公开(公告)号：US20240355093A1

公开(公告)日：2024-10-24

申请号：US18762464

申请日：2024-07-02

Applicant: KABUSHIKI KAISHA TOSHIBA

Inventor： Miyuki UCHIDA ,  Taisuke WASHITANI

IPC: G06V10/764 ,  G06T7/00 ,  G06V10/82

CPC classification number: G06V10/764 ,  G06T7/0008 ,  G06V10/82 ,  G06T2207/30164

Abstract: According to one embodiment, a determination device is configured to determine a suitability of a classification model. The classification model includes a neural network. The classification model is further configured to output a classification result according to an input of an image. The determination device is further configured to acquire intermediate data of an intermediate layer of the neural network when an input image is input to the classification model. The classification model is further configured to determine the suitability by using a plurality of sets of the intermediate data and a plurality of sets of reference data. The plurality of sets of reference data being prepared beforehand.

公开(公告)号：US12118710B2

公开(公告)日：2024-10-15

申请号：US17506718

申请日：2021-10-21

Applicant: UNIVERSITAT D'ALACANT/UNIVERSIDAD DE ALICANTE

Inventor： Guillermo Grindlay Lledó ,  Luis Gras Garcia ,  Juan Mora Pastor ,  Marta Navas García

IPC: G06T7/90 ,  G06T7/00 ,  G06T7/10

CPC classification number: G06T7/0008 ,  G06T7/10 ,  G06T7/90 ,  G06T2207/10064 ,  G06T2207/30128

Abstract: Procedure for the detection of bitter almonds based on the processing of digital images, and a system and device associated therewith. Detection procedure and system for the automated classification of sweet and bitter almonds based on the processing of digital images. The fluorescence of the cyanogenic compounds naturally present in almonds generates a clear difference in colour between sweet and bitter almonds which subsequently is analysed and classified by means of a computer program. The invention also includes the device, either portable or automatic, for carrying out the classification of bitter or sweet almonds. This device will be necessary during the goods reception process and in the validation/verification of the quality of the finished product, prior to the loading and transport process.

公开(公告)号：US20240338810A1

公开(公告)日：2024-10-10

申请号：US18626140

申请日：2024-04-03

Applicant: CANON KABUSHIKI KAISHA

Inventor： KENJI MORITA ,  KENJI KUROKI

IPC: G06T7/00 ,  H04N1/00

CPC classification number: G06T7/0008 ,  H04N1/00045 ,  H04N1/00082 ,  G06T2207/30144

Abstract: An image forming system comprising an image forming apparatus forms an image, a reading apparatus reads the image, an inspection unit inspects the image read by the reading apparatus to detect defect on the image, and a controller configured to control, in a case where a first type of defect is detected by the inspection unit during formation of a plurality of images by the image forming apparatus, the image forming apparatus to stop the formation, and execute an adjustment operation for adjusting a quality of an image to be formed by the image forming apparatus, and control, in a case where a second type of defect is detected by the inspection unit during the formation, the image forming apparatus to continue the formation, wherein the second type of defect is different from the first type of defect.

公开(公告)号：US20240335855A1

公开(公告)日：2024-10-10

申请号：US18747315

申请日：2024-06-18

Applicant: Foreman Technologies Inc., dba PaintJet

Inventor： Nick Hegeman ,  Sonia Chacko ,  Tom Jose ,  Kevin Ozbirn ,  Vineeth Budamkayala ,  Piyush Warhade ,  Matt Lopez

IPC: B05D1/36 ,  B05D7/00 ,  G06T7/00 ,  G06T7/11 ,  G06T11/00

CPC classification number: B05D1/36 ,  B05D7/52 ,  G06T7/0004 ,  G06T7/0008 ,  G06T7/11 ,  G06T11/00 ,  G06T2207/20212 ,  G06T2207/20221

Abstract: One variation of a method includes: navigating a set of spray nozzles across a first segment of the target surface according to a toolpath; applying paint onto the first segment of the target surface via the set of spray nozzles; accessing a first image depicting paint applied onto the first segment of the target surface; navigating the set of spray nozzles across a second segment of the target surface according to the toolpath; applying paint onto the second segment of the target surface via the set of spray nozzles; accessing a second image depicting paint applied onto the second segment of the target surface; and aggregating the first image and the second image into a paint map representing application of paint onto the first segment and the second segment of the target surface.

公开(公告)号：US20240311997A1

公开(公告)日：2024-09-19

申请号：US18589658

申请日：2024-02-28

Applicant: Kioxia Corporation

Inventor： Shuhei IIJIMA ,  Osamu YAMANE ,  Youyang NG ,  Yuchieh LIN ,  Takuji OHASHI ,  Takeshi FUJIWARA

IPC: G06T7/00 ,  G06T5/50 ,  G06T7/194 ,  G06V10/44 ,  G06V10/764 ,  G06V20/70

CPC classification number: G06T7/0008 ,  G06T5/50 ,  G06T7/194 ,  G06V10/44 ,  G06V10/764 ,  G06V20/70 ,  G06T2207/20224 ,  G06T2207/30148

Abstract: A semiconductor image processing apparatus including a processing circuitry, the processing circuitry configured to identify a label corresponding to a feature amount included in an input image by using an identifier, learn a model for inferring the feature amount included in the input image and learns the identifier, and perform additional learning of the model based on the input image and the learned identifier.

公开(公告)号：US20240302662A1

公开(公告)日：2024-09-12

申请号：US18665675

申请日：2024-05-16

Applicant: Panasonic Intellectual Property Corporation of America

Inventor： Kenta MURAKAMI ,  Naomi TOMIYAMA ,  Satoshi MATSUI

IPC: G02B27/01 ,  G06T7/00 ,  G06T7/73 ,  G06T19/00 ,  G06V20/80 ,  G06V40/10

CPC classification number: G02B27/0172 ,  G06T7/0008 ,  G06T7/73 ,  G06T19/006 ,  G06V20/80 ,  G06V40/11 ,  G06T2207/10004

Abstract: The camera photographs a visual field of the user. The controller acquires an image captured by the camera, recognizes, through image recognition processing, a package that is a work target of the user and a hand of the user from the acquired image, determines whether or not the user is in a state of being about to carry a package based on a positional relationship between the recognized package and the recognized hand, and recognizes, through image recognition processing, a package ID from the acquired image in a case where it is determined that the user is in a state of being about to carry the package. The communication part receives delivery information regarding the package corresponding to the package ID from a delivery management server. The controller generates, based on the delivery information, alert information to be presented to the user, and outputs the generated alert information.

公开(公告)号：US20240289942A1

公开(公告)日：2024-08-29

申请号：US18436478

申请日：2024-02-08

Applicant: TOYOTA BOSHOKU KABUSHIKI KAISHA

Inventor： Yasunori SAKURAI ,  Hiroyuki SAIKI

IPC: G06T7/00 ,  B32B3/26 ,  B32B3/30 ,  B32B15/01 ,  B32B41/00 ,  G06T7/73 ,  G06V10/75 ,  G06V10/764 ,  G06V20/50

CPC classification number: G06T7/001 ,  B32B3/266 ,  B32B3/30 ,  B32B15/011 ,  B32B41/00 ,  G06T7/0008 ,  G06T7/74 ,  G06V10/751 ,  G06V10/764 ,  G06V20/50 ,  B32B2041/04 ,  B32B2311/30 ,  G06T2207/30136 ,  G06V2201/06

Abstract: A laminated block correctness determining method determines whether a laminated block to be laminated is a correct laminated block when manufacturing a laminated iron core by laminating laminated blocks. Orientation identification portions are respectively disposed on opposite end surfaces of each of the laminated blocks in an axial direction. The laminated block correctness determining method includes acquiring, with an imaging device, a captured image of the laminated block by capturing one end surface of the laminated block in the axial direction. The laminated block correctness determining method further includes determining whether the orientation of the laminated block is correct by comparing the orientation identification portion in a registered image with the orientation identification portion in the captured image.

公开(公告)号：US20240289941A1

公开(公告)日：2024-08-29

申请号：US17768612

申请日：2020-10-05

Applicant: NEC Corporation

Inventor： Yuka OSHIMA ,  Takuroh KASHIMA ,  Yusuke KOITABASHI ,  Atsushi MATSUDA

IPC: G06T7/00 ,  G06T7/62

CPC classification number: G06T7/0008 ,  G06T7/62 ,  G06T2207/30156 ,  G06T2207/30204

Abstract: A conversion equation calculation unit 81 calculates, based on a defect image with marker in which a marker of a predetermined size that can be recognized regardless of color of appearance of an object to be inspected and a defect of the object to be inspected are taken, a conversion equation from size of the defect image with marker to actual size. A defect type determination unit 82 determines, by using a model for detecting the defect of the object to be inspected from an image and determining a defect type, the defect type included in the defect image with marker. A defect measuring unit 83 measures defect size included in the defect image with marker by using the conversion equation. A defect content output unit 84 outputs the determined defect type and the measured defect size.

公开(公告)号：US12073552B2

公开(公告)日：2024-08-27

申请号：US17370966

申请日：2021-07-08

Applicant: Align Technology, Inc.

Inventor： Paren Indravadan Shah ,  Anatoliy Parpara ,  Andrey Cherkas ,  Alexey Kalinichenko

IPC: G06T7/00 ,  B29C64/386 ,  B33Y50/00 ,  G06K9/62 ,  G06T7/11 ,  G06T7/12 ,  G06T7/60 ,  G06T7/70 ,  G06V10/98 ,  G06V20/64 ,  H04N23/74

CPC classification number: G06T7/0008 ,  B29C64/386 ,  B33Y50/00 ,  G06T7/001 ,  G06T7/11 ,  G06T7/12 ,  G06T7/60 ,  G06T7/70 ,  G06V10/993 ,  G06V20/64 ,  H04N23/74 ,  G06T2207/10152 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20132 ,  G06T2207/30036 ,  G06T2207/30144 ,  G06T2207/30168

Abstract: Systems and methods for performing automated quality control for 3D printed molds for orthodontic aligners are described. A method includes generating a plurality of images of the 3D printed mold for the orthodontic aligner using one or more imaging devices, wherein each image of the plurality of images depicts a distinct region of the 3D printed mold for the orthodontic aligner; processing the plurality of images by a processing device to identify one or more types of manufacturing defects of the 3D printed mold for the orthodontic aligner, wherein for each type of manufacturing defect a probability that an image comprises a defect of that type of manufacturing defect is determined; and classifying, by the processing device, the 3D printed mold for the orthodontic aligner as defective based on identifying the one or more types of manufacturing defects.

公开(公告)号：US20240281957A1

公开(公告)日：2024-08-22

申请号：US18443593

申请日：2024-02-16

Applicant: SEIKO EPSON CORPORATION

Inventor： Ryotaro HAYASHI

IPC: G06T7/00 ,  G06T7/90 ,  H04N1/00 ,  H04N1/60

CPC classification number: G06T7/0008 ,  G06T7/90 ,  H04N1/00023 ,  H04N1/60 ,  G06T2207/10024 ,  G06T2207/30144

Abstract: An information processing device includes an obtainer configured to obtain color information of a spot color patch targeted for a color difference inspection and inspection result information indicating a result of the color difference inspection for the spot color patch, a determiner configured to determine, among colors included in image data, a color to be printed as the spot color patch based on the color information and the inspection result information, and a print controller configured to cause a printing device to print the image data and the spot color patch of the color determined by the determiner. The determiner is configured to change the number of colors to be printed as the spot color patch based on the inspection result information on the colors included in the image data.