US 12,314,314 B2
Image data processing method and apparatus, electronic device, and storage medium
Li Qiang Liu, Shenzhen (CN); and Xuan Luo, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Guangdong (CN)
Filed on Aug. 6, 2021, as Appl. No. 17/395,920.
Application 17/395,920 is a continuation of application No. PCT/CN2020/099706, filed on Jul. 1, 2020.
Claims priority of application No. 201910663368.9 (CN), filed on Jul. 22, 2019.
Prior Publication US 2021/0365749 A1, Nov. 25, 2021
Int. Cl. G06F 16/583 (2019.01); G06F 16/58 (2019.01); G06F 18/2431 (2023.01); G06F 18/25 (2023.01); G06V 10/762 (2022.01); G06V 40/16 (2022.01)
CPC G06F 16/5854 (2019.01) [G06F 16/5866 (2019.01); G06F 18/2431 (2023.01); G06F 18/251 (2023.01); G06F 18/254 (2023.01); G06V 10/762 (2022.01); G06V 40/168 (2022.01); G06V 40/174 (2022.01); G06V 40/176 (2022.01)] 21 Claims
OG exemplary drawing
 
1. An image data processing method, performed by an electronic device, the method comprising:
receiving an expression image trigger operation of a target user in a state in which a session page of an instant messaging application between the target user and an associated user is displayed;
obtaining, in response to the expression image trigger operation of the target user, an operation object associated with the expression image trigger operation on the session page of the instant messaging application;
based on the operation object being image data sent from the associated user and displayed on the session page and on which the expression image trigger operation having been performed, extracting a target object feature in the image data, and obtaining, from an object feature library, a first image set based on similarities between with the target object feature and expression images of the first image set; and
switching from the session page to an expression image search page that displays at least one expression image included in the first image set, determining a target expression image in response to a selection trigger operation of the target user among the first image set, and displaying the target expression image on the session page,
wherein the extracting the target object feature and obtaining the first image set comprises:
performing face positioning on the image data, and extracting facial features from the face positioning;
determining similarities between the extracted facial features and a plurality of object features included in the object feature library; and
determining the first image set based on the similarities between extracted facial features and the plurality of object features.