公开(公告)号：US12183059B2

公开(公告)日：2024-12-31

申请号：US17686950

申请日：2022-03-04

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Liang Wang ,  Jiarui Sun ,  Rongbo Shen ,  Cheng Jiang ,  Yanchun Zhu ,  Jianhua Yao

IPC: G06V10/26 ,  G06T3/4038 ,  G06V10/764 ,  G06V10/82

Abstract: An AI-based object classification method and apparatus, a computer-readable storage medium, and a computer device. The method includes: obtaining a target image to be processed, the target image including a target detection object; separating a target detection object image of the target detection object from the target image; inputting the target detection object image into a feature object prediction model to obtain a feature object segmentation image of a feature object in the target detection object image; obtaining quantitative feature information of the target detection object according to the target detection object image and the feature object segmentation image; and classifying the target detection object image according to the quantitative feature information to obtain category information of the target detection object in the target image.

公开(公告)号：US11847812B2

公开(公告)日：2023-12-19

申请号：US17684608

申请日：2022-03-02

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Liang Wang ,  Jiarui Sun ,  Yanchun Zhu ,  Jianhua Yao

IPC: G06V10/44 ,  G06V10/46

CPC classification number: G06V10/44 ,  G06V10/46

Abstract: An image generation method, apparatus, device, and storage medium. The method includes: obtaining contour information and target region information; determining at least one target contour according to the contour information and the target region information, the at least one target contour wholly or partly located in a target region; decreasing first coordinates of a plurality of contour points in the at least one target contour to obtain second location information, second location information of the at least one target contour includes second coordinates of a plurality of contour points in the at least one target contour, and the first coordinates of the plurality of contour points in the at least one target contour having a same decreasing extent; and generating a target image corresponding to the target region according to the second location information of the at least one target contour and the target region information.