Underline removal apparatus
To remove an underline even if a business document includes a chart or even if the underline touches a character string, provided is an underline removal apparatus that removes an underline area from binary image data including the underline area touching a character string, the underline removal apparatus including: an underline search processing unit that executes a line template matching process by setting a point on the binary image data as a starting point to set a rectangular line template, tracing pixels included in the line template, and extracting a polyline indicating underline position coordinates; and an underline removal processing unit that uses the polyline to execute a process of obtaining background borderline coordinates between the underline area and a background area and character borderline coordinates between the underline area and the character string obtained by applying an interpolation process to a part in the underline area touching the character string and to execute a process of replacing an area surrounded by the background borderline coordinates and the character borderline coordinates by a color of pixels of the background area.
1. An underline removal apparatus that removes an underline area from binary image data including the underline area touching a character string, the underline removal apparatus comprising:
an underline search processing unit that executes a line template matching process by setting a point on the binary image data as a starting point to set a rectangular line template, tracing pixels included in the line template, and extracting a polyline indicating underline position coordinates,
wherein the underline search processing unit repeats the line template matching process by setting a point on the binary image data corresponding to the end point as a new starting point to set the left edge of the rectangular line template and setting as a new end point the right edge of the rectangular line template,
the underline search processing unit detects that the rectangular line template overlaps a pixel of the background area and corrects the end point of the rectangular line template based on a result of the detection processing to generate a corrected end point, and
the underline search processing unit uses the corrected end point as the new starting point in repeating the line template matching process; and
an underline removal processing unit that uses the polyline to execute a process of obtaining background borderline coordinates between the underline area and a background area and character borderline coordinates between the underline area and the character string obtained by applying an interpolation process to a part in the underline area touching the character string and to execute a process of removing an area surrounded by the background borderline coordinates and the character borderline coordinates from the binary image data.
2. The underline removal apparatus according to claim 1 , wherein
the underline search processing unit traces pixels satisfying a predetermined number of pixels among the pixels in the line template.
3. The underline removal apparatus according to claim 1 , wherein
the underline search processing unit further traces pixels in the perpendicular direction from the polyline, and when there are more than a predetermined range of pixels satisfying a predetermined number of pixels, executes a process of determining that the polyline is a ruled line constituting a chart.
4. The underline removal apparatus according to claim 1 , wherein
the underline removal processing unit further traces pixels in the perpendicular direction from the polyline, and when there are more than a predetermined range of pixels satisfying a predetermined number of pixels, executes a process of determining that the character string touches the underline area.
5. The underline removal apparatus according to claim 1 , wherein the underline removal processing unit executes a process of removing the underline area by replacing an area surrounded by the background borderline coordinates and the character borderline coordinates by a color of pixels of the background area.
6. A non-transitory computer readable storage medium comprising instructions that when executed perform a method for removing an underline area from binary image data including the underline area touching a character string, the method comprising:
a. executing a line template matching process by:
i. setting a point on the binary image data as a starting point to set a left edge of a rectangular line template,
ii. setting as an end point a right edge of the rectangular line template,
iii. tracing pixels included in the line template,
iv. extracting a polyline indicating underline position coordinates,
v. detecting a portion of the rectangular line template which overlaps a pixel of the background area,
vi. generating a corrected end point of the rectangular line template based on a result of the detecting a portion of the rectangular line template, and
vii. using the corrected end point as the new starting point in repeating the line template matching process;
b. obtaining background borderline coordinates between the underline area and a background area and character borderline coordinates between the underline area and the character string obtained by applying an interpolation process to a part in the underline area touching the character sting from the polyline; and
c. removing an area surrounded by the background borderline coordinates and the character borderline coordinates from the binary image data.