Identification and processing of facial wrinkles in a digital image

• US 9,600,713 B2
• Filed: 04/27/2015
• Issued: 03/21/2017
• Est. Priority Date: 04/27/2015
• Status: Expired due to Fees

• Current Assignee: AprilAge Inc.
• Original Assignee: AprilAge Inc.
• Inventors: Chen, Fang, Estey, Ronald, Ellefson, Chris
• Primary Examiner(s): MARIAM, DANIEL G
• Application Number:
  US14/696,646
• Publication Number:
  US 20160314342A1
• Time in Patent Office: 694 Days
• Field of Search: 382/118, 382/218
• US Class Current: 1/1
• CPC Class Codes: G06F 3/04845 for image manipulation, e.g. dragging, rotation, expansion or change of colour
• CPC Class Codes: G06T 2207/20064 Wavelet transform [DWT]
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/162 using pixel segmentation or colour matching
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships

Abstract

A computer-implemented method of processing an input digital image is provided. The method includes forming a representation of the input digital image as wavelet components; and for each of a plurality of facial regions in the input digital image: forming a reconstructed facial region based on a subset of the wavelet components; and identifying pixels associated with facial wrinkles in the facial region as pixels In the reconstructed facial region that differ from corresponding pixels in the facial region by a first threshold amount.

Claims

1. A computer-implemented method of processing an input digital image, the method comprising:

forming a representation of the input digital image as wavelet components; and

for each of a plurality of facial regions in the input digital image;

forming a reconstructed facial region based on a subset of the wavelet components, the subset of the wavelet components for the facial region differing from a subset of the wavelet components for at least one other facial region of the plurality of facial regions; and

identifying pixels associated with facial wrinkles in the facial region as pixels in the reconstructed facial region that differ from corresponding pixels in the facial region by a first threshold amount.

2. The method of claim 1, wherein the subset of wavelet components for each of the one or more facial regions is based on a respective expected wrinkle pattern within each facial region.

3. The method of claim 2, wherein the expected wrinkle pattern comprises at least one expected wrinkle direction.

4. The method of claim 3, wherein the subset of wavelet components for each of the facial regions is absent at least one low-frequency wavelet component corresponding to at least one expected wrinkle direction.

5. The method of claim 4, wherein the subset of wavelet components for at least one of the facial regions is absent at least one low-frequency wavelet component corresponding to a plurality of expected wrinkle directions.

6. The method of claim 3, wherein the subset of wavelet components for at least one of the facial regions is absent a plurality of low-frequency wavelet components corresponding to at least one expected wrinkle direction.

7. The method of claim 3, wherein the at least one expected wrinkle direction is/are selected from the group consisting of:

horizontal direction, vertical direction, and diagonal direction.

8. The method of claim 1, wherein the first threshold amount is calculated based on the contents of the facial region.

9. The method of claim 1, further comprising:

for one or more facial region in the input digital image;

identifying pixels associated with shadows in the facial region as pixels having an intensity that is below a second threshold amount.

10. The method of claim 9, further comprising:

determining the second threshold amount adaptively.

11. The method of one of claims 1 to 10, further comprising:

forming a modified digital image based on the input digital image and modified values of pixels identified as associated with facial wrinkles.

12. The method of claim 11, wherein the forming is responsive to receipt of user instructions.

13. The method of claim 11, wherein the modified value of a pixel is based on values of a plurality of pixels in a neighborhood of the pixel.

14. The method of one of claims 11 to 13, further comprising:

forming the modified digital image also based modified values of pixels identified as associated with temple regions in the input digital image.

15. The method of claim 11 when dependent on claim 9, further comprising:

forming the modified digital image based on the input digital image and modified values of pixels identified as associated with shadows.

16. A non-transitory computer readable medium embodying a computer program executable on a computing system for processing an input digital image, the computer program comprising:

computer program code for forming a representation of the input digital image as wavelet components; and

computer program code for, for one or more of a plurality of facial regions in the input digital image;

forming a reconstructed facial region based on a subset of the wavelet components, the subset of the wavelet components for the facial region differing from a subset of the wavelet components for at least one other facial region of the plurality of facial regions; and

identifying pixels associated with facial wrinkles in the facial region as pixels in the reconstructed facial region that differ from corresponding pixels in the facial region by a first threshold amount.

17. The non-transitory computer readable medium of claim 16, wherein the computer program further comprises:

computer program code for forming a modified digital image based on the input digital image and modified values of pixels identified as associated with facial wrinkles.

18. A computing system comprising at least one processor executing instructions for processing an input digital image, the at least one processor configured therewith to form a representation of the input digital image as wavelet components and, for one or more of a plurality of facial regions in the input digital image, form a reconstructed facial region based on a subset of the wavelet components, the subset of the wavelet components for the facial region differing from a subset of the wavelet components for at least one other facial region of the plurality of facial regions, and identify pixels associated with facial wrinkles in the facial region as pixels in the reconstructed facial region that differ from corresponding pixels in the facial region by a first threshold amount.

19. The computing system of claim 18, where the at least one processor is further configured to form a modified digital image based on the input digital image and modified values of pixels identified as associated with facial wrinkles.