-
1.发明申请公开(公告)号：US20250078479A1
公开(公告)日：2025-03-06
申请号：US18948735
申请日：2024-11-15
Inventor： Han ZHENG , Hong SHANG , Xiaoning WANG , Jianhua YAO
IPC: G06V10/774 , G06V10/74 , G06V10/764 , G06V10/77 , G06V10/776 , G06V10/82
Abstract: An artificial intelligence-based image processing method includes: obtaining a first sample image of a source domain and a second sample image of a target domain, the first sample image of the source domain carrying a corresponding target processing result; converting the first sample image into a target sample image, the target sample image carrying a corresponding target processing result; training a first image processing model based on the target sample image and the target processing result corresponding to the target sample image, to obtain a second image processing model; and inputting, in response to obtaining a human tissue image of the target domain, the human tissue image into the second image processing model, positioning, by the second image processing model, a target human tissue in the human tissue image, and outputting position information of the target human tissue in the human tissue image.
-
2.发明公开公开(公告)号：US20240184854A1
公开(公告)日：2024-06-06
申请号：US18438595
申请日：2024-02-12
Inventor： Hong SHANG , Han ZHENG , Zhongqian SUN
IPC: G06F18/214 , G06F18/21 , G06N7/01 , G16H30/40 , G16H50/20
CPC classification number: G06F18/2155 , G06F18/217 , G06N7/01 , G16H30/40 , G16H50/20 , G06V2201/03
Abstract: A method for training an image recognition model includes: obtaining training image sets; obtaining a first predicted probability, a second predicted probability, a third predicted probability, and a fourth predicted probability based on the training image sets by using an initial image recognition model; determining a target loss function according to the first predicted probability, the second predicted probability, the third predicted probability, and the fourth predicted probability; and training the initial image recognition model based on the target loss function, to obtain an image recognition model.
-
公开(公告)号：US20210272681A1
公开(公告)日：2021-09-02
申请号：US17321219
申请日：2021-05-14
Inventor： Han ZHENG , Zhongqian Sun , Hong Shang , Xinghui Fu , Wei Yang
Abstract: This application relates to an image recognition model training method, an image recognition method, apparatus, and system. The method includes: obtaining a to-be-recognized image; extracting image feature information of the to-be-recognized image; and obtaining a lesion category recognition result of the to-be-recognized image by using the image feature information of the to-be-recognized image as an input parameter of a preset image recognition model, the image recognition model being trained by using a training image sample set comprising at least one strong-label training image sample, to determine the lesion category recognition result; and the strong-label training image sample representing an image sample having strong-label information, and the strong-label information comprising at least annotation information of a lesion category and a lesion position in the strong-label training image sample. According to the lesion position, image feature information of a specific lesion category may be more accurately positioned, thereby improving reliability and accuracy.
-
公开(公告)号：US20220189147A1
公开(公告)日：2022-06-16
申请号：US17682353
申请日：2022-02-28
Inventor： Jiaxuan ZHUO , Hong SHANG , Zhongqian SUN , Han ZHENG , Xinghui FU
IPC: G06V10/774 , G06V10/776 , G06V10/764 , G06V10/778 , G06V10/40 , G06T7/73 , G06T7/00 , G16H30/40
Abstract: An object detection model training method includes: inputting an unannotated first sample image into an initial detection model of a current round, and outputting a first prediction result for a target object, transforming the first sample image and a first prediction position region within the first prediction result to obtain a second sample image and a prediction transformation result in the second sample image; inputting the second sample image into the initial detection model, and outputting a second prediction result for the target object; obtaining a loss value of unsupervised learning according to a difference between the second prediction result and the prediction transformation result; and adjusting model parameters of the initial detection model according to the loss value and returning to the operation of inputting a first sample image into an initial detection model of a current round to perform iterative training, to obtain an object detection model.
-
Patent Agency Ranking
5.发明申请公开(公告)号：US20220222925A1
公开(公告)日：2022-07-14
申请号：US17710254
申请日：2022-03-31
Inventor： Han ZHENG , Hong SHANG , Xiaoning WANG , Jianhua YAO
IPC: G06V10/774 , G06V10/764 , G06V10/82 , G06V10/776 , G06V10/74 , G06V10/77
Abstract: An artificial intelligence-based image processing method includes: obtaining a first sample image of a source domain and a second sample image of a target domain, the first sample image of the source domain carrying a corresponding target processing result; converting the first sample image into a target sample image, the target sample image carrying a corresponding target processing result; training a first image processing model based on the target sample image and the target processing result corresponding to the target sample image, to obtain a second image processing model; and inputting, in response to obtaining a human tissue image of the target domain, the human tissue image into the second image processing model, positioning, by the second image processing model, a target human tissue in the human tissue image, and outputting position information of the target human tissue in the human tissue image.
-
公开(公告)号：US20220172828A1
公开(公告)日：2022-06-02
申请号：US17674126
申请日：2022-02-17
Inventor： Junwen QIU , Zhongqian SUN , Xinghui FU , Hong SHANG , Han ZHENG
Abstract: This application relates to an endoscopic image display method, apparatus, computer device, and storage medium, and relates to the field of machine learning technologies. The method acquiring an endoscopic image; locating a target region image in the endoscopic image, the target region image being a partial image comprising a target region; inputting the target region image into a coding network to obtain a semantic feature of the target region image, the coding network being a part of an image classification network, and the image classification network being a machine learning network obtained through training with first training images; matching the semantic feature of the target region image against semantic features of image samples to obtain a matching result, the matching result indicating a target image sample that matches the target region image; and displaying the endoscopic image and the matching result in an endoscopic image display interface.
-
公开(公告)号：US20220058821A1
公开(公告)日：2022-02-24
申请号：US17520715
申请日：2021-11-07
Inventor： Xinghui FU , Han ZHENG , Junwen QIU , Hong SHANG , Zhongqian SUN
Abstract: A medical image processing method includes: determining a target mask of a target object in a medical image and a reference mask of a reference object in the medical image, the target mask indicating a position and a boundary of the target object, and the reference mask indicating a position and a boundary of the reference object; determining a feature size of the target object based on the target mask; determining a feature size of the reference object based on the reference mask; and determining a target size of the target object based on the feature size of the reference object, a preset mapping relationship between the feature size of the reference object and a reference size, and the feature size of the target object.
-
公开(公告)号：US20220207862A1
公开(公告)日：2022-06-30
申请号：US17699056
申请日：2022-03-18
Inventor： Xiaoning WANG , Jianhua YAO , Hong SHANG , Han ZHENG
IPC: G06V10/764 , G06V10/82 , G06V10/774 , G06V10/776 , G06V10/22
Abstract: An image analysis method includes: obtaining an image; performing image classification on the image by using an image classification network, to obtain an image classification result of an image category of the image, the image category including a first category and a second category different from the first category; performing object detection on the image by using an object detection network, to obtain an object detection result of a target object associated with the first category; and generating an image analysis result of the image based on the image classification result and the object detection result.
-
公开(公告)号：US20190095293A1
公开(公告)日：2019-03-28
申请号：US16203376
申请日：2018-11-28
Inventor： Wen ZHANG , Yongfu SUN , Baiwan ZHU , Rui LI , Han ZHENG , Zhigang HAO
Abstract: A data disaster tolerance method, device and system is disclosed. Each node in a logic unit including a single master node and two or more slave nodes is monitored. If the master node is abnormal, the server acquires log information of the plurality of two or more slave nodes separately, the log information of the two or more slave nodes includes respective time points of data synchronization between the slave nodes and the master node A respective slave node of the two or more slave nodes having the time point of data synchronization closest to a current time is selected as a target node. A master-slave relationship in the logic unit is updated to change a role of the target node to that of the master node.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.018 seconds)
