US 11,704,921 B2
Image processing apparatus, image processing method, and storage medium
Makoto Enomoto, Tokyo (JP)
Assigned to Canon Kabushiki Kaisha, Tokyo (JP)
Filed by CANON KABUSHIKI KAISHA, Tokyo (JP)
Filed on Jan. 24, 2022, as Appl. No. 17/583,055.
Claims priority of application No. 2021-013430 (JP), filed on Jan. 29, 2021.
Prior Publication US 2022/0245957 A1, Aug. 4, 2022
Int. Cl. G06V 30/24 (2022.01); G06V 30/32 (2022.01); G06V 30/41 (2022.01); G06V 30/224 (2022.01)
CPC G06V 30/2552 (2022.01) [G06V 30/224 (2022.01); G06V 30/32 (2022.01); G06V 30/41 (2022.01)] 11 Claims
OG exemplary drawing
 
1. An image processing apparatus for extracting a character string that is to be an item value corresponding to a specific item among character strings described in a document, the image processing apparatus comprising:
a memory that stores a program; and
a processor that executes the program to perform:
obtaining, among character areas in a scanned image of the document, a handwritten character area representing handwritten characters and a printed character area representing printed characters;
performing first character recognition processing for handwritten character to the handwritten character area;
performing second character recognition processing for printed character to the printed character area;
integrating character recognition results for the handwritten character area and character recognition results for the printed character area; and
determining a character string that is the item value based on results by calculating a likelihood indicating a probability of being an extraction target for a candidate character string that is an extraction candidate among the integrated character recognition results, wherein
in the determining, the likelihood is calculated by using different evaluation indications in a case where a character originating from the handwritten character area is included in characters constituting the candidate character string and in a case where such a character is not included.