Character region extracting apparatus and method using character stroke width calculation

摘要

A character region extracting apparatus and method which extract a character region through the calculation of character stroke widths are provided. The method includes producing a binary image including a candidate character region from an original image; extracting a character outline from the candidate character region; acquires character outline information for the extracted outline; setting a representative character stroke width and a representative character angle in each of the pixels forming the outline, based on the character outline information; and determining a character existing region in the candidate character region by confirming the ratio of effective representative stroke widths and effective angles as compared to the entire length of the outline. Accordingly, it is possible to efficiently determine whether one or more characters exist in the candidate character region.

主权项

1. A character region extracting apparatus which extracts a character region through character stroke width calculation, the character region extracting apparatus comprising:
a candidate character region detecting unit for producing a binary image including a candidate character region from an original image; a character outline information acquisition unit for extracting a character outline from the candidate character region, and acquiring character outline information for the extracted outline; a character region information acquisition unit for setting a representative character stroke width and a representative character angle in each pixel forming the outline, on the basis of the character outline information; and a character region determining unit for determining a character existing region in the candidate character region by detecting a first area of pixels in the outline where the representative character angle varies within a first tolerance, detecting a second area of pixels within the detected first area where the representative character stroke width varies within a second tolerance, and determining the detected second area is the character existing region if the ratio of the length of the detected second area to the entire length of the outline is not less than a preset ratio, wherein the representative character stroke width is a shortest stroke width among a plurality of stroke widths from a specific pixel to a pixel on the character outline, and wherein the representative character angle is an angle corresponding to the representative character stroke.