Method of improving orientation and color balance of digital images using face detection information
View Patent ↗A method of generating one or more new spatial and chromatic variation digital images uses an original digitally-acquired image which including a face or portions of a face. A group of pixels that correspond to a face within the original digitally-acquired image is identified. A portion of the original image is selected to include the group of pixels. Values of pixels of one or more new images based on the selected portion are automatically generated, or an option to generate them is provided, in a manner which always includes the face within the one or more new images. Such method may be implemented to automatically establish the correct orientation and color balance of an image. Such method can be implemented as an automated method or a semi automatic method to guide users in viewing, capturing or printing of images.
1. A method of digital image processing using face detection to achieve desired contrast and color balance of two or more detected faces, comprising:
identifying two or more groups of pixels that correspond to two or more faces within a digital image;
identifying one or more sub-groups of pixels that correspond to one or more facial features of each of the two or more faces;
determining initial values of contrast and color balance of pixels of the two or more groups of pixels based on values of said one or more sub-groups of pixels of said each of the two or more faces, including calculating luminance and chrominance characteristics of said groups;
determining initial contrast and color balance of the two or more faces within the digital image based on the initial values; and
determining adjusted values of pixels within the digital image for adjusting the contrast or color balance, or both, respectively to the desired contrast or color balance.
2. The method of claim 1 , further comprising determining which of the sub-group of pixels belong to which said group of face pixels.
3. The method of claim 1 , said determining initial values of contrast or color balance, or both, of pixels being calculated based on the luminance or chrominance characteristics, or both, of said one or more sub-groups that correspond to one or more facial features.
4. The method of claim 1 , the one or more facial features including an eye, two eyes, a mouth, lips, hair or hairline, ears, nostrils, nose bridge, eyebrows, chin, neck or a nose, or combinations thereof.
5. The method of claim 1 , wherein the one or more facial features include at least two features, and the method further comprises determining relative luminance and chrominance of the at least two features based on the initial values, and the initial values of contrast and color balance being determined based on the relative luminance and chrominance of the at least two features.
6. The method of claim 1 , further comprising:
determining initial values of relative positions, orientations and pose angles of pixels of the two or more groups of pixels based on values of said one or more sub-groups of pixels of said each of the two or more faces, including calculating spatial orientations of axes of ellipses fit to said groups;
determining initial relative positions, orientations and pose angles of the two or more faces within the digital image based on the initial values; and
determining adjusted values of pixels within the digital image for adjusting the relative positions, orientations or pose angles, or combinations thereof, respectively, to the desired relative positions, orientations or pose angles.
7. A portable image acquisition and processing device, comprising a processor, image sensor and lens to acquire digital images, and a memory having code embedded therein for programming the processor to perform a method of digital image processing using face detection to achieve desired contrast and color balance of two or more detected faces, wherein the method comprises:
identifying two or more groups of pixels that correspond to two or more faces within a digital image;
identifying one or more sub-groups of pixels that correspond to one or more facial features of each of the two or more faces;
determining initial values of contrast and color balance of pixels of the two or more groups of pixels based on values of said one or more sub-groups of pixels of said each of the two or more faces, including calculating luminance and chrominance characteristics of said groups;
determining initial contrast and color balance of the two or more faces within the digital image based on the initial values; and
determining adjusted values of pixels within the digital image for adjusting the contrast or color balance, or both, respectively to the desired contrast or color balance.
8. The device of claim 7 , wherein the method further comprises determining which of the sub-group of pixels belong to which said group of face pixels.
9. The device of claim 7 , wherein said determining initial values of contrast or color balance, or both, of pixels includes calculating based on the luminance or chrominance characteristics, or both, of said one or more sub-groups that correspond to one or more facial features.
10. The device of claim 7 , the one or more facial features including an eye, two eyes, a mouth, lips, hair or hairline, ears, nostrils, nose bridge, eyebrows, chin, neck or a nose, or combinations thereof.
11. The device of claim 7 , wherein the one or more facial features include at least two features, and the method further comprises determining relative luminance and chrominance of the at least two features based on the initial values, and the initial values of contrast and color balance being determined based on the relative luminance and chrominance of the at least two features.
12. The device of claim 7 , wherein the method further comprises:
determining initial values of relative positions, orientations and pose angles of pixels of the two or more groups of pixels based on values of said one or more sub-groups of pixels of said each of the two or more faces, including calculating spatial orientations of axes of ellipses fit to said groups;
determining initial relative positions, orientations and pose angles of the two or more faces within the digital image based on the initial values; and
determining adjusted values of pixels within the digital image for adjusting the relative positions, orientations or pose angles, or combinations thereof, respectively, to the desired relative positions, orientations or pose angles.
13. One or more non-transitory processor-readable media having code embedded therein for programming the processor to perform a method of digital image processing using face detection to achieve desired contrast and color balance of two or more detected faces, wherein the method comprises:
identifying two or more groups of pixels that correspond to two or more faces within a digital image;
identifying one or more sub-groups of pixels that correspond to one or more facial features of each of the two or more faces;
determining initial values of contrast and color balance of pixels of the two or more groups of pixels based on values of said one or more sub-groups of pixels of said each of the two or more faces, including calculating luminance and chrominance characteristics of said groups;
determining initial contrast and color balance of the two or more faces within the digital image based on the initial values; and
determining adjusted values of pixels within the digital image for adjusting the contrast or color balance, or both, respectively to the desired contrast or color balance.
14. The one or more processor-readable media of claim 13 , wherein the method further comprises determining which of the sub-group of pixels belong to which said group of face pixels.
15. The one or more processor-readable media of claim 13 , wherein said determining initial values of contrast or color balance, or both, of pixels includes calculating based on the luminance or chrominance characteristics, or both, of said one or more sub-groups that correspond to one or more facial features.
16. The one or more processor-readable media of claim 13 , the one or more facial features including an eye, two eyes, a mouth, lips, hair or hairline, ears, nostrils, nose bridge, eyebrows, chin, neck or a nose, or combinations thereof.
17. The one or more processor-readable media of claim 13 , wherein the one or more facial features include at least two features, and the method further comprises determining relative luminance and chrominance of the at least two features based on the initial values, and the initial values of contrast and color balance being determined based on the relative luminance and chrominance of the at least two features.
18. The one or more processor-readable media of claim 13 , wherein the method further comprises:
determining initial values of relative positions, orientations and pose angles of pixels of the two or more groups of pixels based on values of said one or more sub-groups of pixels of said each of the two or more faces, including calculating spatial orientations of axes of ellipses fit to said groups;
determining initial relative positions, orientations and pose angles of the two or more faces within the digital image based on the initial values; and
determining adjusted values of pixels within the digital image for adjusting the relative positions, orientations or pose angles, or combinations thereof, respectively, to the desired relative positions, orientations or pose angles.