IP Library › Granted Patent US 12664806
Granted Patent B2
US 12664806 · App. 18/535,197 · Granted Jun 23, 2026

Image processing apparatus, image processing method, and storage medium, that obtain a single continuous character string based on character recognition results of a scanned image

Inventor: Keisuke Ito (Tokyo, JP)
Assignee: CANON KABUSHIKI KAISHA
G06V30/22G06F40/166G06V30/1456
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12664806
App. No.
18/535,197
Granted
Jun 23, 2026
Kind
B2
Abstract

An image processing apparatus and method displays a scanned image obtained by scanning a document, including handwritten characters, printed characters, and objects on a UI screen for a user to designate a character area in the scanned image. When the designated character area includes strings of handwritten characters and a string of printed characters, or an object existing between the strings of handwritten characters, a predetermined delimiter character is inserted in place of the string of printed characters or the object forming a single continuous character string.

Claims (57)

1 . An image processing apparatus comprising:

a controller including a processor and a memory, configured to:

obtain a scanned image by scanning a document including a plurality of strings of handwritten characters and a string of printed characters;

obtain character recognition results for a plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters included in the scanned image, character recognition results for a printed character block corresponding to the string of printed characters included in the scanned image, and an object other than characters included in the scanned image;

display the scanned image on a UI screen for a user to designate a character area in the scanned image; and

in a case where the character area designated by the user includes: (i) the plurality of strings of handwritten characters and (ii) the string of printed characters or the object exists between the plurality of strings of handwritten characters:

insert a predetermined delimiter character in place of the string of printed characters or the object existing between the plurality of strings of handwritten characters; and

display on the UI screen a first single continuous character string combining the character recognition results for the plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters and the predetermined delimiter character between the plurality of handwritten character blocks.

2 . The image processing apparatus according to claim 1 , wherein:

the controller is configured to further display on the UI screen:

a second single continuous character string combining only the character recognition results for the plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters by deleting the string of printed characters and the object;

a third single continuous character string combining the character recognition results for the plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters and the character recognition results for the printed character block corresponding to the string of printed characters by inserting the predetermined delimiter character in place of the object; and

a fourth single continuous character string combining the character recognition results for the plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters and the character recognition results for the printed character block corresponding to the string of printed characters by deleting the object; and

one of the displayed first single continuous character string, the displayed second single continuous character string, the displayed third single continuous character string, or the displayed fourth single continuous character string is selectable by the user.

3 . The image processing apparatus according to claim 1 , wherein the controller is further configured to:

determine whether or not the character recognition results for the printed character block is a combining-target character string based on sizes of the plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters; and

display, on the UI screen, a second single continuous character string combining the character recognition results for the plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters and the character recognition results for the printed character block without inserting the predetermined delimiter character, in response to the character recognition results being the combining-target character string.

4 . The image processing apparatus according to claim 1 , wherein the controller is further configured to:

determine, in a case where a length in a vertical direction of the printed character block corresponding to the string of printed characters existing between the plurality of strings of handwritten characters is not smaller than an average value of lengths in a vertical direction of the plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters by a predetermined ratio or more, that the character recognition results for the printed character block is the combining-target character string; and

display, on the UI screen, a second single continuous character string combining the character recognition results for the plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters and the character recognition results for the printed character block without inserting the predetermined delimiter character, in response to the character recognition results being the combining-target character string.

5 . The image processing apparatus according to claim 1 , wherein the controller is further configured to:

display on the UI screen, in a case where a second single continuous character string combining the character recognition results for the plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters and the character recognition results for the printed character block corresponding to the string of printed characters existing between the plurality of strings of handwritten characters has a predetermined format, the second single continuous character string without inserting the predetermined delimiter character.

6 . The image processing apparatus according to claim 5 , wherein the controller is further configured to:

determine whether or not to insert the predetermined delimiter character based on a character code of the handwritten characters adjacent before and after the string of printed characters existing between the plurality of string of handwritten characters; and

display on the UI screen the second single continuous character string in accordance with the determination.

7 . The image processing apparatus according to claim 6 , wherein the controller is further configured to:

display on the UI screen, in a case where a character code of a last handwritten character of one of the plurality of strings of handwritten characters, which is adjacent before the string of printed characters existing between the plurality of strings of handwritten characters, and a character code of a first handwritten character of one of the plurality of strings of handwritten characters, which is adjacent after the string of printed characters existing between the plurality of strings of handwritten characters is a predetermined character code, the second single continuous character string with the predetermined delimiter character inserted in place of the string of printed characters existing between the plurality of strings of handwritten characters.

8 . The image processing apparatus according to claim 6 , wherein the controller is further configured to:

display on the UI screen, in a case where a character code of a last handwritten character of one of the plurality of strings of handwritten characters, which is adjacent before the string of printed characters existing between the plurality of strings of handwritten characters, and a character code of a first handwritten character of one of the plurality of strings of handwritten characters, which is adjacent after the string of printed characters existing between the plurality of strings of handwritten characters is not a predetermined character code, the second single continuous character string with the string of printed characters existing between the plurality of strings of handwritten characters deleted without inserting the predetermined delimiter character.

9 . The image processing apparatus according to claim 1 , wherein the controller is further configured to:

receive designation of an item by a user operation; and

display, on the UI screen, a second single continuous character string on the UI screen, which is generated based on the character recognition results for the plurality of handwritten character blocks and the printed character block, respectively, which correspond to the designated item.

10 . The image processing apparatus according to claim 1 , wherein the controller is further configured to:

register arrangement information on the plurality of handwritten character blocks and the printed character block corresponding to the plurality of strings of handwritten characters and the string of printed characters, respectively, which are included in the scanned image, and the character recognition results for the plurality of handwritten character blocks and the character recognition results for the printed character block, respectively, in association with each other for each of the scanned images set by a user operation.

11 . The image processing apparatus according to claim 1 , wherein the controller is further configured to:

transmit the scanned image to an external apparatus performing character recognition processing and receive the character recognition results for the plurality of handwritten character blocks and the printed character block in the scanned image from the external apparatus.

12 . The image processing apparatus according to claim 11 , wherein the controller is further configured to:

obtain, in a case where a format of the document of the transmitted scanned image is similar to a format of a document registered in advance in the external apparatus, the character recognition results for the plurality of handwritten blocks and the printed character block, respectively, which are determined based on a rule set to the format of the document registered in advance in the external apparatus.

13 . The image processing apparatus according to claim 1 , wherein the object is a ruled line or a frame line.

14 . The image processing apparatus according to claim 1 , wherein the first single continuous character string, displayed on the UI screen, corresponds to a file name of the scanned image.

15 . The image processing apparatus according to claim 1 , wherein the controller is further configured to:

separate blocks into the plurality of handwritten character blocks and the printed character block corresponding to the plurality of strings of handwritten characters and the string of printed characters, respectively, which are included in the scanned image, by analyzing the scanned image; and

perform character recognition processing on the separated plurality of handwritten character blocks and the separated printed character block.

16 . An image processing method comprising:

obtaining a scanned image by scanning a document including a plurality of strings of handwritten characters and a string of printed characters;

obtaining character recognition results for a plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters included in the scanned image, character recognition results for a printed character block corresponding to the string of printed characters included in the scanned image, and an object other than characters included in the scanned image; and

displaying the scanned image on a UI screen for a user to designate a character area in the scanned image; and

in a case where the character area designated by the user includes: (i) the plurality of strings of handwritten characters and (ii) the string of printed characters or the object exists between the plurality of handwritten characters:

inserting a predetermined delimiter character in place of the string of printed characters or the object existing between the plurality of strings of handwritten characters; and

displaying on the UI screen a first single continuous character string combining the character recognition results for the plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters and the predetermined delimiter character between the plurality of handwritten character blocks.

17 . A non-transitory computer readable storage medium storing a program executable by a computer to perform an image processing method comprising:

obtaining a scanned image by scanning a document including a plurality of strings of handwritten characters and a string of printed characters;

obtaining character recognition results for a plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters included in the scanned image, character recognition results for a printed character block corresponding to the string of printed characters included in the scanned image, and an object other than characters included in the scanned image; and

displaying the scanned image on a UI screen for a user to designate a character area in the scanned image; and

in a case where the character area designated by the user includes: (i) the plurality of strings of handwritten characters and (ii) the string of printed characters or the object exists between the plurality of handwritten characters:

inserting a predetermined delimiter character in place of the string of printed characters or the object existing between the plurality of strings of handwritten characters; and

displaying on the UI screen a first single continuous character string combining the character recognition results for the plurality of handwritten character blocks corresponding to the plurality of strings of handwritten characters and the predetermined delimiter character between the plurality of handwritten character blocks.