-
公开(公告)号：US12131579B2
公开(公告)日：2024-10-29
申请号：US17761596
申请日：2021-03-22
Applicant: RAKUTEN GROUP, INC.
Inventor： Yeongnam Chae , Bjorn Stenger
CPC classification number: G06V40/162 , G06V10/56 , G06V40/168
Abstract: An information processing device extracts, from an image taken by an imaging device, a human area in which it is determined that a human is present, acquires a representative value of first feature values, the first feature values being calculated by inputting, to a conversion function, each color of pixels included in a part of the human area, corrects, based on the representative value, a skin range indicating that a color indicated by a feature value acquired with the conversion function is a color of human skin, and determines whether a human is present in a part of the image acquired by the imaging device, based on whether a second feature value calculated with the conversion function for each of a plurality of pixels forming the part of the image is within the corrected skin range.
-
公开(公告)号：US11557108B2
公开(公告)日：2023-01-17
申请号：US16649776
申请日：2019-04-10
Applicant: Rakuten Group, Inc.
Inventor： Yeongnam Chae
IPC: G06K9/62 , G06V10/44 , G06V30/18 , G06V30/184 , G06V30/19 , G06V30/414 , G06T7/60 , G06V30/10
Abstract: An object is to provide a polygon detection device, a polygon detection method, and a polygon detection program to accurately detect a polygon resembling a reference polygon from an image.
The polygon detection device acquires a ratio among lengths of sides of a reference polygon included in an appearance of a predetermined object. The polygon detection device acquires a photographic image of the predetermined object. The polygon detection device detects line segments from the acquired photographic image. The polygon detection device forms at least one polygon based on the detected line segments. The polygon detection device identifies, from the formed polygon, a polygon corresponding to the reference polygon based on a degree of similarity between a ratio among lengths of sides of the formed polygon and the acquired ratio among the lengths of sides of the reference polygon, among from the formed polygon.-
公开(公告)号：US11314986B2
公开(公告)日：2022-04-26
申请号：US16635578
申请日：2019-05-31
Applicant: Rakuten Group, Inc.
Inventor： Yeongnam Chae , Kobagapu Bhaskar Rao
Abstract: For each of a plurality of images, a learning device acquires first training data including an image, a class of each of one or more objects shown in the image, and the number of objects, from a storage. The learning device trains a feature extraction part, a class estimation part, and an object number estimation part using the first training data. For each of images of which the number is smaller than the plurality of images, the learning device acquires second training data including an image and coordinates of each of one or more objects in the image, from the storage. The learning device causes the trained feature extraction part to output a feature map of the image included in the second training data, and trains a coordinate estimation part using the feature map and the coordinates included in the second training data.
-
4.发明授权公开(公告)号：US12067708B2
公开(公告)日：2024-08-20
申请号：US17419285
申请日：2020-09-08
Applicant: RAKUTEN GROUP, INC.
Inventor： Yeongnam Chae , Preetham Prakasha
CPC classification number: G06T7/0006 , G06N3/045 , G06V10/774 , G06V10/82 , G06N3/08 , G06T2207/20081 , G06T2207/20084
Abstract: To easily and correctly determine substantial identity of a plurality of images in each of which an object is placed, provided is an image judgement method including steps of obtaining first object data from a first image with a use of an R-CNN 12, which is a first machine learning model, where the first object data indicates an attribute and a layout of an object in the first image, obtaining second object data from a second image with a use of the R-CNN 12, where the second object data indicates an attribute and a layout of an object in the second image, and determining substantial identity of the first image and the second image based on the first object data and the second object data with a use of a CNN, which is a second machine learning model.
-
公开(公告)号：US11798134B2
公开(公告)日：2023-10-24
申请号：US16470309
申请日：2017-06-05
Applicant: Rakuten Group, Inc.
Inventor： Yeongnam Chae , Jiu Xu
Abstract: An image processing device according to one embodiment includes an acquisition unit, a generation unit, a calculation unit, and an estimation unit. The acquisition unit acquires an input image. The generation unit generates a plurality of comparison images by superimposing each of a plurality of noises with different densities from each other on a target region being at least part of the input image. The calculation unit calculates, for each of the plurality of comparison images, the degradation level of the comparison image with respect to the input image. The estimation unit estimates the noise level of the input image based on a plurality of calculated degradation levels.
-
Patent Agency Ranking
公开(公告)号：US12087067B2
公开(公告)日：2024-09-10
申请号：US17697954
申请日：2022-03-18
Applicant: RAKUTEN GROUP, INC.
Inventor： Yeongnam Chae , Preetham Prakasha
IPC: G06V30/148 , G06V30/146 , G06V30/18 , G06V30/19 , G06V30/242
CPC classification number: G06V30/153 , G06V30/1478 , G06V30/18105 , G06V30/242 , G06V30/18095 , G06V30/19107
Abstract: The information processing device obtains a character string image which includes a plurality of characters, and which includes the characters arranged in an arrangement direction, obtains a probability image representing a probability of an existence of a character in each of the pixel included in the character string image, obtains a plurality of character regions in which the characters are estimated to respectively exist in the character string image based on the probability image, obtains an additional character region which is located in the character string image, and which does not overlap the plurality of character regions based on a determination result on whether or not a pixel of a non-background color exists in a direction perpendicular to the arrangement direction at every position in the arrangement direction in the character string image, and recognizes the plurality of characters from the character regions and the additional character region.
-
公开(公告)号：US11971969B2
公开(公告)日：2024-04-30
申请号：US17419296
申请日：2020-09-17
Applicant: RAKUTEN GROUP, INC.
Inventor： Yeongnam Chae
CPC classification number: G06F21/32 , G06F21/316 , G06F21/35 , G06F21/36 , H04L9/32 , H04L9/3231 , G06F2221/2111
Abstract: An authentication system includes at least one processor configured to register user information on a user who is to visit a predetermined location, and scheduled time information on scheduled time at which the user is to visit the predetermined location, in association with each other in a storage, execute, when someone visits the predetermined location, authentication based on visitor information on the someone, the user information, visit time information on time at which the someone visits the predetermined location, and the scheduled time information.
-
公开(公告)号：US11928199B2
公开(公告)日：2024-03-12
申请号：US17418855
申请日：2019-12-27
Applicant: RAKUTEN GROUP, INC.
Inventor： Yeongnam Chae
IPC: G06F21/32
CPC classification number: G06F21/32
Abstract: An authentication system, including at least one processor configured to: perform authentication based on a first authentication method; record, when the authentication by the first authentication method is successful, an authenticated user and a location of the authenticated user in association with each other in a storage; perform authentication based on a second authentication method; and restrict successful authentication by the second authentication method when a user to be authenticated by the second authentication method and a location of the user to be authenticated are not associated with each other in the storage.
-
公开(公告)号：US11482028B2
公开(公告)日：2022-10-25
申请号：US17357408
申请日：2021-06-24
Applicant: Rakuten Group, Inc.
Inventor： Yeongnam Chae
Abstract: A transformed image generation unit 32 generates a transformed image by transforming an oblique image. A target region specifying unit 36 specifies a target region indicating the target in the front image based on a feature extracted from a typical portion of a document written on a target in a sample image and a feature extracted from at least a part of the front image. A verification unit 38 determines whether a target shown in the oblique image is the same as a target shown in the front image by verifying the target region in the front image and a region in the transformed image associated with the target region.
-
公开(公告)号：US12141938B2
公开(公告)日：2024-11-12
申请号：US17055999
申请日：2018-07-06
Applicant: RAKUTEN GROUP, INC.
Inventor： Yeongnam Chae
IPC: G06K9/34 , G06T3/18 , G06V10/24 , G06V10/44 , G06V30/14 , G06V30/146 , G06V30/18 , G06V30/414 , G06V30/418 , G06V30/10 , G06V30/16
Abstract: To speed up image processing, an obtaining means of an image processing system obtains a captured image of a document that includes a fixed part and an un-fixed part, where the document is captured by an image reader or an image capture device. A first shaping means shapes the captured image based on a feature of the document in a sample image and a feature of the document in the captured image so as to obtain a first shaped image. A detecting means detects a feature part of the fixed part from the first shaped image. A second shaping means shapes the first shaped image such that a position of the feature part detected by the detecting means is aligned with a predetermined position so as to obtain a second shaped image.
-
-
-
-
-
-
-
-
-
Search Results
22
records
(took 0.047 seconds)
