US 12,094,229 B2
Character recognition method and apparatus, computer device, and storage medium
Pengyuan Lv, Shenzhen (CN); Zhicheng Yang, Shenzhen (CN); Xinhang Leng, Shenzhen (CN); Ruiyu Li, Shenzhen (CN); Xiaoyong Shen, Shenzhen (CN); Yuwing Tai, Shenzhen (CN); and Jiaya Jia, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by Tencent Technology (Shenzhen) Company Limited, Shenzhen (CN)
Filed on Sep. 15, 2021, as Appl. No. 17/476,327.
Application 17/476,327 is a continuation of application No. PCT/CN2020/087010, filed on Apr. 26, 2020.
Claims priority of application No. 201910387655.1 (CN), filed on May 10, 2019.
Prior Publication US 2022/0004794 A1, Jan. 6, 2022
Int. Cl. G06N 3/08 (2023.01); G06F 18/22 (2023.01); G06V 10/44 (2022.01); G06V 30/148 (2022.01); G06V 30/10 (2022.01)
CPC G06V 30/153 (2022.01) [G06F 18/22 (2023.01); G06N 3/08 (2013.01); G06V 10/443 (2022.01); G06V 30/10 (2022.01)] 20 Claims
OG exemplary drawing
 
12. A computer device, comprising:
one or more processors; and
memory storing one or more programs, that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
extracting an image feature of an image that includes one or more characters to be recognized, the image feature including a plurality of image feature vectors;
based on the plurality of image feature vectors, acquiring a target number of attention weight values through parallel computing, wherein each of the attention weight values corresponds to one or more respective characters and represents an importance of the plurality of image feature vectors for the one or more respective characters; and
obtaining at least one character according to the plurality of image feature vectors and the target number of attention weight values.