US 11,704,901 B2
Method of detecting wrinkles based on artificial neural network and apparatus therefor
Yongjoon Choe, Seoul (KR); Se Min Kim, Ansan-si (KR); Sang Wook Yoo, Seoul (KR); Chan Hyeok Lee, Seoul (KR); and Jong Ha Lee, Hwaseong-si (KR)
Assigned to LULULAB INC., Seoul (KR)
Filed by LULULAB INC., Seoul (KR)
Filed on Oct. 17, 2022, as Appl. No. 17/967,445.
Claims priority of application No. 10-2021-0117687 (KR), filed on Sep. 3, 2021; application No. 10-2022-0037541 (KR), filed on Mar. 25, 2022; and application No. 10-2022-0050797 (KR), filed on Apr. 25, 2022.
Prior Publication US 2023/0075333 A1, Mar. 9, 2023
Int. Cl. G06V 10/82 (2022.01); G06T 7/11 (2017.01); G06T 7/73 (2017.01); G06V 10/44 (2022.01); G06V 10/84 (2022.01)
CPC G06V 10/82 (2022.01) [G06T 7/11 (2017.01); G06T 7/73 (2017.01); G06V 10/454 (2022.01); G06V 10/84 (2022.01); G06T 2207/20076 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30088 (2013.01); G06V 2201/08 (2022.01)] 4 Claims
OG exemplary drawing
 
1. A wrinkle detection service providing server for providing a wrinkle detection method based on an artificial intelligence, comprising:
a data pre-processor for obtaining a skin image of a user from a skin measurement device and performing pre-processing based on feature points based on the skin image;
a wrinkle detector for inputting the skin image pre-processed through the data pre-processing into an artificial neural network and generating a wrinkle probability map corresponding to the skin image;
a data post-processor for post-processing the generated wrinkle probability map; and
a wrinkle visualization service providing unit for superimposing the post-processed wrinkle probability map on the skin image and providing a wrinkle visualization image to a user terminal of the user,
wherein the wrinkle detector comprises a wrinkle detection model that is trained using training data consisting of a training input value corresponding to a skin image of each of a plurality of users obtained from a plurality of user terminals and a training output value corresponding to the wrinkle probability map and generates the wrinkle probability map corresponding to the user based on a deep learning network consisting of a plurality of hidden layers,
and the wrinkle detector inputs the pre-processed skin image of the user into the wrinkle detection model based on a convolutional neural network (CNN), and generates a wrinkle probability map corresponding to the skin image based on output of the wrinkle detection model.