Image processing apparatus and image processing method

1. An image processing apparatus comprising:

a region analysis unit configured to generate a plurality of quantized regions by integrating regions that are included in an input multivalued image and have similar colors and to determine connected components included in each of the generated quantized regions, and to obtain region information of the connected components, the region information including attribute information, positional information, color information and surrounding relationship information of the connected components; and

a character portion filling unit configured to acquire the quantized regions adjacent to a connected component having a character attribute based on the region information, and to determine a color used for filling the connected component having the character attribute based on a count number, the attribute information and the color information of the acquired quantized regions, and to execute processing for filling the connected component having the character attribute based on the determined color,

wherein the character portion filling unit is configured to change, based on the count number and the attribute information of the acquired quantized regions, a method for determining the color used for filling the connected component having the character attribute.

2. The image processing apparatus according to claim 1 , wherein the character portion filling unit is configured, if only one quantized region exists adjacent to the connected component having the character attribute and the adjacent quantized region has a single-color background attribute, to determine a color of the adjacent quantized region as the color use for filling, and if a plurality of quantized regions exist adjacent to the connected component having the character attribute or if a quantized region existing adjacent to the connected component having the character attribute has a multicolor background attribute, the character portion filling unit is configured to determine an average color of pixels surrounding the connected component as the color used for filling.

3. The image processing apparatus according to claim 2 , wherein the character portion filling unit is configured, if a plurality of quantized regions exist adjacent to the connected component having the character attribute, to segment the connected component based on the adjacent quantized region and to determine an average color of pixels surrounding the segmented connected components as the color used for filling.

4. The image processing apparatus according to claim 1 , wherein the character portion filling unit is configured to change the method for determining the color used for filling for each quantized region including a plurality of connected components determined to have the character attribute.

5. The image processing apparatus according to claim 1 , wherein the character portion filling unit is configured to change the method for determining the color used for filling for each connected component having the character attribute.

6. The image processing apparatus according to claim 1 , wherein the character portion filling unit is configured to determine whether only one quantized region exists adjacent to the connected component having the character attribute and the adjacent quantized region has a single-color background attribute for each quantized region including a plurality of connected components having the character attribute,

if it is determined that only one adjacent quantized region exists and the adjacent quantized region has the single-color background attribute, the character portion filling unit is configured to determine a color of the adjacent quantized region as the color used for filling, and

if it is determined that a plurality of quantized regions exist adjacent to the connected component having the character attribute or the adjacent quantized region has a multicolor background attribute, the character portion filling unit is configured to change the method for determining the color used for filling according to a result of determination as to whether the count number of the adjacent quantized region is one and whether only one adjacent quantized region exists and the adjacent quantized region has the single-color background attribute.

7. The image processing apparatus according to claim 1 , further comprising:

a vectorization processing unit configured to convert the connected component having the character attribute into vector data; and

an electronic file generation unit configured to generate an electronic file including the vector data generated by the vectorization processing unit and an image whose character portion has been filled by the character portion filling unit.

8. An image processing method comprising:

generating a plurality of quantized regions by integrating regions that are included in an input multivalued image and have similar colors, and determining connected components included in each of the generated quantized regions, and obtaining region information of the connected components, the region information including attribute information, positional information, color information and surrounding relationship information of the connected components;

acquiring the quantized regions adjacent to a connected component having the character attribute based on the region information, and determining a color used for filling the connected component having the character attribute based on a count number, the attribute information and the color information of the acquired quantized regions, and executing processing for filling the connected component having the character attribute based on the determined color; and

changing, based on the count number and the attribute information of the acquired quantized regions, a method for determining the color used for filling the connected component having the character attribute.

9. A non-transitory computer-readable storage medium storing instructions which, when executed by an image processing apparatus, cause the image processing apparatus to perform operations comprising:

generating a plurality of quantized regions by integrating regions that are included in an input multivalued image and have similar colors, and determining connected components included in each of the generated quantized regions, and obtaining region information of the connected components, the region information including attribute information, positional information, color information and surrounding relationship information of the connected components;

acquiring the quantized regions adjacent to a connected component having the character attribute based on the region information, and determining a color used for filling the connected component having the character attribute based on a count number, the attribute information and the color information of the acquired quantized regions, and executing processing for filling the connected component having the character attribute; and

changing, based on the count number and the attribute information of the acquired quantized regions, a method for determining the color used for filling the connected component having the character attribute.