Graphic data alteration to enhance online privacy
A computer alters at least one recognizable metric or text in a digitally-encoded photographic image by operating an alteration algorithm in response to user input data while preserving an overall aesthetic quality of the image and obscuring an identity of at least one individual or geographic location appearing in the image. An altered digitally-encoded photographic image prepared by the altering of the at least one recognizable metric or text in the image is stored in a computer memory. User feedback and/or automatic analysis may be performed to define parameter values of the alteration algorithm such that the alteration process achieves preservation of aesthetic qualities while obscuring an identity of interest.
1. A method, comprising:
altering selected facial recognition metrics in a digitally-encoded image of a person, by a computer operating an alteration algorithm that identifies an alteration of the selected facial recognition metrics based on a value of
Δ
=
∑
1
to
M
∂
i
_
calculated to substantially reduce risk of automatic recognition of the person while preserving an overall aesthetic quality of the image, wherein δi is a measure of metric alteration of each of a number M of the selected facial recognition metrics; and
storing, in a computer memory, an altered digitally-encoded image prepared by the altering of the selected facial recognition metrics in the digitally-encoded image.
2. The method of claim 1 , further comprising controlling at least one parameter of the alteration algorithm so as to reduce risk of automatic recognition of the person to below a defined minimum confidence level.
3. The method of claim 2 , further comprising modifying at least one parameter of the alteration algorithm in response to user input specifying the desired minimum confidence level.
4. The method of claim 2 , further comprising identifying a recognition parameter set based on an automatic recognition algorithm, wherein the recognition parameter set is defined by a set of parameter range values outside of which the recognition algorithm cannot recognize the identity above the defined minimum confidence level.
5. The method of claim 4 , further comprising defining parameter values for the alteration algorithm used in the altering of the image within the recognition parameter set.
6. The method of claim 4 , further comprising controlling at least one parameter of the alteration algorithm so as to preserve an overall aesthetic quality of the image as determined by an aesthetic quality measuring algorithm to above a defined minimum preservation level.
7. The method of claim 6 , further comprising identifying an aesthetic preservation parameter set based on an aesthetic quality measuring algorithm, wherein the aesthetic preservation parameter set is defined by a set of parameter range values outside of which the aesthetic quality measuring algorithm determines that the aesthetic quality of the image has changed in an amount that exceeds the defined minimum preservation level.
8. The method of claim 7 , further comprising determining a third set of parameter values by a set difference of the aesthetic preservation parameter set and the recognition parameter set, wherein the set difference is defined as parameter values that are members of the aesthetic preservation parameter set and are not members of the recognition parameter set.
9. The method of claim 1 , further comprising:
publishing the altered digitally-encoded image in an electronic medium;
receiving user feedback data, by a computer server via a communications network, regarding at least one of whether (a) the overall aesthetic quality of the image is preserved or (b) risk of automatic recognition of the person is sufficiently reduced.
10. The method of claim 9 , further comprising modifying at least one parameter of the alteration algorithm in response to the user feedback data.
11. The method of claim 10 , further comprising altering at least one of the selected facial recognition metrics in the digitally-encoded image, based on a modified parameter of the alteration algorithm from the modifying at least one parameter of the alteration algorithm.
12. The method of claim 1 , further comprising selecting the number M of metrics so as to lower each applied δi to below a human-perceptible threshold.
13. An apparatus comprising a processor and a memory coupled to the processor; wherein the memory holds program instructions, that when executed by the processor, causes the apparatus to perform:
altering selected facial recognition metrics in a digitally-encoded image of a person, using an alteration algorithm that identifies an alteration of the selected facial recognition metrics based on a value of
Δ
=
∑
1
to
M
∂
i
_
calculated to substantially reduce risk of automatic recognition of the person while preserving an overall aesthetic quality of the image, wherein δi is a measure of metric alteration of each of a number M of the selected facial recognition metrics; and
storing an altered digitally-encoded image prepared by the altering of the selected facial recognition metrics in the digitally-encoded image.
14. The apparatus of claim 13 , wherein the memory holds further instructions for controlling at least one parameter of the alteration algorithm so as to reduce risk of automatic recognition of the person to below a defined minimum confidence level.
15. The apparatus of claim 14 , wherein the memory holds further instructions for modifying at least one parameter of the alteration algorithm in response to user input specifying the desired minimum confidence level.
16. The apparatus of claim 14 , wherein the memory holds further instructions for identifying a recognition parameter set based on an automatic recognition algorithm, wherein the recognition parameter set is defined by a set of parameter range values outside of which the recognition algorithm cannot recognize the identity above the defined minimum confidence level.
17. The apparatus of claim 16 , wherein the memory holds further instructions for defining parameter values for the alteration algorithm used in the altering of the image within the recognition parameter set.
18. The apparatus of claim 16 , wherein the memory holds further instructions for controlling at least one parameter of the alteration algorithm so as to preserve an overall aesthetic quality of the image as determined by an aesthetic quality measuring algorithm to above a defined minimum preservation level.
19. The apparatus of claim 18 , wherein the memory holds further instructions for identifying an aesthetic preservation parameter set based on an aesthetic quality measuring algorithm, wherein the aesthetic preservation parameter set is defined by a set of parameter range values outside of which the aesthetic quality measuring algorithm determines that the aesthetic quality of the image has changed in an amount that exceeds the defined minimum preservation level.
20. The apparatus of claim 19 , wherein the memory holds further instructions for determining a third set of parameter values by a set difference of the aesthetic preservation parameter set and the recognition parameter set, wherein the set difference is defined as parameter values that are members of the aesthetic preservation parameter set and are not members of the recognition parameter set.
21. The apparatus of claim 13 , wherein the memory holds further instructions for:
publishing the altered digitally-encoded image in an electronic medium;
receiving user feedback data, by a computer server via a communications network, regarding at least one of whether (a) the overall aesthetic quality of the image is preserved or (b) risk of automatic recognition of the person is sufficiently reduced.
22. The apparatus of claim 21 , wherein the memory holds further instructions for modifying at least one parameter of the alteration algorithm in response to the user feedback data.
23. The apparatus of claim 22 , wherein the memory holds further instructions for altering at least one of the selected facial recognition metrics in the digitally-encoded image, based on a modified parameter of the alteration algorithm from the modifying at least one parameter of the alteration algorithm.
24. The apparatus of claim 13 , wherein the memory holds further instructions for selecting the number M of metrics so as to lower each applied δi to below a human-perceptible threshold.