Granted Patent B2

US 12,586,157 · App. 18/332,861 · Granted Mar 24, 2026

Inventors: Xin Chung (Bolingbrook, IL); Bruce V. Schwartz (Bolingbrook, IL); Giorgio Patrini (Bolingbrook, IL); Ajinkya Indulkar (Bolingbrook, IL); Ghassen Chaabouni (Bolingbrook, IL); Alberto Gaona (Bolingbrook, IL); Juan Cardelino (Montevideo, UY)

Assignee: Ulta Salon, Cosmetics & Fragrance, Inc.

G06T5/50G06T5/73G06T5/77G06T7/194G06T11/10G06V10/82G06V40/162G06T2207/10024G06T2207/20021G06T2207/20084G06T2207/20212G06T2207/30201

Abstract

Claims (58)

1 . A computer-implemented image processing method, comprising:

receiving an original digital image including a face area of a person and a background area;

receiving an input parameter for modification of a feature of hair on the person;

modifying the original digital image based on the input parameter utilizing a generative neural network to create a modified digital image in which the feature of the hair on the person is modified and a portion of the face area and the background area is modified;

extracting a hair area from the modified digital image, and the face area and the background area from the original digital image; and

replacing a portion of modified face and background areas of the modified digital image with the face area and the background area from the original digital image to create a composite modified digital image that includes (i) data representing a modified feature of hair on the person as extracted from the modified digital image and (ii) data representing the face area and the background area as extracted from the original digital image.

2 . The method of claim 1 , wherein receiving the input parameter for modification of the feature of hair on the person comprises receiving a modification request for at least one of a texture of the hair, a length of the hair, a volume of the hair, and a color of the hair.

3 . The method of claim 1 , further comprising:

receiving an instruction of an area of hair on the person to modify, wherein the input parameter indicates the modification of the feature of the hair.

4 . The method of claim 1 , further comprising:

performing pre-processing of the original digital image for at least one of aligning, cropping, and resizing the original digital image prior to modifying the original digital image utilizing the generative neural network.

5 . The method of claim 1 , wherein modifying the original digital image based on the input parameter utilizing the generative neural network comprises:

modifying, by a processor utilizing a generative adversarial network (GAN), the original digital image based on the input parameter.

6 . The method of claim 1 , wherein modifying the original digital image based on the input parameter utilizing the generative neural network to create the modified digital image in which the feature of the hair on the person is modified comprises:

projecting the original digital image into a latent vector space to create a vector image;

modifying the vector image based on the input parameter utilizing the generative neural network to create a modified vector image; and

inverting the modified vector image into the modified digital image.

7 . The method of claim 1 , wherein extracting the hair area from the modified digital image, and the face area and the background area from the original digital image comprises:

performing mask segmentation of (i) the original digital image to segment the face area of the person and the background area and of (ii) the modified digital image to segment the hair area.

8 . The method of claim 1 , further comprising:

based on a comparison of the original digital image, the modified digital image, and the composite modified digital image, restoring the composite modified digital image to a photo-realistic view.

9 . The method of claim 1 , further comprising:

inpainting the composite modified digital image to preserve a photo-realistic view of the person.

10 . The method of claim 9 , wherein inpainting the composite modified digital image comprises:

based on a comparison of the original digital image, the modified digital image, and the composite modified digital image, filling in an area of the modified feature of hair within the hair area extracted from the modified digital image; and

preserving an identity of the person for a photo-realistic view of the person in the composite modified digital image.

11 . The method of claim 9 , wherein inpainting the composite modified digital image comprises:

performing segmentation of the composite modified digital image to segment the background area and the modified feature of hair into a reference hair image;

filling in an area of the modified feature of hair within the reference hair image; and

positioning the face area of the person from the original digital image into the reference hair image for a pasted reference hair image.

12 . The method of claim 11 , further comprising:

using a face segmenting mask, positioning a forehead and hairline area from the composite modified digital image into the pasted reference hair image to create a pre-output image.

13 . The method of claim 12 , further comprising:

modifying the pre-output image to include clothing based on a length of hair in the original digital image in relation to a shoulder area of the person.

14 . The method of claim 12 , further comprising:

modifying the pre-output image to include clothing based on occlusion of hair in the original digital image in relation to the person.

15 . The method of claim 1 , further comprising:

applying a sharpening filter to the composite modified digital image.

16 . The method of claim 1 , wherein receiving the input parameter for modification of the feature of hair on the person comprises receiving the input parameter for a desired color of hair, and the method further comprises:

retrieving a reference color hair image having hair of the desired color; and

wherein modifying the original digital image based on the input parameter utilizing the generative neural network to create the modified digital image in which the feature of the hair on the person is modified comprises applying the reference color hair image to the original digital image utilizing a histogram matching process to create the modified digital image having the desired color of the reference color hair image.

17 . A non-transitory computer-readable media having stored therein executable instructions, which when executed by a system including one or more processors causes the system to perform functions comprising:

receiving an original digital image including a face area of a person and a background area;

receiving an input parameter for modification of a feature of hair on the person;

modifying the original digital image based on the input parameter utilizing a generative neural network to create a modified digital image in which the feature of the hair on the person is modified and a portion of the face area and the background area is modified;

extracting a hair area from the modified digital image, and the face area and the background area from the original digital image; and

replacing a portion of modified face and background areas of the modified digital image with the face area and the background area from the original digital image to create a composite modified digital image that includes (i) data representing a modified feature of hair on the person as extracted from the modified digital image and (ii) data representing the face area and the background area as extracted from the original digital image.

18 . The non-transitory computer-readable media of claim 17 , wherein the functions further comprise:

based on a comparison of the original digital image, the modified digital image, and the composite modified digital image, restoring the composite modified digital image to a photo-realistic view.

19 . A system comprising:

one or more processors and non-transitory computer-readable media having stored therein instructions, which when executed by the one or more processors, causes the system to perform functions comprising:

receiving an original digital image including a face area of a person and a background area;

receiving an input parameter for modification of a feature of hair on the person;

modifying the original digital image based on the input parameter utilizing a generative neural network to create a modified digital image in which the feature of the hair on the person is modified and a portion of the face area and the background area is modified;

extracting a hair area from the modified digital image, and the face area and the background area from the original digital image; and

replacing a portion of modified face and background areas of the modified digital image with the face area and the background area from the original digital image to create a composite modified digital image that includes (i) data representing a modified feature of hair on the person as extracted from the modified digital image and (ii) data representing the face area and the background area as extracted from the original digital image.

20 . The system of claim 19 , wherein the functions further comprise:

inpainting the composite modified digital image to preserve a photo-realistic view of the person.

Assignments (1)

Continuity (1)

References Cited (22)