| 主权项 |
1. An image processing apparatus comprising:
one or more processors; and memory storing executable instructions which, when executed by the one or more processors, cause the one or more processors to perform the steps of: accepting character information about a character image in a character region in an image; performing character recognition on the character image in the character region to obtain a plurality of character recognition results, wherein the performing comprises:
separating the character image into at least one single-character candidate region corresponding to one character in the character image, wherein the character region is set by a pointing device, andperforming the character recognition on the separated at least one single-character candidate region and outputting the plurality of character recognition results for the at least one single-character candidate region; selecting a character recognition result, from among the plurality of character recognition results, that matches the accepted character information, wherein the selecting comprises:
checking each of the plurality of character recognition results for the at least one single-character candidate region against text information in the accepted character information, the text information corresponding to a character in the at least one single-character candidate region, andselecting a character recognition result, from among the plurality of character recognition results, that matches the text information; associating the selected character recognition result with the character image to generate an output result, wherein the output result is a combination of the character image and a character code; and outputting the output result as training data for subsequent character recognition processing. |
