Classification and organization of consumer digital images using workflow, and face detection and recognition
View Patent ↗A processor-based system operating according to digitally-embedded programming instructions performs a method including identifying a group of pixels corresponding to a face region within digital image data acquired by an image acquisition device. A set of face analysis parameter values is extracted from said face region, including a faceprint associated with the face region. First and second reference faceprints are determined for a person using reference images captured respectively in predetermined face-portrait conditions and using ambient conditions. The faceprints are analyzed to determine a baseline faceprint and a range of variability from the baseline associated with the person. Results of the analyzing are stored and used in subsequent recognition of the person in a subsequent image acquired under ambient conditions.
1. A processor-based image acquisition and processing system comprising:
an image acquisition component comprising a lens and image sensor for acquiring a digital image, and
a processing component including a processor and a memory having processor-readable code embedded therein for programming the processor to perform a method of classifying and archiving images including face regions that are acquired with an image acquisition component, wherein the method comprises:
identifying a group of pixels corresponding to a face region within digital image data acquired by the acquisition device;
extracting a set of face analysis parameter values from said face region, said set of face analysis parameter values comprising a faceprint associated with said face region that comprises a vector defined by a set of values for a set of face classifier parameters mapped into a faceprint space within one or more existing face classes or within a new face class defined as including one or more faceprints that are defined by vectors defined by a set of values that fall within a certain geometric distance of the vector defining a faceprint data range;
determining a first reference faceprint for a person using a reference image captured in predetermined face-portrait conditions;
determining a second reference faceprint for a person using a reference image captured using ambient conditions;
analyzing said first and second reference faceprints to determine a baseline faceprint and a range of variability from said baseline associated with said person; and
storing results of said analyzing and using said results in the subsequent recognition of said person in a subsequent image acquired under ambient conditions.
2. The system of claim 1 , wherein the method further comprises repeating for one or more different persons.
3. The system of claim 1 , wherein the method further comprising normalizing said face regions with respect to size.
4. The system of claim 1 , wherein the method further comprises normalizing said face regions with respect to a standard size based on one or more distances between eyes, nose or mouth, or combinations thereof.
5. The system of claim 1 , wherein the method further comprises normalizing said face regions first with respect to pose, and then with respect to orientation, and then with respect to size.
6. A method of classifying and archiving images including face regions that are acquired with an image acquisition component, wherein the method comprises:
using a processor;
identifying a group of pixels corresponding to a face region within digital image data acquired by the acquisition device;
extracting a set of face analysis parameter values from said face region, said set of face analysis parameter values comprising a faceprint associated with said face region that comprises a vector defined by a set of values for a set of face classifier parameters mapped into a faceprint space within one or more existing face classes or within a new face class defined as including one or more faceprints that are defined by vectors defined by a set of values that fall within a certain geometric distance of the vector defining a faceprint data range;
determining a first reference faceprint for a person using a reference image captured in predetermined face-portrait conditions; determining a second reference faceprint for a person using a reference image captured using ambient conditions;
analyzing said first and second reference faceprints to determine a baseline faceprint and a range of variability from said baseline associated with said person; and
storing results of said analyzing and using said results in the subsequent recognition of said person in a subsequent image acquired under ambient conditions.
7. The method of claim 6 , further comprising repeating for one or more different persons.
8. The method of claim 6 , further comprising normalizing said face regions with respect to size.
9. The method of claim 6 , further comprising normalizing said face regions with respect to a standard size based on one or more distances between eyes, nose or mouth, or combinations thereof.
10. The method of claim 6 , further comprising normalizing said face regions first with respect to pose, and then with respect to orientation, and then with respect to size.
11. One or more non-transitory computer-readable media having code embedded therein for programming a processor to perform a method of classifying and archiving images including face regions that are acquired with an image acquisition component, wherein the method comprises:
identifying a group of pixels corresponding to a face region within digital image data acquired by the acquisition device;
extracting a set of face analysis parameter values from said face region, said set of face analysis parameter values comprising a faceprint associated with said face region that comprises a vector defined by a set of values for a set of face classifier parameters mapped into a faceprint space within one or more existing face classes or within a new face class defined as including one or more faceprints that are defined by vectors defined by a set of values that fall within a certain geometric distance of the vector defining a faceprint data range;
determining a first reference faceprint for a person using a reference image captured in predetermined face-portrait conditions; determining a second reference faceprint for a person using a reference image captured using ambient conditions;
analyzing said first and second reference faceprints to determine a baseline faceprint and a range of variability from said baseline associated with said person;
storing results of said analyzing and using said results in the subsequent recognition of said person in a subsequent image acquired under ambient conditions.
12. The one or more computer-readable media of claim 11 , wherein the method further comprises repeating for one or more different persons.
13. The one or more computer-readable media of claim 11 , wherein the method further comprising normalizing said face regions with respect to size.
14. The one or more computer-readable media of claim 11 , wherein the method further comprises normalizing said face regions with respect to a standard size based on one or more distances between eyes, nose or mouth, or combinations thereof.
15. The one or more computer-readable media of claim 11 , wherein the method further comprises normalizing said face regions first with respect to pose, and then with respect to orientation, and then with respect to size.