Methods and apparatuses for half-face detection
View Patent ↗Classifier chains are used to determine quickly and accurately if a window or sub-window of an image contains a right face, a left face, a full face, or does not contain a face. After acquiring a digital image, an integral image is calculated based on the acquired digital image. Left-face classifiers are applied to the integral image to determine the probability that the window contains a left face. Right-face classifiers are applied to the integral image to determine the probability that the window contains a right face. If the probability of the window containing a right face and a left face are both greater than threshold values, then it is determined that the window contains a full face. Alternatively, if only one of the probabilities exceeds a threshold value, then it may be determined that the window contains only a left face or a right face.
1. A method comprising steps of:
determining a left-face probability based at least in part on an application of one or more left-face classifiers to an image;
determining a right-face probability based at least in part on an application of one or more right-face classifiers to the image;
selecting a particular characterization of the image, from a plurality of supported characterizations of the image, based at least in part on both the left-face probability and the right-face probability, wherein the plurality of supported characterizations include at least:
(a) the image contains a left face without a visible right face, and
(b) the image contains a right face without a visible left face; and
wherein the steps are performed by an automated device.
2. The method of claim 1 , further comprising:
determining that a result of an application of the left-face classifiers and the right-face classifiers to the image contradicts a result of an application of a full-face classifier to the image; and
in response to determining that the result of the application of the left-face classifiers and the right-face classifiers to the image contradicts the result of the application of the full-face classifier to the image, performing additional analysis relative to the image to determine whether the image contains a left face only, a right face only, a full face, or no face.
3. The method of claim 1 , further comprising:
calculating at least one of the right-face classifiers based on at least one of the left-face classifiers.
4. The method of claim 1 , further comprising:
identifying, within the image, a region that contains at least a specified proportion of skin-toned pixels;
wherein the application of the one or more left-face classifiers to the image consists of an application of the one or more left-face classifiers only to said region; and
wherein the application of the one or more right-face classifiers to the image consists of an application of the one or more right-face classifiers only to said region.
5. The method of claim 4 , wherein said image is a first image, and further comprising:
after identifying, within the first image, the region that contains the at least a specified proportion of skin-toned pixels, adjusting parameters of a face-detection algorithm based on luminance characteristics of pixels within the region and applying said face-detection algorithm to a second image that differs from said first image.
6. The method of claim 1 , further comprising:
incrementally adjusting a camera's exposure over time until application of the left-face classifiers and right-face classifiers results in a detection of at least a portion of a face within the image.
7. The method of claim 1 , wherein determining the left-face probability based at least in part on the application of the one or more left-face classifiers to an image comprises:
applying, to the image, a first left-face classifier that is designed to detect a presence of a first feature in the image; and
only if the first left-face classifier returns a result that indicates that the first left-face classifier detected the presence of the first feature in the image, applying, to the image, a second left-face classifier that is designed to detect a presence, in the image, of a second feature that differs from the first feature;
wherein the application of the first left-face classifier is less computationally expensive than the application of the second left-face classifier.
8. The method of claim 1 wherein the plurality of supported characterizations further include at least:
(c) the image contains a full face, and
(d) the image does not contain a face.
9. The method of claim 8 , further comprising determining that the image contains a full face by:
determining that the image prospectively contains a full face due to the left-face probability exceeding a first specified threshold and the right-face probability exceeding a second specified threshold; and
verifying that the image contains a full face by receiving a positive result from an application of a full-face classifier to the image.
10. The method of claim 8 , further comprising determining that the image contains a left face without a right face by:
determining that the image prospectively contains a left face without a right face due to the left-face probability exceeding a first specified threshold and the right-face probability failing to exceed a second specified threshold; and
verifying that the image does not contain a full face by receiving a negative result from an application of a full-face classifier to the image.
11. The method of claim 8 , further comprising determining that the image contains no face by:
determining that the image prospectively contains no face due to the left-face probability failing to exceed a first specified threshold and the right-face probability failing to exceed a second specified threshold; and
verifying that the image does not contain a full face by receiving a negative result from an application of a full-face classifier to the image.
12. A volatile or non-volatile computer-readable storage medium storing instructions which, when executed by one or more processors, cause the processors to perform steps comprising:
determining a left-face probability based at least in part on an application of one or more left-face classifiers to an image;
determining a right-face probability based at least in part on an application of one or more right-face classifiers to the image;
selecting a particular characterization of the image, from a plurality of supported characterizations of the image, based at least in part on both the left-face probability and the right-face probability, wherein the plurality of supported characterizations include at least:
(a) the image contains a left face without a visible right face, and
(b) the image contains a right face without a visible left face.
13. The computer-readable storage medium of claim 12 , wherein the steps further comprise:
determining that a result of an application of the left-face classifiers and the right-face classifiers to the image contradicts a result of an application of a full-face classifier to the image; and
in response to determining that the result of the application of the left-face classifiers and the right-face classifiers to the image contradicts the result of the application of the full-face classifier to the image, performing additional analysis relative to the image to determine whether the image contains a left face only, a right face only, a full face, or no face.
14. The computer-readable storage medium of claim 12 , wherein the steps further comprise:
calculating at least one of the right-face classifiers based on at least one of the left-face classifiers.
15. The computer-readable storage medium of claim 12 , wherein the steps further comprise:
identifying, within the image, a region that contains at least a specified proportion of skin-toned pixels;
wherein the application of the one or more left-face classifiers to the image consists of an application of the one or more left-face classifiers only to said region; and
wherein the application of the one or more right-face classifiers to the image consists of an application of the one or more right-face classifiers only to said region.
16. The computer-readable storage medium of claim 15 , wherein said image is a first image, and wherein the steps further comprise:
after identifying, within the first image, the region that contains the at least a specified proportion of skin-toned pixels, adjusting parameters of a face-detection algorithm based on luminance characteristics of pixels within the region and applying said face-detection algorithm to a second image that differs from said first image.
17. The computer-readable storage medium of claim 12 , wherein the steps further comprise:
incrementally adjusting a camera's exposure over time until application of the left-face classifiers and right-face classifiers results in a detection of at least a portion of a face within the image.
18. The computer-readable storage medium of claim 12 , wherein determining the left-face probability based at least in part on the application of the one or more left-face classifiers to an image comprises:
applying, to the image, a first left-face classifier that is designed to detect a presence of a first feature in the image; and
only if the first left-face classifier returns a result that indicates that the first left-face classifier detected the presence of the first feature in the image, applying, to the image, a second left-face classifier that is designed to detect a presence, in the image, of a second feature that differs from the first feature;
wherein the application of the first left-face classifier is less computationally expensive than the application of the second left-face classifier.
19. The computer-readable storage medium of claim 12 , wherein the plurality of supported characterizations further include at least:
(c) the image contains a full face, and
(d) the image does not contain a face.
20. The computer-readable storage medium of claim 19 , further comprising determining that the image contains a full face by:
determining that the image prospectively contains a full face due to the left-face probability exceeding a first specified threshold and the right-face probability exceeding a second specified threshold; and
verifying that the image contains a full face by receiving a positive result from an application of a full-face classifier to the image.
21. The computer-readable storage medium of claim 19 , further comprising determining that the image contains a left face without a right face by:
determining that the image prospectively contains a left face without a right face due to the left-face probability exceeding a first specified threshold and the right-face probability failing to exceed a second specified threshold; and
verifying that the image does not contain a full face by receiving a negative result from an application of a full-face classifier to the image.
22. The computer-readable storage medium of claim 19 , further comprising determining that the image contains no face by:
determining that the image prospectively contains no face due to the left-face probability failing to exceed a first specified threshold and the right-face probability failing to exceed a second specified threshold; and
verifying that the image does not contain a full face by receiving a negative result from an application of a full-face classifier to the image.
23. A digital camera comprising:
an image capturing and storing module;
a left-face classifier module that determines a left-face probability based at least in part on an application of one or more left-face classifiers to an image;
a right-face classifier module that determines a right-face probability based at least in part on an application of one or more right-face classifiers to the image; and
an image labeling module that selects a particular characterization of the image, from a plurality of supported characterizations of the image, based at least in part on both the left-face probability and the right-face probability, wherein the plurality of supported characterizations include at least:
(a) the image contains a left face without a visible right face, and
(b) the image contains a right face without a visible left face.
24. The digital camera of claim 23 , further comprising:
an analytical modules that (a) determines that a result of an application of the left-face classifiers and the right-face classifiers to the image contradicts a result of an application of a full-face classifier to the image and (b) in response to determining that the result of the application of the left-face classifiers and the right-face classifiers to the image contradicts the result of the application of the full-face classifier to the image, performs additional analysis relative to the image to determine whether the image contains a left face only, a right face only, a full face, or no face.
25. The digital camera of claim 23 , further comprising:
a classifier-generating module that calculates at least one of the right-face classifiers based on at least one of the left-face classifiers.
26. The digital camera of claim 23 , further comprising:
a tone-identifying module that identifies, within the image, a region that contains at least a specified proportion of skin-toned pixels;
wherein the application of the one or more left-face classifiers to the image consists of an application of the one or more left-face classifiers only to said region; and
wherein the application of the one or more right-face classifiers to the image consists of an application of the one or more right-face classifiers only to said region.
27. The digital camera of claim 26 , wherein said image is a first image, and further comprising:
an algorithm-adjustment module which, after identifying, within the first image, the region that contains the at least a specified proportion of skin-toned pixels, adjusts parameters of a face-detection algorithm based on luminance characteristics of pixels within the region and an application of said face-detection algorithm to a second image that differs from said first image.
28. The digital camera of claim 23 , further comprising:
an exposure-adjustment module that incrementally adjusts a camera's exposure over time until application of the left-face classifiers and right-face classifiers results in a detection of at least a portion of a face within the image.
29. The digital camera of claim 23 , wherein determining the left-face probability based at least in part on the application of the one or more left-face classifiers to an image comprises:
applying, to the image, a first left-face classifier that is designed to detect a presence of a first feature in the image; and
only if the first left-face classifier returns a result that indicates that the first left-face classifier detected the presence of the first feature in the image, applying, to the image, a second left-face classifier that is designed to detect a presence, in the image, of a second feature that differs from the first feature;
wherein the application of the first left-face classifier is less computationally expensive than the application of the second left-face classifier.
30. The digital camera of claim 23 , wherein the plurality of supported characterizations further include at least:
(c) the image contains a full face, and
(d) the image does not contain a face.
31. The digital camera of claim 30 , further comprising determining that the image contains a full face by:
determining that the image prospectively contains a full face due to the left-face probability exceeding a first specified threshold and the right-face probability exceeding a second specified threshold; and
verifying that the image contains a full face by receiving a positive result from an application of a full-face classifier to the image.
32. The digital camera of claim 30 , further comprising determining that the image contains a left face by:
determining that the image prospectively contains a left face without a right face due to the left-face probability exceeding a first specified threshold and the right-face probability failing to exceed a second specified threshold; and
verifying that the image does not contain a full face by receiving a negative result from an application of a full-face classifier to the image.
33. The digital camera of claim 30 , further comprising determining that the image contains a no face by:
determining that the image prospectively contains no face due to the left-face probability failing to exceed a first specified threshold and the right-face probability failing to exceed a second specified threshold; and
verifying that the image does not contain a full face by receiving a negative result from an application of a full-face classifier to the image.
34. A method comprising steps of:
determining a left-face probability based at least in part on an application of a particular left-face classifier of a plurality of left-face classifiers to an image,
wherein each left-face classifier of the plurality of left-face classifiers includes a left-face classifier threshold,
wherein the particular left-face classifier includes a first left-face classifier threshold that is different than a second left-face classifier threshold;
determining whether the left-face probability is equal to or greater than the first left-face classifier threshold;
determining a right-face probability based at least in part on an application of a particular right-face classifier of a plurality of right-face classifiers to the image,
wherein each right-face classifier of the plurality of right-face classifiers includes a right-face classifier threshold,
wherein the particular right-face classifier includes a first right-face classifier threshold that is different than a second right-face classifier threshold;
determining whether the right-face probability is equal to or greater than the first right-face classifier threshold;
based at least in part whether the left-face probability is equal to or greater than the first left-face classifier threshold and whether the right-face probability is equal to or greater than the first right-face classifier threshold, determining which one of the following is true relative to the image:
(a) the image contains a full face,
(b) the image contains a left face without a right face,
(c) the image contains a right face without a left face, or
(d) the image does not contain a face;
wherein the steps are performed by an automated device.