US 11,694,458 B2
Image processing apparatus that sets metadata of image data, method of controlling same, and storage medium
Hiroki Takeishi, Machida (JP)
Assigned to CANON KABUSHIKI KAISHA, Tokyo (JP)
Filed by CANON KABUSHIKI KAISHA, Tokyo (JP)
Filed on Jun. 9, 2020, as Appl. No. 16/896,527.
Claims priority of application No. 2019-109609 (JP), filed on Jun. 12, 2019.
Prior Publication US 2020/0394432 A1, Dec. 17, 2020
Int. Cl. G06V 30/412 (2022.01); G06F 18/22 (2023.01); G06V 30/196 (2022.01); G06V 30/10 (2022.01)
CPC G06V 30/412 (2022.01) [G06F 18/22 (2023.01); G06V 30/1985 (2022.01); G06V 30/10 (2022.01)] 5 Claims
OG exemplary drawing
 
1. An image processing apparatus that sets metadata of image data using one of a plurality of metadata templates, each metadata template associated with a different type of work, comprising:
at least one memory that stores a program; and
at least one processor that executes the program to perform:
selecting a type of work corresponding to the image data;
performing an optical character recognition (OCR) processing for the image data to obtain character strings corresponding to a plurality of character string areas included in the image data;
identifying a key candidate from the obtained character strings based on one or more key types defined in a first metadata template of the plurality of metadata templates, the first metadata template corresponding to the selected type of work;
identifying a value candidate, as a value for the identified key candidate, from the obtained character strings based on a value type rule and a value search area rule defined for a key type of the identified key candidate, wherein the value type rule is a rule for identifying a character string of a specific type from the obtained character strings, and wherein the value search area rule defines a distance between a character string area corresponding to the identified key candidate and a character string area corresponding to the value candidate to be identified; and
setting the identified value candidate as the metadata of the image data.