Image processing apparatus, image processing method, and non-transitory recording medium

Patent metadata

Field	Value
Publication number	US-12288407-B2
Application number	US-202217812258-A
Country	US
Kind code	B2
Filing date	Jul 13, 2022
Priority date	Jul 16, 2021
Publication date	Apr 29, 2025
Grant date	Apr 29, 2025

Abstract

An image processing apparatus includes circuitry to set first upper limit values for vertical and horizontal sizes of a character included in image data for erecting direction determination, segment the image data in units of character into a plurality of rectangular areas, determine, in the image data, a plurality of first rectangular areas each of which satisfies the first upper limit values, perform character recognition on characters in the plurality of first rectangular areas in four directions of a +X direction, a −X direction, a +Y direction, and a −Y direction, calculate degrees of certainty of the four directions, determine whether a direction having a highest degree of certainty among the calculated degrees of certainty of the four directions is an erecting direction of the image data to output a determination result, and perform, along the erecting direction, character recognition on characters in a plurality of second rectangular areas of the image data, the plurality of second rectangular areas satisfying second upper limit values for the vertical and horizontal sizes smaller than the first upper limit values for erecting direction determination.

First claim

The invention claimed is:

1. An image processing apparatus comprising circuitry configured to:
set first upper limit values for vertical and horizontal sizes of a character included in image data for erecting direction determination;
segment the image data in units of character into a plurality of rectangular areas;
determine, in the image data, a plurality of first rectangular areas each of which satisfies the first upper limit values;
perform character recognition on characters in the plurality of first rectangular areas in four directions of a +X direction, a −X direction, a +Y direction, and a −Y direction;
calculate degrees of certainty of the four directions;
determine whether a direction having a highest degree of certainty among the calculated degrees of certainty of the four directions is an erecting direction of the image data to output a determination result;
perform, along the erecting direction, character recognition on characters in a plurality of second rectangular areas of the image data, the plurality of second rectangular areas satisfying second upper limit values for the vertical and horizontal sizes smaller than the first upper limit values for erecting direction determination;
score one point in one of the four directions having the highest of the calculated degrees of certainty in a case where at least one of the calculated degrees of certainty exceeds a first threshold value of the degree of certainty;
divide a score in each direction by a total score in the four directions, to normalize the score in each direction; and
in a case where the normalized score in one of the four directions exceeds a second threshold value of the degree of certainty that is different from the first threshold, determine, as the erecting direction, the direction having the normalized score exceeding the second threshold value.

2. The image processing apparatus according to claim 1 , wherein:
the circuitry is configured to increase the first upper limit values for the vertical and horizontal sizes in a case where the plurality of rectangular areas includes a rectangular area having a vertical or horizontal size not exceeding the first upper limit value and the determination result indicates that the erecting direction is undetermined.

3. The image processing apparatus according to claim 1 , wherein:
the circuitry is further configured to:
count, in a row or a column of the plurality of rectangular areas, a number of characters having vertical or horizontal sizes not exceeding the first upper limit value for the vertical or horizontal size; and
increase the first upper limit values for the vertical and horizontal sizes in a case where the counted number of characters is equal to or smaller than a reference value in the row or the column.

4. The image processing apparatus according to claim 1 , wherein:
the circuitry is configured to:
count, in a row or a column of the plurality of rectangular areas, a number of characters adjacent to each other having vertical or horizontal sizes exceeding the first upper limit value for the vertical or horizontal size; and
increase the first upper limit values in a case where the counted number of characters adjacent to each other is two or more in the row or the column for a first time.

5. The image processing apparatus according to claim 3 , wherein:
the circuitry is configured to increase the first upper limit values for the vertical and horizontal sizes in a case where the counted number of characters is more than a half of a total number of the characters in a same row or a same column.

6. The image processing apparatus according to claim 1 , wherein:
the circuitry is further configured to:
extract characters having vertical or horizontal sizes exceeding the first upper limit value for the vertical or horizontal size; and
control the first upper limit values to be taken over in a case where the extracted characters exist in adjacent two rows or adjacent two columns.

7. The image processing apparatus according to claim 1 , wherein:
the circuitry is configured to:
determine the direction having the highest degree of certainty to be the erecting direction in a case where the highest degree of certainty is larger than a predetermined value of the degree of certainty; and
increase the predetermined value of the degree of certainty in a case where the first upper limit values for the vertical and horizontal sizes are increased.

8. The image processing apparatus according to claim 1 , wherein:
the circuitry is configured to:
set the second upper limit values for the vertical and horizontal sizes based on the first upper limit values for erecting direction determination.

9. An image processing method, the method comprising:
setting first upper limit values for vertical and horizontal sizes of a character included in image data for erecting direction determination;
segmenting the image data in units of character into a plurality of rectangular areas;
determining, in the image data, a plurality of first rectangular areas each of which satisfies the first upper limit values;
performing character recognition on characters in the plurality of first rectangular areas in four directions of a +X direction, a −X direction, a +Y direction, and a −Y direction;
calculating degrees of certainty of the four directions;
determining whether a direction having a highest degree of certainty among the calculated degrees of certainty of the four directions is an erecting direction of the image data to output a determination result;
performing, along the erecting direction, character recognition on characters in a plurality of second rectangular areas of the image data, the plurality of second rectangular areas satisfying second upper limit values for the vertical and horizontal sizes smaller than the first upper limit values for erecting direction determination;
scoring one point in one of the four directions having the highest of the calculated degrees of certainty in a case where at least one of the calculated degrees of certainty exceeds a first threshold value of the degree of certainty;
dividing a score in each direction by a total score in the four directions, to normalize the score in each direction; and
in a case where the normalized score in one of the four directions exceeds a second threshold value of the degree of certainty that is different from the first threshold, determining, as the erecting direction, the direction having the normalized score exceeding the second threshold value.

10. A non-transitory recording medium storing a plurality of program codes which, when executed by one or more processors, causes the processors to perform a method, the method comprising:
setting first upper limit values for vertical and horizontal sizes of a character included in image data for erecting direction determination;
segmenting the image data in units of character into a plurality of rectangular areas;
determining, in the image data, a plurality of first rectangular areas each of which satisfies the first upper limit values;
performing character recognition on characters in the plurality of first rectangular areas in four directions of a +X direction, a −X direction, a +Y direction, and a −Y direction;
calculating degrees of certainty of the four directions;
determining whether a direction having a highest degree of certainty among the calculated degrees of certainty of the four directions is an erecting direction of the image data to output a determination result;
performing, along the erecting direction, character recognition on characters on a plurality of second rectangular areas of the image data, the plurality of second rectangular areas s

Assignees

• Sakuyama Hiroyuki
• Ricoh Co Ltd

Inventors

• Sakuyama Hiroyuki

Classifications

• G06T3/40

  Scaling of whole images or parts thereof, e.g. expanding or contracting · CPC title

• G06V30/1448

  based on markings or identifiers characterising the document or the area · CPC title

• G06V30/184

  by analysing segments intersecting the pattern · CPC title

• G06V30/153 Primary

  using recognition of characters or words · CPC title

• G06V30/166 Primary

  Normalisation of pattern dimensions · CPC title