract: An artificial neural network for analyzing input data, the input data being a 3D tensor having D channels, such as D frames of a video snippet, to recognize an action therein, including: D spatial transformer modules, each generating first and second spatial transformations and corresponding first and second attention windows using only one of the D channels, and transforming first and second regions of each of the D channels corresponding to the first and second attention windows to generate first and second patch sequences; first and second CNNs, respectively processing a concatenation of the D first patch sequences and a concatenation of the D second patch sequences; and a classification network receiving a concatenation of the outputs of the first and second CNNs and the D sets of transformation parameters of the first transformation outputted by the D spatial transformer modules, to generate a predicted action class.
-
30.发明申请公开(公告)号：US20180191921A1
公开(公告)日：2018-07-05
申请号：US15393917
申请日：2016-12-29
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Maria PEREZ
CPC classification number: H04N1/32117 , H04L69/22 , H04N1/00307 , H04N1/00915 , H04N1/00925 , H04N1/32021 , H04N1/33384 , H04N2201/0094 , H04N2201/3223 , H04N2201/3253 , H04W4/023
Abstract: A method, a computer readable medium, and a multi-function peripheral are disclosed, which use IPv6 packet extensions for execution of a job request based on proximity. The method including sending a job to be processed by a multi-function peripheral with an IPv6 Destination Options extension header from a client device to the multi-function peripheral, the IPv6 Destination Options extension header containing a physical location of the client device; receiving the job with the IPv6 Destination Options extension header containing the physical location of the client device on the multi-function peripheral; examining the IPv6 Destination Options extension header containing the physical location of the client device on the multi-function peripheral; and executing the job if the physical location of the client device is within a defined proximity to the multi-function peripheral.
-
-
-
-
-
-
-
-
-
Search Results
533
records
(took 0.029 seconds)
