Image processing apparatus and image processing method
View Patent ↗According to an embodiment, an image processing apparatus selects as an output image a candidate character component, from which a non-character component is removed, in a gradation having the largest number of pixels when there is a significant difference between the number of character pixels in the gradation having the largest number of character pixels and the number of character pixels in a gradation having the second largest number of character pixels, and selects as an output image a candidate character component, from which the non-character component is removed, in a gradation having the smallest number of edge pixels when there is no significant difference between the number of character pixels in the gradation having the largest number of character pixels and the number of character pixels in the gradation having the second largest number of character pixels.
1. An image processing apparatus comprising:
a processor that
acquires image data,
extracts a set of candidate character components from the image data for each gradation of the image data on the basis of a predetermined first criterion,
removes a non-character component from the set of the candidate character components on the basis of a predetermined second criterion;
counts the number of character pixels representing the number of pixels included in the candidate character component after the non-character component is removed;
counts the number of edge pixels representing the number of edge pixels adjacent to the candidate character component after the non-character component is removed;
selects as an output image the candidate character component, from which the non-character component is removed, in the gradation having a largest number of pixels when there is a significant difference between the number of character pixels in the gradation having the largest number of character pixels and the number of character pixels in the gradation having the second largest number of character pixels,
selects as the output image the candidate character component, from which the non-character component is removed, in the gradation having a smallest number of edge pixels when there is no significant difference between the number of character pixels in the gradation having the largest number of character pixels and the number of character pixels in the gradation having the second largest number of character pixels, and
outputs the output image being selected.
2. The apparatus according to claim 1 , wherein the processor removes from the set the candidate character component that is exceptional as the non-character component at least one of when a position of the candidate character component in the image data is exceptional compared with that of another one of the candidate character component, when a size of the candidate character component is exceptional compared with that of another one of the candidate character component, when a stroke width of the candidate character component is exceptional compared with that of another one of the candidate character component, and when the number of pixels included in the candidate character component is exceptional compared with that of another one of the candidate character component.
3. The apparatus according to claim 1 , wherein the processor converts the image data being acquired to a binary image.
4. The apparatus according to claim 1 , wherein the processor divides the image data being acquired into one or more sectioned areas grouped by a disposition of a pixel value,
extracts the candidate character component for each of the sectioned areas, and
removes the candidate character component for each of the sectioned areas.
5. The apparatus according to claim 4 , wherein the processor divides the image data into one or more small areas smaller than the sectioned area, generates a histogram of the pixel value for each of the small areas, and determine a set of the small areas each having a similar value in a histogram as the sectioned area.
6. An image processing method comprising:
acquiring image data;
extracting a set of candidate character components from the image data for each gradation of the image data on the basis of a predetermined first criterion;
removing a non-character component from the set of the candidate character components on the basis of a predetermined second criterion;
counting a number of character pixels representing the number of pixels included in the set after the non-character component is removed;
counting a number of edge pixels representing the number of pixels that is a pixel adjacent to the set after the non-character component is removed;
selecting as an output image the candidate character component, from which the non-character component is removed, in the gradation having a largest number of pixels when there is a significant difference between the number of character pixels in the gradation having the largest number of character pixels and the number of character pixels in the gradation having the second largest number of character pixels;
selecting as the output image the candidate character component, from which the non-character component is removed, in the gradation having a smallest number of edge pixels when there is no significant difference between the number of character pixels in the gradation having the largest number of character pixels and the number of character pixels in the gradation having the second largest number of character pixels; and
outputting the output image.