公开(公告)号：US20240153108A1

公开(公告)日：2024-05-09

申请号：US18547465

申请日：2021-12-20

Applicant: OMRON Corporation

Inventor： Tatsuki SAWADA

IPC: G06T7/246 ,  G06T7/73 ,  G06T7/90

CPC classification number: G06T7/248 ,  G06T7/74 ,  G06T7/90 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/30196

Abstract: An image processing apparatus includes a tracking target setter that sets a tracking target in a first frame of a video, a first feature tracker that tracks the tracking target in a second frame based on a first feature of the tracking target set in the first frame, a second feature tracker that tracks the tracking target in the second frame based on a second feature of the tracking target set in the first frame, a tracking manager that mixes a tracking result obtained by the first feature tracker with a tracking result obtained by the second feature tracker at a predetermined mixing ratio, and an output unit that outputs a detection position of the tracking target in the second frame based on a mixing result obtained by the tracking manager.

公开(公告)号：US20240144444A1

公开(公告)日：2024-05-02

申请号：US18376902

申请日：2023-10-05

Applicant: GWANGJU INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Bochang MOON ,  Geunwoo OH ,  Jonghee BACK

IPC: G06T5/00 ,  G06T5/50 ,  G06T7/90

CPC classification number: G06T5/002 ,  G06T5/50 ,  G06T7/90 ,  G06T2207/20084 ,  G06T2207/20221

Abstract: The present disclosure relates to an apparatus and method for improving no-flash image quality by removing noise included in a no-flash image using a flash image. An apparatus for improving no-flash image quality using a flash image according to an example embodiment of the present disclosure includes an artificial neural network module which is trained by receiving an image pair of a flash image and a no-flash image and configured to output a convolutional kernel kc and a composite weight wci from a local flash image patch and a no-flash image patch, a convolution unit configured to convolve the flash image patch and the convolutional kernel to generate a consistent flash image patch, and a combining module configured to combine the no-flash image patch and the consistent flash image patch using the composite weight wci to produce a denoised image.

公开(公告)号：US11972594B2

公开(公告)日：2024-04-30

申请号：US17673484

申请日：2022-02-16

Applicant: SHARP KABUSHIKI KAISHA

Inventor： Teruhiko Matsuoka ,  Akihito Yoshida ,  Masahiko Takashima

IPC: G06T7/90

CPC classification number: G06T7/90 ,  G06T2207/10024 ,  G06T2207/30176

Abstract: A multifunction peripheral includes a color number conversion determiner. The color number conversion determiner determines whether it is appropriate to perform either an index color process or a full-color process based on a color distribution degree, which is a distribution degree of pixel values of the respective sets of pixel data included in input image data, a photograph area ratio, which is a ratio of photograph area pixel data forming a photograph area to the pixel data, and a color uniformity area ratio, which is a ratio of white base area pixel data forming a white base area to the pixel data.

公开(公告)号：US11972543B2

公开(公告)日：2024-04-30

申请号：US17306904

申请日：2021-05-03

Applicant: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.

Inventor： Zibo Meng ,  Chiuman Ho

IPC: G06T5/00 ,  G06T5/20 ,  G06T7/90 ,  G06T11/00

CPC classification number: G06T5/008 ,  G06T5/007 ,  G06T5/20 ,  G06T7/90 ,  G06T11/001

Abstract: A method includes receiving and processing a first image by an encoder-decoder network. The first image includes a first portion and a second portion located at different locations. The encoder-decoder network includes an encoder and a decoder. The encoder is configured to output at least one feature map including global information and local information such that whether a color consistency relationship between the first portion and the second portion of the first image exists is encoded into the global information and the local information. The decoder is configured to output a second image generated from the at least one feature map, wherein a first portion of the second image corresponding to the first portion of the first image and a second portion of the second image corresponding to the second portion of the first image are restored considering whether the color consistency relationship exists.

公开(公告)号：US11971329B2

公开(公告)日：2024-04-30

申请号：US17538717

申请日：2021-11-30

Applicant: General Electric Company

Inventor： Brandon S. Good ,  Bijan Chitsaz ,  Guanghua Wang ,  Bernard P. Bewlay ,  Gyeong Woo Cheon ,  Alberto Santamaria-Pang

IPC: G01M3/38 ,  F02C7/00 ,  G01J5/00 ,  G06T7/00 ,  G06T7/90 ,  G08B21/18 ,  H04N23/90

CPC classification number: G01M3/38 ,  F02C7/00 ,  G01J5/0003 ,  G06T7/0002 ,  G06T7/90 ,  G08B21/182 ,  H04N23/90 ,  F05D2260/80 ,  G01J2005/0077 ,  G06T2207/10048 ,  G06T2207/20084

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to autonomously detect thermal anomalies. Disclosed examples include an example apparatus to detect engine anomalies comprising: at least one memory; instructions in the apparatus; and processor circuitry to execute the instructions to: control a plurality of infrared cameras to capture a baseline image set, the baseline image set including at least two thermal images; generate emissivity data based on the baseline image set; provide the baseline image set and the emissivity data to an artificial intelligence model, the artificial intelligence model to generate a reconstructed image set; determine a difference between the baseline image set and the reconstructed image set; and in response to the difference exceeding a threshold, generate an alert indicating detection of an engine anomaly.

公开(公告)号：US11969212B2

公开(公告)日：2024-04-30

申请号：US18175925

申请日：2023-02-28

Applicant: Ohio State Innovation Foundation

Inventor： Melissa Bailey ,  Charles Bosworth

IPC: G06T7/00 ,  A61B3/00 ,  A61B3/117 ,  G06T7/90

CPC classification number: A61B3/1176 ,  A61B3/0025 ,  G06T7/0016 ,  G06T7/90 ,  G06T2207/30041

Abstract: Disclosed herein are methods and apparatus for making a determination about a cataract in an eye in ambient lighting conditions.

公开(公告)号：US20240135588A1

公开(公告)日：2024-04-25

申请号：US18548267

申请日：2022-03-01

Applicant: PPG Industries Ohio, Inc.

Inventor： A'Lisa M. Krawciw ,  Anthony J. Foderaro ,  Alison M. Norris

IPC: G06T7/90 ,  G06V10/56 ,  G06V10/74

CPC classification number: G06T7/90 ,  G06V10/56 ,  G06V10/761 ,  G06T2207/10024

Abstract: A computer system for comparing complex coating mixtures with sparkle color can receive at least one image of a target coating. The computer system calculates a sparkle color distribution of the at least one image of the target coating, wherein the sparkle color distribution represents a relative number of sparkle points of one color compared to a number of sparkle points of one or more other colors in a measured area. Further, the computer system searches a database for a plurality of reference coatings with sparkle color distributions that match the sparkle color distribution of the target coating, wherein each reference coating in the plurality has a different sparkle color distribution. The computer system calculates a degree to which the plurality of reference coatings matches the target coating based on sparkle color distribution. Finally, the computer system identifies a closest matching reference coating from the plurality of reference coatings.

公开(公告)号：US20240135587A1

公开(公告)日：2024-04-25

申请号：US18134328

申请日：2023-04-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sung Kwang CHO ,  Geonwoo Kim ,  Yang Ho Cho ,  Dong Kyung Nam

IPC: G06T7/90

CPC classification number: G06T7/90 ,  G06T2207/10024 ,  G06T2207/20081

Abstract: A method of learning a parameter of a sensor filter and an apparatus for performing the method are provided. The learning method may include performing a simulation on a target image for each spectrum of a sensor filter, obtaining an output value by inputting the simulated image to a vision model for a vision task, and learning a parameter of the sensor filter based on a loss between a label of the vision model and the output value of the vision model.

公开(公告)号：US11967094B2

公开(公告)日：2024-04-23

申请号：US17350803

申请日：2021-06-17

Applicant: NIKON CORPORATION

Inventor： Satoshi Hasegawa ,  Yoshihiro Nakagawa ,  Masashi Hashimoto

IPC: G06T7/41 ,  G06T7/529 ,  G06T7/70 ,  G06T7/90

CPC classification number: G06T7/41 ,  G06T7/529 ,  G06T7/70 ,  G06T7/90

Abstract: To reduce the feel of incongruity in a model, provided is a detection device comprising: a texture detector that detects texture information of a target object from a first position; a position detector that detects depth information to each point in the target object from a second position different from the first position; a region detector that detects a data deficient region in which the depth information has been acquired but the texture information has not been acquired, on the basis of a detection result of the texture detector and a detection result of the position detector; and an adder that adds specific texture information to the data deficient region.

公开(公告)号：US11967071B2

公开(公告)日：2024-04-23

申请号：US17620780

申请日：2019-11-11

Applicant: PING AN TECHNOLOGY (SHENZHEN) CO., LTD.

Inventor： Rui Wang ,  Junhuan Zhao ,  Lilong Wang ,  Yuanzhi Yuan ,  Chuanfeng Lv

IPC: G06T7/00 ,  G06N3/045 ,  G06T7/90 ,  G06V10/82

CPC classification number: G06T7/0012 ,  G06N3/045 ,  G06T7/90 ,  G06V10/82 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30041

Abstract: The present disclosure provides a method, device, computer apparatus, and storage medium for training recognition model and recognizing fundus features. The method includes: obtaining a color fundus image sample associated with a label value, inputting the color fundus image sample into a preset recognition model containing initial parameters; extracting a red channel image; inputting the red channel image into the first convolutional neural network to obtain a first recognition result and a feature image of the red channel image; combining the color fundus image sample with the feature image to generate a combined image, and inputting the combined image into the second convolutional neural network to obtain a second recognition result; obtaining a total loss value through a loss function, and when the total loss value is less than or equal to a preset loss threshold, ending the training of the preset recognition model.