Image analysis using sub-sectional component evaluation to augment classifier usage
Images are analyzed using sub-sectional component evaluation in order to augment classifier usage. An image of an individual is obtained. The face of the individual is identified, and regions within the face are determined. The individual is evaluated to be within a sub-sectional component of a population based on a demographic or based on an activity. An evaluation of content of the face is performed based on the individual being within a sub-sectional component of a population. The sub-sectional component of a population is used for disambiguating among content types for the content of the face. A Bayesian framework that includes a conditional probability is used to perform the evaluation of the content of the face, and the evaluation is further based on a prior event that occurred.
1. A computer-implemented method for image analysis comprising:
obtaining an image of an individual;
identifying a face of the individual utilizing a multilayered analysis engine comprising a neural network that includes an input layer;
evaluating the individual to be within a sub-sectional component of a population; and
performing, using one or more processors, an evaluation of content of the face based on the evaluating of the individual to be within the sub-sectional component of the population, wherein the performing the evaluation of content of the face is based on modulating a sensitivity to an emotional content by selecting a first threshold for the evaluation that is associated with the sub-sectional component of the population.
2. The method of claim 1 further comprising disambiguating among a plurality of content types for the content of the face based on the sub-sectional component of the population.
3. The method of claim 2 wherein the disambiguating is further based on experiential context for the individual.
4. The method of claim 1 wherein the sub-sectional component is determined based on a demographic.
5. The method of claim 4 wherein the demographic includes an age, ethnicity, culture, or gender.
6. The method of claim 4 wherein the evaluating the individual to be within the sub-sectional component is based on applying image classifiers to the face.
7. The method of claim 1 wherein the sub-sectional component is determined based on an activity in which the individual is participating.
8. The method of claim 1 wherein the sub-sectional component is determined based on information pertaining to prior experiential information for the individual.
9. The method of claim 1 wherein the performing the evaluation of the content of the face is based on modifying emotion classifiers.
10. The method of claim 9 wherein the modifying is based on the individual being within the sub-sectional component of the population.
11. The method of claim 1 wherein the performing the evaluation of the content of the face is based on a Bayesian framework.
12. The method of claim 11 wherein the Bayesian framework includes a conditional probability based on the individual being within the sub-sectional component of the population.
13. The method of claim 11 wherein the performing the evaluation of content of the face is further based on a prior probability that occurred.
14. The method of claim 1 wherein the identifying further comprises identifying a second face within the image.
15. The method of claim 14 further comprising:
identifying a second face within the image;
evaluating a person associated with the second face to be within a second sub-sectional component of the population; and
performing an evaluation of content of the second face based on the evaluating of the person to be within a second sub-sectional component of the population.
16. The method of claim 15 wherein the sub-sectional component and the second sub-sectional component are identical.
17. The method of claim 14 wherein the face and the second face are from a plurality of people within the image.
18. The method of claim 1 wherein the evaluation of content of the face is based on a mental state event temporal signature.
19. The method of claim 1 further comprising:
defining a region of interest (ROI) in the image that includes the face;
extracting one or more histogram-of-oriented-gradients (HoG) features from the ROI; and
computing a set of facial metrics based on the one or more HoG features.
20. The method of claim 1 further comprising:
identifying multiple human faces within the image;
defining a region of interest (ROI) in the image for each identified human face;
extracting one or more histogram-of-oriented-gradients (HoG) features from each ROI; and
computing a set of facial metrics based on the one or more HoG features for each of the multiple human faces.
21. A computer program product embodied in a non-transitory computer readable medium for image analysis, the computer program product comprising code which causes one or more processors to perform operations of:
obtaining an image of an individual;
identifying a face of the individual utilizing a multilayered analysis engine comprising a neural network that includes an input layer;
evaluating the individual to be within a sub-sectional component of a population; and
performing an evaluation of content of the face based on the evaluating of the individual to be within the sub-sectional component of the population, wherein the performing the evaluation of content of the face is based on modulating a sensitivity to an emotional content by selecting a first threshold for the evaluation that is associated with the sub-sectional component of the population.
22. A computer system for image analysis comprising:
a memory which stores instructions;
one or more processors attached to the memory wherein the one or more processors, when executing the instructions which are stored, are configured to:
obtain an image of an individual;
identify a face of the individual utilizing a multilayered analysis engine comprising a neural network that includes an input layer;
evaluate the individual to be within a sub-sectional component of a population; and
perform an evaluation of content of the face based on the evaluating of the individual to be within the sub-sectional component of the population, wherein the performing the evaluation of content of the face is based on modulating a sensitivity to an emotional content by selecting a first threshold for the evaluation that is associated with the sub-sectional component of the population.
23. The method of claim 1 wherein the modulating is based on the evaluating of the sub-sectional component.
24. The method of claim 15 wherein the performing the evaluation of content of the second face is based on modulating a sensitivity to an emotional content by selecting a second threshold for the evaluation that is associated with the second sub-sectional component of the population, wherein the first threshold and second threshold are different.
25. The method of claim 1 wherein the sub-sectional component of the population is an ethnicity.
26. The method of claim 1 wherein the modulating a sensitivity to an emotional content includes adjusting a gain of a sensitivity to the emotional content, wherein the gain is associated with the sub-sectional component of the population.
27. The method of claim 1 wherein the input layer performs edge detection on the image.
28. The method of claim 1 wherein performing the evaluation of content of the face further includes identifying a plurality of action units.