Image processing apparatus and non-transitory computer readable medium
An image processing apparatus includes an acquisition unit that acquires an image; and a modifying unit that modifies the image acquired by the acquisition unit by turning an intermittent line different from a line that constitutes a character into a mark by using machine learning in a stage before the image is classified into the character and a mark by a classifying unit.
1. An image processing apparatus comprising:
a memory, storing a program; and
a processor, executing the program to be configured to function as
an acquisition unit that acquires an image; and
a modifying unit that modifies the image acquired by the acquisition unit by turning an intermittent line different from a line that constitutes a character into a mark by using machine learning in a stage before the image is classified into the character and a mark by a classifying unit;
wherein in the stage, a divided image on which the character has been falsely recognized by a character recognizing function among a plurality of divided images obtained by dividing a character recognition target image decided as a target of character recognition by the character recognizing function is acquired as the image by the acquisition unit.
2. The image processing apparatus according to claim 1 , wherein
the modifying unit turns the intermittent line into a mark by turning the intermittent line into a solid line.
3. The image processing apparatus according to claim 2 , wherein
the machine learning is machine learning using an image generation network; and
the modifying unit turns the intermittent line into a solid line by using a generator included in the image generation network.
4. The image processing apparatus according to claim 3 , wherein
the modifying unit causes the generator that has learned by competing with a discriminator included in the image generation network to turn the intermittent line into a solid line.
5. The image processing apparatus according to claim 4 , wherein
the modifying unit modifies the image by causing the generator to generate a solid-line image on which the intermittent line has been turned into a solid line from the image acquired by the acquisition unit.
6. The image processing apparatus according to claim 3 , wherein
the modifying unit acquires a learning result obtained by the generator that has learned by competing with a discriminator included in the image generation network and turns the intermittent line into a solid line by using the acquired learning result.
7. The image processing apparatus according to claim 6 , wherein
the modifying unit modifies the image by generating a solid-line image on which the intermittent line has been turned into a solid line from the image acquired by the acquisition unit by using the learning result.
8. An image processing apparatus comprising:
a memory, storing a program; and
a processor, executing the program to be configured to function as
an acquisition unit that acquires an image; and
a modifying unit that modifies the image acquired by the acquisition unit by removing an intermittent line different from a line that constitutes a character by using machine learning in a stage before the image is classified into the character and a mark by a classifying unit
wherein in the stage, a divided image on which the character has been falsely recognized by a character recognizing function among a plurality of divided images obtained by dividing a character recognition target image decided as a target of character recognition by the character recognizing function is acquired as the image by the acquisition unit.
9. The image processing apparatus according to claim 8 , wherein
the machine learning is machine learning using an image generation network; and
the modifying unit removes the intermittent line by using a generator included in the image generation network.
10. The image processing apparatus according to claim 9 , wherein
the modifying unit causes the generator that has learned by competing with a discriminator included in the image generation network to remove the intermittent line.
11. The image processing apparatus according to claim 10 , wherein
the modifying unit modifies the image by causing the generator to generate, from the image acquired by the acquisition unit, an intermittent-line-removed image on which the intermittent line has been removed.
12. The image processing apparatus according to claim 9 , wherein
the modifying unit acquires a learning result obtained by the generator that has learned by competing with a discriminator included in the image generation network and removes the intermittent line by using the acquired learning result.
13. The image processing apparatus according to claim 12 , wherein
the modifying unit modifies the image by generating, from the image acquired by the acquisition unit, an intermittent-line-removed image on which the intermittent line has been removed by using the learning result.
14. The image processing apparatus according to claim 1 , wherein the processor is further comprising configured to function as an extracting unit that extracts a character region including the character from a modified image obtained by modifying the image by the modifying unit.
15. The image processing apparatus according to claim 8 , wherein the processor is further configured to function as an extracting unit that extracts a character region including the character from a modified image obtained by modifying the image by the modifying unit.
16. The image processing apparatus according to claim 14 , wherein the processor is further configured to function as a character recognizing unit that performs character recognition on the character region extracted by the extracting unit.
17. The image processing apparatus according to claim 16 , wherein the processor is further configured to function as a controller that causes a character recognition result of the character recognizing unit to be displayed on a display.
18. A non-transitory computer readable medium storing a program causing a computer to execute a process for image processing, the process comprising:
acquiring an image; and
modifying the acquired image by turning an intermittent line different from a line that constitutes a character into a mark by using machine learning in a stage before the image is classified into the character and a mark;
wherein in the stage, a divided image on which the character has been falsely recognized by a character recognizing function among a plurality of divided images obtained by dividing a character recognition target image decided as a target of character recognition by the character recognizing function is acquired as the image by acquiring the image.