Apparatus, method, and program for face feature point detection
First Claim
1. A face feature point detection apparatus, comprising:
- an image capturing means capturing a face image;
an edge calculating means creating a horizontal edge image by arranging horizontal edge values based on a pixel arrangement in the face image, each horizontal edge value indicating a luminance change in a horizontal direction, and creating a vertical edge image by arranging vertical edge values based on a pixel arrangement in the face image, each vertical edge value indicating a luminance change in a vertical direction, in the face image; and
a detection target determining means scanning the horizontal edge image and the vertical edge image, which are created by the edge calculating means with an image window, the image window including a horizontal edge window for scanning the horizontal edge image, the horizontal edge window being an aggregation of selected pixels formed in a predetermined shape corresponding to a horizontal edge of an inner corner of the eye or a horizontal edge of an outer corner of the eye, and including the vertical edge window for scanning the vertical edge image, the vertical edge window being an aggregation of selected pixels formed in a predetermined shape corresponding to a vertical edge of an eyelid, the horizontal edge windows corresponding to the inner and outer corners of the eye, being located at both sides of the vertical edge window at a level lower than the vertical edge window, the image window, configured by plural sub-windows, a constant positional relationship of which is maintained while scanning the edge image, the detection target determining means determining a position of the image window having a largest total weighted sum of total weighted sums to be a detection position where an eye, serving as a detection target, is present, providing that the total weighted sum is a total of each weighted sum in each sub-window, each weighed sum being calculated by multiplying the horizontal edge value which corresponds to each pixel in the horizontal edge window by a predetermined value defined on a per-pixel basis in the horizontal edge window and adding up all products of the horizontal edge value and the predetermined value and by multiplying the vertical edge value which corresponds to each pixel in the vertical edge window by a predetermined value defined on a per-pixel basis in the vertical edge window and adding up all products of the vertical edge value and the predetermined value.
1 Assignment
0 Petitions
Accused Products
Abstract
A face feature point detection apparatus includes an image capturing device, an edge calculating unit calculating edge values indicating a luminance change in a direction, and a detection target determining unit scanning an edge image, which is created by arranging the edge values for corresponding pixels based on pixel arrangement of the face images, with an image window being an aggregation of selected pixels formed in a predetermined shape, the detection target determining unit determining a position of the image window having a largest weighted sum of weighted sums to be a detection position where a detection target is present, providing that the weighted sum is calculated by multiplying the edge value which corresponds to each pixel in the image window by a predetermined value defined on a per-pixel basis and adding up all products of the edge value and the predetermined value.
17 Citations
9 Claims
-
1. A face feature point detection apparatus, comprising:
-
an image capturing means capturing a face image; an edge calculating means creating a horizontal edge image by arranging horizontal edge values based on a pixel arrangement in the face image, each horizontal edge value indicating a luminance change in a horizontal direction, and creating a vertical edge image by arranging vertical edge values based on a pixel arrangement in the face image, each vertical edge value indicating a luminance change in a vertical direction, in the face image; and a detection target determining means scanning the horizontal edge image and the vertical edge image, which are created by the edge calculating means with an image window, the image window including a horizontal edge window for scanning the horizontal edge image, the horizontal edge window being an aggregation of selected pixels formed in a predetermined shape corresponding to a horizontal edge of an inner corner of the eye or a horizontal edge of an outer corner of the eye, and including the vertical edge window for scanning the vertical edge image, the vertical edge window being an aggregation of selected pixels formed in a predetermined shape corresponding to a vertical edge of an eyelid, the horizontal edge windows corresponding to the inner and outer corners of the eye, being located at both sides of the vertical edge window at a level lower than the vertical edge window, the image window, configured by plural sub-windows, a constant positional relationship of which is maintained while scanning the edge image, the detection target determining means determining a position of the image window having a largest total weighted sum of total weighted sums to be a detection position where an eye, serving as a detection target, is present, providing that the total weighted sum is a total of each weighted sum in each sub-window, each weighed sum being calculated by multiplying the horizontal edge value which corresponds to each pixel in the horizontal edge window by a predetermined value defined on a per-pixel basis in the horizontal edge window and adding up all products of the horizontal edge value and the predetermined value and by multiplying the vertical edge value which corresponds to each pixel in the vertical edge window by a predetermined value defined on a per-pixel basis in the vertical edge window and adding up all products of the vertical edge value and the predetermined value. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A face feature point detection method, comprising:
-
an edge calculating step creating a horizontal edge image by arranging horizontal edge values based on a pixel arrangement in the face image, each edge value indicating a luminance change in a horizontal direction, and creating a vertical edge image by arranging vertical edge values based on a pixel arrangement in the face image, each vertical edge value indicating a luminance change in a vertical direction, in a face image; and a detection target determining step scanning the horizontal edge image and the vertical edge image, which are created by the edge calculating step with an image window, the image window including a horizontal edge window for scanning the horizontal edge image, the horizontal edge window being an aggregation of selected pixels formed in a predetermined shape corresponding to a horizontal edge of an inner corner of the eye or a horizontal edge of an outer corner of the eye, and including the vertical edge window for scanning the vertical edge image, the vertical edge window being an aggregation of selected pixels formed in a predetermined shape corresponding to a vertical edge of an eyelid, the horizontal edge windows corresponding to the inner and outer corners of the eye, being located at both sides of the vertical edge window at a level lower than the vertical edge window, the image window, configured by plural sub-windows, a constant positional relationship of which is maintained while scanning the edge image, the detection target determining step determining a position of the image window having a largest total weighted sum of total weighted sums to be a detection position where an eye, serving as a detection target, is present, providing that the total weighted sum is a total of each weighted sum in each sub-window, each weighed sum being calculated by multiplying the horizontal edge value which corresponds to each pixel in the horizontal edge window by a predetermined value defined on a per-pixel basis in the horizontal edge window and adding up all products of the horizontal edge value and the predetermined value and by multiplying the vertical edge value which corresponds to each pixel in the vertical edge window by a predetermined value defined on a per-pixel basis in the vertical edge window and adding up all products of the vertical edge value and the predetermined value.
-
-
9. A program stored on a non-transitory computer-readable medium instructing a computer to function as:
-
an edge calculating means creating a horizontal edge image by arranging horizontal edge values based on a pixel arrangement in the face image, each horizontal edge value indicating a luminance change in a horizontal direction, and creating a vertical edge image by arranging vertical edge values based on a pixel arrangement in the face image, each vertical edge value indicating a luminance change in a vertical direction, in the face image; and a detection target determining means scanning the horizontal edge image and the vertical edge image, which are created by the edge calculating means with an image window, the image window including a horizontal edge window for scanning the horizontal edge image, the horizontal edge window being an aggregation of selected pixels formed in a predetermined shape corresponding to a horizontal edge of an inner corner of the eye or a horizontal edge of an outer corner of the eye, and including the vertical edge window for scanning the vertical edge image, the vertical edge window being an aggregation of selected pixels formed in a predetermined shape corresponding to a vertical edge of an eyelid, the horizontal edge windows corresponding to the inner and outer corners of the eye, being located at both sides of the vertical edge window at a level lower than the vertical edge window, the image window, configured by plural sub-windows, a constant positional relationship of which is maintained between the plural sub-windows while scanning the edge image, the detection target determining means determining a position of the image window having a largest total weighted sum of total weighted sums to be a detection position where an eye, serving as a detection target, is present, providing that the total weighted sum is a total of each weighted sum in each sub-window, each weighed sum being calculated by multiplying the horizontal edge value which corresponds to each pixel in the horizontal edge window by a predetermined value defined on a per-pixel basis in the horizontal edge window and adding up all products of the horizontal edge value and the predetermined value and by multiplying the vertical edge value which corresponds to each pixel in the vertical edge window by a predetermined value defined on a per-pixel basis in the vertical edge window and adding up all products of the vertical edge value and the predetermined value.
-
Specification