Method, system and computer program product for generating recommendations for products and treatments

• US 9,760,935 B2
• Filed: 05/20/2015
• Issued: 09/12/2017
• Est. Priority Date: 05/20/2014
• Status: Active Grant

• Current Assignee: L'Oreal SA
• Original Assignee: ModiFace Incorporated (L'Oreal SA)
• Inventors: Aarabi, Parham
• Primary Examiner(s): Strege, John
• Application Number:
  US14/717,928
• Publication Number:
  US 20150339757A1
• Time in Patent Office: 846 Days
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

The present invention is a method, system and computer prod act operable to receive one or more images and/or video and to utilize such images/video to generate an analysis that is the basis tor recommendations for products and/or treatments provided to a user. The invention generates statistical analysis particular to person shown in the images/video. The statistical information may be displayed to a user. This statistical analysis may be utilized by the invention to generate recommendations for products and/or treatments for the person shown in the images/video. The invention may further generate an image showing the result of an application of a product or treatment to the person shown in the video. The invention may be provided to a user on a computing device, such as, for example as an App on a mobile device.

Claims

1. A method for recommending one or more products to a user:

(a) receiving a plurality of digital images showing a person provided by the user;

(b) detecting a face of the person in the plurality of digital images;

(c) establishing a plurality of regions of interest in the face in the plurality of digital images;

(d) detecting one or more features in the plurality of regions of interest in the face in the plurality of digital images, said one or more features including one or more facial features of interest and one or more other facial features, involving the use of image gradient intensities to detect a plurality of individual features if the location of features in the plurality of digital Images is not previously established;

(e) performing multi-level statistical analysis of the plurality of digital images to produce user information;

(f) displaying user information to the user; and

(g) recommending one or more products to the user, based on a database of products reviewed in accordance with the multi-level statistical analysis.

2. The method of claim 1, further comprising the step of:

modifying a digital image from the plurality of digital images by modifying one or more features in the face in the digital image by combining the one or more features in the digital image with corresponding features in relating to the one or more products recommended to the user by blending the one or more features relating to the one or more products recommended to the user into the digital image, thereby defining a modified digital image.

3. The method of claim 1 wherein the features include eyes, eyebrows, nose, mouth, lips or hair.

4. The method of claim 1 further comprising blending, recoloring, shifting or resizing the one or more features in the face in the second digital image.

5. The method of claim 1 further comprising adjusting size and location of the one or more features in the face in the second digital image in the modified digital image to increase the perceived beauty of a face in the modified digital image.

6. The method of claim 1 farther comprising color adjusting the one or more features in the face in the second digital image to correspond with the face in the first digital image, or color adjusting the features of the face in the first digital image to correspond to the modified first digital image.

7. The method of claim 5 comprising the further step of undertaking the multi-level statistical analysis of the plurality of digital images to incorporate analysis of the plurality of digital images as individual images and as a collection of images.

8. The method of claim 7 comprising the further step, of assigning a vote to each of the plurality of images and the vote is binary or real-valued.

9. The method of claim 8 comprising the further step of generating a neural network connection through use of the vote being real-valued.

10. The method of claim 5 wherein the plurality of digital images are derived from video, by the step of detecting a plurality of video frames in the video that show the person.

11. A system for recommending one or more products to a user comprising:

(a) a computer linked to a database, the computer including or being linked to a utility for enabling one or more users upload, store, retrieve, email, display and/or manage digital images;

(b) a processing utility linked to the computer, the processing utility being operable to provide instructions to the computer that enable the computer to;

(i) receive a plurality of digital images showing a person provided by the user;

(ii) defect a face of the person in the plurality of digital images;

(iii) establish a plurality of regions of interest in the face in the plurality of digital images;

(iv) detect one or more features in the plurality of regions of interest in the face in the plurality of digital images, said one or more features including one or more facial features of interest and one or more other facial features, involving the use of image gradient intensities to detect a plurality of individual features if the location of features in the plurality of digital images is not previously established;

(v) perform multi-level statistical analysis of the plurality of digital images to produce user information;

(vi) display user information to the user; and

(vii) recommend one or more products to the user, based on a database of products reviewed in accordance with the multi-level statistical analysis.

12. The system of claim 11, wherein the processing utility is operable to provide instructions to the computer that enable the computer to modify one or more features in the face in the digital image by combining the one or more features in the digital image with corresponding features in relating to the one or more products recommended to the user by blending the one or more features relating to the one or more products recommended to the user into the digital image, thereby defining a modified digital image.

13. The system of claim 11, wherein the system is provided to the user as a website or as an application on a mobile computing device.

14. The system of claim 11, wherein the system is operable to apply the multi-level statistical analysis to the plurality of digital images, said multi-level statistical analysis incorporating an analysis of the plurality of digital images as individual images and as a collection of images.

15. The system of claim 14, wherein the system the multi-level statistical analysis involves the system assign, a vote to each of the plurality of images and the vote is binary or real-valued.

16. The system of claim 15, wherein the vote is real-valued and a neural network connection is generated based upon said vote.

17. The system of claim 11, wherein the plurality of digital images are derived from video, by the step of detecting a plurality of video frames in the video that show the person.

18. A non-transitory computer readable medium for recommending one or more products to a user, said non-transitory computer readable medium comprising;

(a) a computer readable medium bearing software instructions; and

(b) the software instructions for enabling the computer to perform, predetermined operations, the predetermined operations including the steps of;

(i) receiving a plurality of digital images showing a person provided by the user;

(ii) detecting a face of the person in the plurality of digital images;

(iii) establishing a plurality of regions of interest in the face in the plurality of digital images;

(iv) detecting one or more features in the plurality of regions of interest in the face in the plurality of digital images, said one or more features including one or more facial features of interest and one or more other facial features, involving the use of image gradient intensities to detect a plurality of individual features if the location of features in the plurality of digital images is not previously established;

(v) performing multi-level statistical analysis of the plurality of digital images to produce user information;

(vi) displaying user information to the user; and

(vii) recommending one or more products to the user, based on a database of products reviewed in accordance with the multi-level statistical analysis.

19. The non-transitory computer readable medium of claim 18, wherein the software instructions include predetermined operations including the step of:

modifying a digital image from the plurality of digital images by modifying one or more features in the face in the digital image by combining the one or more features in the digital image With corresponding features in relating to the one or more products recommended to the user by blending the one or more features relating to the one or more products recommended to the user into the digital image, thereby defining a modified digital image.

20. The non-transitory computer readable medium of claim 18, wherein the non-transitory computer readable medium is operable to apply the multi-level statistical analysis to the plurality of digital images, said multi-level statistical analysis:

(a) incorporating an analysis of the plurality of digital images as individual images and as a collection of images;

(b) assigning a vote to each of the plurality of images and the vote is binary or real-valued, said vote being real-valued; and

(c) generating a neural network connection based upon the vote.