Method and apparatus for character selection based on character recognition, and terminal device

A terminal device, comprising:

• a memory to store instructions,
• a processor coupled to the memory, wherein the instructions, when executed by the processor, cause the processor to perform operations of character selection based on character recognition, the operations comprising:
• obtaining a connectionist temporal classification sequence corresponding to text content in an original picture, the obtaining comprising;
• recognizing the text content to obtain an initial connectionist temporal classification sequence;
• determining a length of the initial connectionist temporal classification sequence, and determining a width of a to-be-recognized picture;
• and
• cropping the initial connectionist temporal classification sequence to obtain a connectionist temporal classification sequence corresponding to the text content based on a preset downsampling rate, the length of the initial connectionist temporal classification sequence, and the width of the to-be-recognized picture;
• calculating character coordinates of each character in the connectionist temporal classification sequence;
• mapping the character coordinates of each character to the original picture, to obtain target coordinates of each character in the original picture;
• and
• generating a character selection control in the original picture based on the target coordinates, wherein the character selection control is used to indicate a user to select a character in the original picture.

A non-transitory machine-readable storage medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations of character selection based on character recognition, the operations comprising:

• obtaining a connectionist temporal classification sequence corresponding to text content in an original picture, the obtaining comprising;
• recognizing the text content to obtain an initial connectionist temporal classification sequence;
• determining a length of the initial connectionist temporal classification sequence, and determining a width of a to-be-recognized picture;
• and
• cropping the initial connectionist temporal classification sequence to obtain a connectionist temporal classification sequence corresponding to the text content based on a preset downsampling rate, the length of the initial connectionist temporal classification sequence, and the width of the to-be-recognized picture;
• calculating character coordinates of each character in the connectionist temporal classification sequence;
• mapping the character coordinates of each character to the original picture, to obtain target coordinates of each character in the original picture;
• and
• generating a character selection control in the original picture based on the target coordinates, wherein the character selection control is used to indicate a user to select a character in the original picture.