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
\u0394
=
\u2211
1
\u2062
\u2062
to
\u2062
\u2062
M
\u2062
\u2202
i
_
calculated to substantially reduce risk of automatic recognition of the person while preserving an overall aesthetic quality of the image, wherein \u03b4i 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 \u03b4i 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
\u0394
=
\u2211
1
\u2062
\u2062
to
\u2062
\u2062
M
\u2062
\u2202
i
_
calculated to substantially reduce risk of automatic recognition of the person while preserving an overall aesthetic quality of the image, wherein \u03b4i 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 \u03b4i to below a human-perceptible threshold.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A method for video encoding, the method comprising:
obtaining an intra-frame encoding distortion metric representative of distortion associated with a first intra-frame encoding mode for encoding a pixel block in a frame of a video sequence;
adjusting, with a processor, the intra-frame encoding distortion metric based on a characteristic associated with the pixel block to determine an adjusted intra-frame encoding distortion metric; and
comparing the adjusted intra-frame encoding distortion metric with an inter-frame encoding distortion metric representative of distortion associated with a first inter-frame encoding mode for encoding the pixel block to determine whether to use at least one of the first intra-frame encoding mode or the first inter-frame encoding mode to encode the pixel block.
2. A method as defined in claim 1, wherein the characteristic corresponds to at least one of a quantization parameter to be used to encode the pixel block, an encoding resolution for encoding the pixel block or an indication whether the pixel block is a reference block to be used for encoding other pixel blocks.
3. A method as defined in claim 1, wherein adjusting the intra-frame encoding distortion metric includes scaling the intra-frame encoding distortion metric by a scale factor selected, based on the characteristic, from a plurality of scale factors associated with a plurality of possible characteristics.
4. A method as defined in claim 3, wherein the characteristic corresponds to a quantization step size to be used to encode the pixel block, the scale factor is selected based on the quantization step size, and the value of selected scale factor is monotonically non-decreasing as a function of the value of the quantization step size.
5. A method as defined in claim 3, wherein adjusting the intra-frame encoding distortion metric further includes adjusting the intra-frame encoding distortion metric, after the scaling, by an offset selected, based on the characteristic, from a plurality of offsets associated with the plurality of possible characteristics.
6. (canceled)
7. A method as defined in claim 1, further including:
determining to use the first intra-frame encoding mode to encode the pixel block if the adjusted intra-frame encoding distortion metric is less than the inter-frame encoding distortion metric; and
determining to use the first inter-frame encoding mode to encode the pixel block if the inter-frame encoding distortion metric is less than the adjusted intra-frame encoding distortion metric.
8. A method as defined in claim 1, wherein the first intra-frame encoding mode has a lowest intra-frame encoding distortion metric from among a plurality of intra-frame encoding modes capable of being used to encode the pixel block, and the first inter-frame encoding mode has a lowest inter-frame encoding distortion metric from among a plurality of inter-frame encoding modes capable of being used to encode the pixel block.
9. A method as defined in claim 1, further including:
determining the intra-frame encoding distortion metric using original input pixels as predictors for intra-frame prediction of the pixel block performed according to the first intra-frame encoding mode; and
determining the inter-frame encoding distortion metric using reconstructed pixels as predictors for inter-frame prediction of the pixel block performed according to the first inter-frame encoding mode, the reconstructed pixels obtained by decoding a previously encoded reference block that is to be used to encode the pixel block according to the first inter-frame encoding mode.
10. At least one tangible machine readable storage medium comprising machine readable instructions which, when executed, cause a machine to at least:
adjust an intra-frame encoding distortion metric representative of distortion associated with a first intra-frame encoding mode for encoding a pixel block in a frame of a video sequence, the intra-frame encoding distortion metric to be adjusted based on a characteristic associated with the pixel block to determine an adjusted intra-frame encoding distortion metric; and
compare the adjusted intra-frame encoding distortion metric with an inter-frame encoding distortion metric representative of distortion associated with a first inter-frame encoding mode for encoding the pixel block to determine whether to use at least one of the first intra-frame encoding mode or the first inter-frame encoding mode to encode the pixel block.
11. At least one storage medium as defined in claim 10, wherein the machine readable instructions, when executed, further cause the machine to scale the intra-frame encoding distortion metric by a scale factor selected, based on the characteristic, from a plurality of scale factors associated with a plurality of possible characteristics.
12. At least one storage medium as defined in claim 11, wherein the characteristic corresponds to a quantization step size to be used to encode the pixel block, the scale factor is selected based on the quantization step size, and the value of selected scale factor is monotonically non-decreasing as a function of the value of the quantization step size.
13. At least one storage medium as defined in claim 11, wherein the machine readable instructions, when executed, further cause the machine to adjust the intra-frame encoding distortion metric, after being scaled, by an offset selected, based on the characteristic, from a plurality of offsets associated with the plurality of possible characteristics.
14. At least one storage medium as defined in claim 11, wherein the scale factor is a value greater than or equal to one.
15. A video encoder comprising:
a distortion adjuster to adjust an intra-frame encoding distortion metric representative of distortion associated with a first intra-frame encoding mode for encoding a pixel block in a frame of a video sequence, the intra-frame encoding distortion metric to be adjusted based on a characteristic associated with the pixel block to determine an adjusted intra-frame encoding distortion metric; and
a mode selector to compare the adjusted intra-frame encoding distortion metric with an inter-frame encoding distortion metric representative of distortion associated with a first inter-frame encoding mode for encoding the pixel block to determine whether to use at least one of the first intra-frame encoding mode or the first inter-frame encoding mode to encode the pixel block.
16. A video encoder as defined in claim 15, wherein the characteristic corresponds to at least one of a quantization parameter to be used to encode the pixel block, an encoding resolution for encoding the pixel block or an indication whether the pixel block is a reference block to be used for encoding other pixel blocks.
17. A video encoder as defined in claim 15, wherein the distortion adjuster is to scale the intra-frame encoding distortion metric by a scale factor selected, based on the characteristic, from a plurality of scale factors associated with a plurality of possible characteristics.
18. A video encoder as defined in claim 17, wherein the characteristic corresponds to a quantization step size to be used to encode the pixel block, the scale factor is selected based on the quantization step size, and the value of selected scale factor is monotonically non-decreasing as a function of the value of the quantization step size.
19. A video encoder as defined in claim 17, wherein the distortion adjuster is to adjust the intra-frame encoding distortion metric, after being scaled, by an offset selected, based on the characteristic, from a plurality of offsets associated with the plurality of possible characteristics.
20. A video encoder as defined in claim 17, wherein the scale factor is a value greater than or equal to one.
21. An apparatus for video encoding, the apparatus comprising:
means for obtaining an intra-frame encoding distortion metric representative of distortion associated with a first intra-frame encoding mode for encoding a pixel block in a frame of a video sequence;
means for adjusting the intra-frame encoding distortion metric based on a characteristic associated with the pixel block to determine an adjusted intra-frame encoding distortion metric; and
means for comparing the adjusted intra-frame encoding distortion metric with an inter-frame encoding distortion metric representative of distortion associated with a first inter-frame encoding mode for encoding the pixel block to determine whether to use at least one of the first intra-frame encoding mode or the first inter-frame encoding mode to encode the pixel block.
22. An apparatus as defined in claim 21, wherein the adjusting means includes means for scaling the intra-frame encoding distortion metric by a scale factor selected, based on the characteristic, from a plurality of scale factors associated with a plurality of possible characteristics.
23-25. (canceled)
26. At least one storage medium as defined in claim 10, wherein the characteristic corresponds to at least one of a quantization parameter to be used to encode the pixel block, an encoding resolution for encoding the pixel block or an indication whether the pixel block is a reference block to be used for encoding other pixel blocks.
27. A video encoder as defined in claim 15, wherein the mode selector is to:
determine to use the first intra-frame encoding mode to encode the pixel block if the adjusted intra-frame encoding distortion metric is less than the inter-frame encoding distortion metric; and
determine to use the first inter-frame encoding mode to encode the pixel block if the inter-frame encoding distortion metric is less than the adjusted intra-frame encoding distortion metric.
28. A video encoder as defined in claim 15, wherein the first intra-frame encoding mode has a lowest intra-frame encoding distortion metric from among a plurality of intra-frame encoding modes capable of being used to encode the pixel block, and the first inter-frame encoding mode has a lowest inter-frame encoding distortion metric from among a plurality of inter-frame encoding modes capable of being used to encode the pixel block.
29. A video encoder as defined in claim 15, further including a processor to:
determine the intra-frame encoding distortion metric using original input pixels as predictors for intra-frame prediction of the pixel block performed according to the first intra-frame encoding mode; and
determine the inter-frame encoding distortion metric using reconstructed pixels as predictors for inter-frame prediction of the pixel block performed according to the first inter-frame encoding mode, the reconstructed pixels obtained by decoding a previously encoded reference block that is to be used to encode the pixel block according to the first inter-frame encoding mode.