Image processing device, image processing method, and image processing program
View Patent ↗An image processing device includes a data processing unit that processes data of a face image which is captured to include a face. The data processing unit generates an edge image by filtering the face image to detect an edge in a scanning direction, extracts a sampling value as the information regarding a gradient magnitude and whether the gradient is positive or negative from each of positions in the edge image corresponding to a plurality of points constituting the sampling curve, calculates a likelihood with respect to the sampling curve by setting points having a positive gradient and a negative gradient as likelihood evaluation targets in a first point group and a second point group, and detects a sampling curve having a maximum likelihood as a pupil or an iris among a plurality of sampling curves.
1. An image processing device comprising:
a data processing unit that processes data of a face image which is captured to include a face,
wherein the data processing unit:
generates an edge image, which stores information regarding a gradient magnitude and whether the gradient is positive or negative, by filtering the face image to detect an edge in a scanning direction;
extracts, in a state where a sampling curve including an arc-shaped curve, which is virtually positioned on a plane of a three-dimensional model, is projected on the edge image, a sampling value as the information regarding a gradient magnitude and whether the gradient is positive or negative from each of positions in the edge image corresponding to a plurality of points constituting the sampling curve;
calculates a likelihood with respect to the sampling curve by setting points having a positive gradient as likelihood evaluation targets in a first point group which is positioned on a front side in the scanning direction among the plurality of points constituting the sampling curve, and setting points having a negative gradient as likelihood evaluation targets in a second point group which is positioned on a rear side in the scanning direction among the plurality of points constituting the sampling curve; and
detects a sampling curve having a maximum likelihood as a pupil or an iris among a plurality of sampling curves.
2. The image processing device according to claim 1 ,
wherein the scanning direction in which the data processing unit detects an edge by filtering is a direction in which eyes are aligned in the face image.
3. The image processing device according to claim 2 ,
wherein the sampling curve has an arc shape and is projected on the edge image in a state where a bottom as a most swelling part of the arc faces downward in the three-dimensional model.
4. The image processing device according to claim 1 ,
wherein the data processing unit calculates a likelihood with respect to the sampling curve by adding gradient magnitudes of the points having a positive gradient in the first point group and adding gradient magnitudes of the points having a negative gradient in the second point group.
5. An image processing method using an image processing device including a data processing unit that processes data of a face image which is captured to include a face,
the image processing method comprising:
generating an edge image, which stores information regarding a gradient magnitude and whether the gradient is positive or negative, using a filter that detects an edge in the face image in a scanning direction;
extracting, in a state where a sampling curve including an arc-shaped curve, which is virtually positioned on a plane of a three-dimensional model, is projected on the edge image, a sampling value as the information regarding a gradient magnitude and whether the gradient is positive or negative from each of positions in the edge image corresponding to a plurality of points constituting the sampling curve;
calculating a likelihood with respect to the sampling curve by setting points having a positive gradient as likelihood evaluation targets in a first point group which is positioned on a front side in the scanning direction among the plurality of points constituting the sampling curve, and setting points having a negative gradient as likelihood evaluation targets in a second point group which is positioned on a rear side in the scanning direction among the plurality of points constituting the sampling curve; and
detecting a sampling curve having a maximum likelihood as a pupil or an iris among a plurality of sampling curves.
6. A non-transitory computer readable medium storing a program causing a computer to execute a process for processing an image which is captured to include a face,
the process comprising:
generating an edge image, which stores information regarding a gradient magnitude and whether the gradient is positive or negative, using a filter that detects an edge in the face image in a scanning direction;
extracting, in a state where a sampling curve including an arc-shaped curve, which is virtually positioned on a plane of a three-dimensional model, is projected on the edge image, a sampling value as the information regarding a gradient magnitude and whether the gradient is positive or negative from each of positions in the edge image corresponding to a plurality of points constituting the sampling curve;
calculating a likelihood with respect to the sampling curve by setting points having a positive gradient as likelihood evaluation targets in a first point group which is positioned on a front side in the scanning direction among the plurality of points constituting the sampling curve, and setting points having a negative gradient as likelihood evaluation targets in a second point group which is positioned on a rear side in the scanning direction among the plurality of points constituting the sampling curve; and
detecting a sampling curve having a maximum likelihood as a pupil or an iris among a plurality of sampling curves.