Linear mark detection system, linear mark detection method, and non-transitory computer readable medium storing linear mark detecting program
AssigneeNEC Corporation
InventorKazuyuki Sakurai
Life of this patent
Estimating the term…
Abstract
A linear mark detection system includes a filter value calculation unit, a filter value threshold processing unit, and a feature value output unit. The filter value calculation unit calculates, for each pixel of an image, filter values corresponding to each of a plurality of linear mark widths using pixel values inside and outside the linear mark. The filter value threshold processing unit selects the most suitable value from filter values corresponding to each of the plurality of linear mark widths as a feature value. The feature value output unit outputs, for each pixel of the image, the feature value computed by the filter value threshold processing function as the feature value corresponding to the linear mark.
Claims9
A linear mark detection system comprising:
- a linear mark width range group setting unit that sets a plurality of ranges in which a plurality of linear mark widths are formed in groups;
- a filter value calculation unit that calculates, for each pixel of an image, a plurality of filter values corresponding to each of a plurality of linear mark widths in the respective ranges using pixel values inside and outside a linear mark;
- a filter value selection unit that selects one filter value for each of the ranges from the filter values calculated by each of the plurality of linear mark widths;
- a filter value threshold processing unit that sets the one selected filter value out of a plurality of selected filter values to a feature value, the selected filter values being selected by the filter value selection unit;
- and
- a feature value output unit that outputs, for each pixel of the image, the feature value as a feature value corresponding to the linear mark,
- wherein the filter value threshold processing unit sets the one selected filter value selected in the range corresponding to the linear mark width that is smallest among the plurality of selected filter values that are equal to or larger than a threshold to the feature value.
A linear mark detection method comprising:
- setting a plurality of ranges in which the plurality of linear mark widths are formed in groups;
- calculating, for each pixel of an image, a plurality of filter values corresponding to each of a plurality of linear mark widths in the respective ranges using pixel values inside and outside a linear mark;
- selecting one filter value for each of the ranges from the filter values calculated by each of the plurality of linear mark widths;
- setting the one selected filter value out of a plurality of selected filter values to a feature value, wherein the one selected filter value is selected in the range corresponding to the linear mark width that is smallest among the plurality of selected filter values that are equal to or larger than a threshold;
- and
- outputting, for each pixel of the image, the feature value as a feature value corresponding to the linear mark.
A non-transitory computer readable medium storing a program that causes a computer to execute detection processing to detect a linear mark, wherein
- the detection processing comprises processing of:
- setting a plurality of ranges in which the plurality of linear mark widths are formed in groups;
- calculating, for each pixel of an image, a plurality of filter values corresponding to each of a plurality of linear mark widths in the respective ranges using pixel values inside and outside the linear mark;
- selecting one filter value for each of the ranges from the filter values calculated by each of the plurality of linear mark widths;
- setting the one selected filter value out of a plurality of selected filter values to a feature value, wherein the one selected filter value is selected in the range corresponding to the linear mark width that is smallest among the plurality of selected filter values that are equal to or larger than a threshold;
- and
- outputting, for each pixel of the image, the feature value as a feature value corresponding to the linear mark.
Dependencies are inferred from the claim text.