-
公开(公告)号:US20240312173A1
公开(公告)日:2024-09-19
申请号:US18182536
申请日:2023-03-13
发明人: Jason PRIBBLE , Swapnil PATIL , Timothy TRAN
CPC分类号: G06V10/242 , G06V10/70 , G06V30/10 , G06V40/161 , G06V40/171
摘要: In some implementations, a device may receive an image of a document, the image depicting a reference feature associated with the document, the reference feature including at least one of: a face of a person, a machine-readable code, or a text field. The device may identify a rotational angle of the reference feature as depicted in the image based on comparing the reference feature as depicted in the image to one or more orientation parameters of the reference feature associated with a display orientation associated with the document. The device may rotate the image of the document by an angle to obtain an orientated image of the document, the angle being based on the rotational angle of the reference feature as depicted in the image. The device may provide the orientated image of the document for display.
-
公开(公告)号:US20240311966A1
公开(公告)日:2024-09-19
申请号:US18613100
申请日:2024-03-21
申请人: SoftEye, Inc.
发明人: Edwin Chongwoo Park , Te-Won Lee
CPC分类号: G06T3/4092 , G02B27/017 , G06F3/013 , G06V10/25 , G06V20/70 , G06V30/10 , G10L13/08 , G02B2027/0138 , G02B2027/0178
摘要: Systems, apparatus, and methods for augmenting vision with region-of-interest based processing. In one specific example, smart glasses may use an eye-tracking camera to monitor the user's gaze and determine the user's gaze point. When triggered, the camera assembly captures a high-resolution image. The high-resolution image may be cropped to a much smaller region-of-interest (ROI) image based on computer-vision analysis of the user's gaze point. For example, if the smart glasses detect a human face at the gaze point, then the ROI is cropped to the human face. In this manner, the smart glasses may leverage specific capabilities of the smart glasses to augment the user experience; for example, telephoto lenses provide long distance vision, or computer-assisted search may direct the user to interesting activity. Other aspects may include e.g., external database assisted operation and/or ongoing cataloging throughout the day.
-
公开(公告)号:US12090918B2
公开(公告)日:2024-09-17
申请号:US18228580
申请日:2023-07-31
申请人: BlueOwl, LLC
IPC分类号: B60Q1/44 , B60Q1/50 , B60T17/22 , G01L5/28 , G01W1/00 , G05B13/02 , G06V20/58 , G06V30/10 , G06V40/16 , G08G1/0967 , H04W4/40
CPC分类号: B60Q1/444 , B60Q1/50 , B60Q1/5037 , B60T17/221 , G01L5/28 , G01W1/00 , G05B13/0265 , G06V20/58 , G06V40/172 , G08G1/096775 , H04W4/40 , B60Q2400/00 , B60T2210/30 , B60T2210/32 , G06V30/10
摘要: A system for displaying contextually-sensitive braking information on a surface of a vehicle is presented. The system may include a transceiver, one or more memories, an electronic display disposed on the surface, and one or more processors. The one or more processors may be configured to detect a braking event of the vehicle, wherein the braking event has an associated braking force. The one or more processors may compare the braking force to a predetermined threshold braking force to determine whether the braking force exceeds the threshold braking force. The one or more processors may further cause the electronic display to display a braking indication having an intensity that is proportional to the braking force, wherein the braking indication may include a braking rationale corresponding to the braking event in response to determining that the braking force exceeds the threshold braking force.
-
公开(公告)号:US12080084B2
公开(公告)日:2024-09-03
申请号:US17407549
申请日:2021-08-20
发明人: Liangrui Peng , Shanyu Xiao , Ruijie Yan , Gang Yao , Shengjin Wang , Jaesik Min , Jong Ub Suk
CPC分类号: G06V20/63 , G06F18/214 , G06N3/04 , G06N3/084 , G06V10/225 , G06V10/40 , G06V30/10
摘要: A method and a system for detecting a scene text may include extracting a first feature map for a scene image input based on a convolutional neural network, and delivering the first feature map to a sequential deformation module; obtaining sampled feature maps corresponding to sampling positions by performing iterative sampling for the first feature map, obtaining a second feature map by performing a concatenation operation in deep learning according to a channel dimension for the first feature map and the sampled feature maps; obtaining a third feature map by performing a feature aggregation operation for the second feature map in the channel dimension, and delivering the third feature map to the object detection baseline network; and performing text area candidate box extraction for the third feature map and obtaining a text area prediction result as a scene text detection result through regression fitting.
-
公开(公告)号:US12079728B2
公开(公告)日:2024-09-03
申请号:US16980380
申请日:2019-03-07
发明人: Chihiro Watanabe , Kaoru Hiramatsu , Kunio Kashino
CPC分类号: G06N3/084 , G06F18/217 , G06F18/23 , G06V30/1823 , G06V30/19173 , G06V30/10
摘要: The present invention enables the structure of a neural network to be quantitatively analyzed. An analyzing unit calculates, for each of combinations of a dimension of input data and a cluster, a sum of squared errors between an output of each unit belonging to the cluster when a value of the dimension of the input data is replaced with an average value of the dimension of the input data included in learning data and an output of each unit belonging to the cluster for the input data before replacement as a relationship between the combinations, and calculates, for each of combinations of the cluster and a dimension of output data, a squared error between the value of the dimension of the output data when an output value of each unit belonging to the cluster is replaced with an average output value of each unit of the cluster when the input data included in the learning data was input and the value of the dimension of the output data before replacement as a relationship between the combinations.
-
公开(公告)号:US12073373B2
公开(公告)日:2024-08-27
申请号:US16668456
申请日:2019-10-30
IPC分类号: G06Q20/20 , G06Q20/40 , G06Q30/0601 , G06V10/44 , G06V20/30 , G06V20/52 , G06V30/10 , G06V30/18 , G06V30/19 , G06V40/10 , G06V40/70
CPC分类号: G06Q20/20 , G06Q20/40145
摘要: Pay stations in a retail store initiate customer transactions for customers. When a first pay station is unable to complete a customer transaction, it hands the transaction off to a second pay station that is able to complete the transaction. During hand off, the first pay station determines a first set of biometric and contextual data associated with the customers and sends that information to the second pay station. The second pay station then determines, independently, a second set of biometric and contextual data associated with the customers and compares it against the first set. Depending on the results of the comparison, customers are either granted or denied access at the second pay station to complete the transaction. Additionally, all biometric and contextual data are permanently destroyed without being saved to memory.
-
公开(公告)号:US20240281870A1
公开(公告)日:2024-08-22
申请号:US18654184
申请日:2024-05-03
发明人: Yair ADATO , Mark COOK
IPC分类号: G06Q30/0601 , G06F18/21 , G06Q10/0631 , G06Q10/0637 , G06Q10/087 , G06Q20/20 , G06Q30/0201 , G06Q30/0207 , G06Q30/0242 , G06Q30/0251 , G06T7/00 , G06T7/70 , G06V20/00 , G06V20/13 , G06V20/20 , G06V20/52 , G06V30/10 , H02J7/00 , H02J9/06 , H04N7/18 , H04N23/51 , H04N23/54 , H04N23/65
CPC分类号: G06Q30/0639 , G06F18/21 , G06Q10/06312 , G06Q10/06315 , G06Q10/06375 , G06Q10/087 , G06Q20/208 , G06Q30/0201 , G06Q30/0207 , G06Q30/0223 , G06Q30/0242 , G06Q30/0261 , G06Q30/0641 , G06Q30/0643 , G06T7/001 , G06T7/70 , G06V20/00 , G06V20/13 , G06V20/20 , G06V20/52 , H02J7/00036 , H02J7/0013 , H02J7/0048 , H02J7/0068 , H02J9/06 , H04N7/18 , H04N7/181 , H04N23/51 , H04N23/54 , H04N23/65 , G06T2207/30232 , G06V30/10
摘要: A method may include analyzing first images to determine an actual placement of first products displayed on shelves of a retail store; determining a deviation of an actual placement of some of the first products from the desired placement of products associated with a first planogram; receiving second images; analyzing the second images to determine an actual placement of the second products displayed on the shelves; identifying a deviation of the actual placement of some of the second products from the desired placement of products associated with the first planogram; using the second planogram to determine whether an arrangement associated with a second products conforms to the second planogram rather than to the first planogram; and when the arrangement associated with the second products conforms to the second planogram, avoiding issuance of a notification indicating a deviation relative to the first planogram.
-
公开(公告)号:US12056941B2
公开(公告)日:2024-08-06
申请号:US18100998
申请日:2023-01-24
发明人: Khoi Nguyen , Maneesh Kumar Singh
IPC分类号: G06V20/62 , G06F18/20 , G06F18/2413 , G06V30/10 , G06V30/18 , G06V30/19 , G06V30/413 , G06V30/414
CPC分类号: G06V20/62 , G06F18/24147 , G06F18/295 , G06V30/18057 , G06V30/19173 , G06V30/413 , G06V30/414 , G06V30/10
摘要: Computer vision systems and methods for text classification are provided. The system detects a plurality of text regions in an image and generates a bounding box for each detected text region. The system utilizes a neural network to recognize text present within each bounding box and classifies the recognized text, based on at least one extracted feature of each bounding box and the recognized text present within each bounding box, according to a plurality of predefined tags. The system can associate a key with a value and return a key-value pair for each predefined tag.
-
公开(公告)号:US12056661B2
公开(公告)日:2024-08-06
申请号:US17973404
申请日:2022-10-25
发明人: Thomas S. Poole
IPC分类号: G06Q10/087 , G06Q20/00 , G06Q20/32 , G06Q20/36 , G06Q20/38 , G06Q20/40 , G06V10/10 , G06V20/62 , G06V30/142 , G06V30/224 , G06V30/414 , G06V30/10
CPC分类号: G06Q10/087 , G06Q20/00 , G06Q20/3276 , G06Q20/36 , G06Q20/385 , G06Q20/407 , G06V10/10 , G06V20/63 , G06V30/142 , G06V30/224 , G06V30/414 , G06V30/10
摘要: A system and method for generating a notification of a price change for a transaction and facilitating an associated price adjustment based on electronic image capture of a paper receipt. An image capture system captures an electronic image of a paper transaction receipt, which is transmitted to a data extraction processor that extracts transaction receipt data from the captured electronic image. A unique key is generated that is matched to a transaction record to generate a reliability score for the OCRed image and to authorize price matching. If the price monitoring server identifies that the price of a purchased transaction item has changed, the price monitoring server automatically generates a notification to the user indicating the price change and an email to the customer service department of the merchant from which the transaction item was purchased, requesting a price adjustment that is credited back to the payment instrument.
-
公开(公告)号:US20240256302A1
公开(公告)日:2024-08-01
申请号:US18612460
申请日:2024-03-21
申请人: SAP SE
发明人: Gregor Berg , Andre Niklas Wenz , Bernhard Hoeppner , Thomas Bodner , Olga Cherepanova , Lasse Steffen , Jan Siebert , David Hennemann , Pascal Schulze , Konstantin Dobler , Kris-Fillip Kahl , Paul Udo Beneke , Philipp Bernhard Hoberg
IPC分类号: G06F9/451 , G06F3/0482 , G06F9/455 , G06V30/10 , G06V30/148
CPC分类号: G06F9/451 , G06F3/0482 , G06F9/45512 , G06V30/153 , G06V30/10
摘要: An application server provides an application to client devices. Users of the client devices interact with the application to perform a business process. Data regarding user interactions with the application is transmitted from the client devices to the application server. Based on an analysis of the received data, a bot generation server generates a bot to automate a process step. The bot generation server provides a heatmap user interface (UI) that provides information regarding the process steps. Using the heatmap UI, the administrator selects a process step for automation. In response to the selection, the bot generation server identifies, based on the observed behavior, relationships between input fields, typical values for input fields, typical order of data entry into input fields, or any suitable combination thereof. Based on the identified patterns, the bot generation server generates a bot to automate some or all of the process step.
-
-
-
-
-
-
-
-
-