Image processing apparatus and non-transitory computer readable medium storing program

Patent metadata

Field	Value
Publication number	US-11153447-B2
Application number	US-201916246555-A
Country	US
Kind code	B2
Filing date	Jan 14, 2019
Priority date	Jan 25, 2018
Publication date	Oct 19, 2021
Grant date	Oct 19, 2021

Abstract

An image processing apparatus includes a layout analyzing part that executes layout analysis for image data, an extraction part that extracts a diagrammatic representation from the image data by using a result of the layout analysis, a character recognizing part that executes character recognition for a partial area having a high probability of presence of a character string in a relationship with the extracted diagrammatic representation, and an erecting direction deciding part that decides an erecting direction of the image data by using a result of the character recognition.

First claim

What is claimed is:

1. An image processing apparatus, comprising:
a processor, configured to:
execute layout analysis for image data;
extract a diagrammatic representation from the image data by using a result of the layout analysis;
execute character recognition for a partial area having a high probability of presence of a character string in a positional relationship with the extracted diagrammatic representation; and
decides decide an erecting direction of the image data by using a result of the character recognition for the partial area.

2. The image processing apparatus according to claim 1 , wherein the partial area is decided based on a relative position in the extracted diagrammatic representation.

3. The image processing apparatus according to claim 1 , wherein, when the extracted diagrammatic representation has m rows and n columns (m and n are natural numbers) with respect to a long side or a short side of the image data, the partial area is an area in a first row or an m-th row.

4. The image processing apparatus according to claim 3 , wherein, when the extracted diagrammatic representation has the m rows and the n columns (m and n are natural numbers) with respect to the long side or the short side of the image data and when the erecting direction is not confirmed as a result of the character recognition for the first row that is executed, the m-th row is then set as the partial area.

5. The image processing apparatus according to claim 1 , wherein, when the extracted diagrammatic representation has m rows and n columns (m and n are natural numbers) with respect to a long side or a short side of the image data, the partial area is an area in a first column or an n-th column.

6. The image processing apparatus according to claim 5 , wherein, when the extracted diagrammatic representation has the m rows and the n columns (m and n are natural numbers) with respect to the long side or the short side of the image data and when the erecting direction is not confirmed as a result of the character recognition for the first column that is executed, the n-th column is then set as the partial area.

7. The image processing apparatus according to claim 1 , wherein, when the extracted diagrammatic representation has m rows and n columns (m and n are natural numbers) with respect to a long side or a short side of the image data and when a width of a second column or a width of an (n−1)th column is larger as a result of comparison between a width of a first column and the width of the second column and between a width of an n-th column and the width of the (n−1)th column, the second column or the (n−1)th column is set as the partial area.

8. The image processing apparatus according to claim 1 , wherein, when the extracted diagrammatic representation has m rows and n columns (m and n are natural numbers) with respect to a long side or a short side of the image data, the partial area is an a-th column (1≤a≤n) that is a column having a relatively high frequency of presence of pixels as a result of the layout analysis.

9. The image processing apparatus according to claim 1 , wherein, when the extracted diagrammatic representation has m rows and n columns (m and n are natural numbers) with respect to a long side or a short side of the image data, the partial area is an a-th column (1≤a≤n) that is a widest column as a result of the layout analysis.

10. The image processing apparatus according to claim 1 , wherein, when the extracted diagrammatic representation extracted by the extraction part has m rows and n columns (m and n are natural numbers) with respect to a long side or a short side of the image data, the partial area is an a-th column (1≤a≤n) that is a widest column having a relatively high frequency of presence of pixels as a result of the layout analysis.

11. The image processing apparatus according to claim 1 , wherein, when the extracted diagrammatic representation has m rows and n columns (m and n are natural numbers) with respect to a long side or a short side of the image data, the partial area is an area including a plurality of rows less than the in rows.

12. The image processing apparatus according to claim 1 , wherein, when the extracted diagrammatic representation has m rows and n columns (m and n are natural numbers) with respect to a long side or a short side of the image data, the partial area is an area including a plurality of columns less than the n columns.

13. The image processing apparatus according to claim 1 ,
wherein the processor sequentially executes the character recognition for the character string in the partial area and calculates a certainty factor of the character recognition, and
wherein, when the certainty factor is equal to or larger than a reference value, the processor decides the erecting direction of the image data without executing the character recognition for a remaining part of the character string in the partial area by the character recognizing part.

14. The image processing apparatus according to claim 1 ,
wherein the partial area is an area of a title of the extracted diagrammatic representation or, when the extracted diagrammatic representation has in rows and n columns (m and n are natural numbers), an area in a first row or an m-th row or an area in a first column or an n-th column, and
wherein the processor first executes the character recognition for the area of the title of the diagrammatic representation and, when the erecting direction of the image data is not decided, then executes the character recognition for the area in the first row or the m-th row or executes the character recognition for the area in the first column or the n-th column.

15. The image processing apparatus according to claim 14 ,
wherein, when the extracted diagrammatic representation has the m rows and the n columns (m and n are natural numbers), the partial area is an area in a second column or an (n−1)th column, and
wherein the processor executes the character recognition for the area in the first column or the n-th column and, when the erecting direction of the image data is not decided, executes the character recognition for the area in the second column or the (n−1)th column.

16. The image processing apparatus according to claim 1 ,
wherein the diagrammatic representation comprises a table having the character string, and
wherein the processor detects a character direction of the character string in at least one of a horizontally-oriented rectangular area and a vertically-oriented rectangular area of the table so as to determine the erecting direction of the image data.

17. The image processing apparatus according to claim 1 ,
wherein the diagrammatic representation comprises a table having the character string, and
wherein the processor detects a character direction of the character string in an area near the table so as to determine the erecting direction of the image data.

18. A non-transitory computer readable medium storing a program causing a computer to execute a process comprising:
acquiring image data by reading a document;
executing layout analysis for the image data;
extracting a diagrammatic representation from the image data by using a result of the layout analysis;
executing character recognition for a partial area having a high probability of presence of a character string in a positional relationship with the extracted diagrammatic representation; and
deciding and outputting an erecting direction of the image data by using a result of the character recognition for the partial area.

Assignees

• Fujifilm Business Innovation Corp

Inventors

• Oya Kazuhiro
• Abe Akane
• Yamaguchi Akinobu
• Kobayashi Kunihiko
• Shimizu Junichi
• Okada Shigeru
• Adachi Shintaro
• Nakamura Shinya

Classifications

• G06V30/1463

  Orientation detection or correction, e.g. rotation of multiples of 90 degrees · CPC title

• G06V30/10

  Character recognition · CPC title

• G06V30/414

  Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text · CPC title

• H04N1/00336

  with an apparatus performing pattern recognition, e.g. of a face or a geographic feature (image or video recognition or understanding of scenes G06V20/00) · CPC title

• H04N1/00331 Primary

  with an apparatus performing optical character recognition (character recognition G06V30/10) · CPC title