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

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.

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 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.