STORAGE MEDIUM, INFORMATION PROCESSING APPARATUS AND CHARACTER RECOGNITION METHOD

• US 20140340333A1
• Filed: 04/18/2014
• Published: 11/20/2014
• Est. Priority Date: 05/16/2013
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: TAKASUGI, Aya, Hoshi, Tetsuro
• Granted Patent: US 9,298,365 B2
• Time in Patent Office: Days
• US Class Current: 345/173
• CPC Class Codes: G06F 3/018 Input/output arrangements for oriental characters
• CPC Class Codes: G06F 3/04883 for inputting data by handwriting, e.g. gesture or text
• CPC Class Codes: G06T 11/203 Drawing of straight lines or curves
• CPC Class Codes: G06V 30/32 Digital ink

Abstract

An information processing apparatus includes a storage unit configured to store a first information in which a character code and an image data of a character are associated with each other and an operation unit. The operation unit is configured to detect a second information indicating an input position of each of a plurality of characters input through a handwriting input and a plurality of character codes associated with the plurality of characters, acquire a plurality of first image data associated with the plurality of characters codes by referring to the first information, generate a second image data by combining the plurality of first image data based on the second information, and output an image data of the character associated with the second image data or the character code associated with the second image data by referring to the first information.

Claims

1. A computer-readable recording medium storing a character recognition program that, when executed, causes a computer to perform a character recognition method, the character recognition method comprising:

detecting a first information indicating an input position of each of a plurality of characters input through a handwriting input and a plurality of character codes associated with the plurality of characters;

acquiring a plurality of first image data associated with each of the plurality of character codes by referring to a second information in which the character codes and image data of the characters are associated with each other;

generating a second image data by combining the plurality of first image data based on the first information; and

outputting an image data of a character associated with the second image data or a character code associated with the second image data by referring to the second information.

2. The computer-readable recording medium according to claim 1, wherein the generating includes:

deforming the plurality of first image data based on the first information; and

generating the second image data by combining the plurality of first image data deformed at the deforming.

3. The computer-readable recording medium according to claim 2, wherein the deforming includes:

specifying a plurality of rectangles that indicate an area in which the plurality of characters are input based on the first information; and

matching an aspect ratio of each of the plurality of the first image data deformed at the deforming to an aspect ratio of each of the plurality of rectangles.

4. The computer-readable recording medium according to claim 3, wherein the deforming includes matching an area ratio of each of the plurality of first image data to an area ratio of each of the plurality of rectangles.

5. The computer-readable recording medium according to claim 1, wherein the generating includes:

specifying a relative positional relationship between input positions of the plurality of characters based on the first information; and

maintaining the relative positional relationship to combine the plurality of first image data.

6. The computer-readable recording medium according to claim 1, wherein the detecting includes:

for each time when one stroke in handwriting is received, collating information indicating a reference stroke included in a dictionary data with a set of strokes that are not decided for forming a character, among input strokes, by referring to the dictionary data in which a plurality of associations between the character code and information indicating a reference stroke are registered each time; and

detecting each of the plurality of character codes sequentially based on a collation result.

7. The computer-readable recording medium according to claim 6, wherein the collating includes:

calculating a similarity between the set of strokes that are not decided for forming a character and a plurality of reference strokes included in the dictionary data to acquire a character code associated with the reference stroke having the maximum similarity;

deciding the character code acquired at the previous time for a set of strokes input up to the previous time among the set of strokes that are not decided for forming a character when the maximum similarity at the present time is less than or equal to the maximum similarity at the previous time and the maximum similarity at the previous time is equal to or larger than a threshold value.

8. The computer-readable recording medium according to claim 7, wherein the collating includes:

detecting the last character code among the plurality of character codes by deciding the character code acquired lastly for the set of strokes that are not decided for forming a character when inputting of the next stroke is not started within a limitation time after receiving input of the stroke.

9. The computer-readable recording medium according to claim 1, wherein the second information is information of a character font maintained by the computer in advance or information prepared based on the information of the character font.

10. An information processing apparatus, comprising:

a storage unit configured to store a first information in which a character code and an image data of a character are associated with each other; and

an operation unit,

wherein the operation unit is configured to;

detect a second information indicating an input position of each of a plurality of characters input through a handwriting input and a plurality of character codes associated with the plurality of characters;

acquire a plurality of first image data associated with the plurality of characters codes by referring to the first information;

generate a second image data by combining the plurality of first image data based on the second information; and

output an image data of the character associated with the second image data or the character code associated with the second image data by referring to the first information.