US 12,340,510 B2
Oral care based digital imaging systems and methods for analyzing attributes of a facial image portion
Amirhossein Tavanaei, Mason, OH (US); Matthew Lloyd Barker, Mason, OH (US); Faiz Feisal Sherman, Mason, OH (US); Sherrie Lee Kinderdine, Mason, OH (US); Scott Alan Hayes, Cincinnati, OH (US); David Anthony Hengehold, Florence, KY (US); Yanyan He, Beijing (CN); Yumeng Ouyang, Beijing (CN); Jiahui Li, Beijing (CN); Nataliya Gurich, Cincinnati, OH (US); and Ming Qi, Beijing (CN)
Assigned to The Procter & Gamble Company, Cincinnati, OH (US)
Filed by The Procter & Gamble Company, Cincinnati, OH (US)
Filed on Dec. 5, 2023, as Appl. No. 18/529,554.
Application 18/529,554 is a continuation of application No. 17/337,503, filed on Jun. 3, 2021, granted, now 11,978,207.
Claims priority of application No. PCT/CN2020/094342 (WO), filed on Jun. 4, 2020.
Prior Publication US 2024/0104738 A1, Mar. 28, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/00 (2017.01); A61B 1/24 (2006.01); G06Q 10/083 (2024.01); G06Q 30/0601 (2023.01); G06V 40/16 (2022.01); G16H 50/20 (2018.01)
CPC G06T 7/0014 (2013.01) [G06Q 10/083 (2013.01); G06Q 30/0631 (2013.01); G06V 40/166 (2022.01); G06V 40/171 (2022.01); G06V 40/175 (2022.01); G16H 50/20 (2018.01); A61B 1/24 (2013.01); G06T 2207/30036 (2013.01); G06T 2207/30201 (2013.01)] 19 Claims
OG exemplary drawing
 
1. An oral care digital imaging computer-implemented method for analyzing a facial image portion of a person depicted in a digital image, the method comprising the steps of:
a) obtaining a digital image comprising the facial image portion of the person;
b) analyzing the facial image portion for positive and negative attributes as defined by pixel data of the digital image;
c) generating a probability value based on the positive and negative attributes in the facial image portion in the digital image, wherein the probability value is determined by a model constructed by a machine learning system trained by a training dataset, and wherein the training dataset comprises (i) a plurality of simulated images of a facial image portion comprising more than one attribute; and (ii) an associated class definition based on the more than one attribute;
d) further generating an image description that identifies an area in the facial image portion based on the probability value; and
e) presenting the image description to a user.