US 12,299,959 B2
Method and electronic device for detecting candid moment in image frame
Gaurav Ramola, Karnataka (IN); Nikhar Maheshwari, Karnataka (IN); Aniket Devdatta Rege, Karnataka (IN); Sudha Velusamy, Karnataka (IN); Girish Kulkarni, Karnataka (IN); Sai Pranav Mathivanan, Karnataka (IN); Swadha Jaiswal, Karnataka (IN); and Pradeep Kumar Vegireddi, Karnataka (IN)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on May 13, 2022, as Appl. No. 17/743,990.
Application 17/743,990 is a continuation of application No. PCT/KR2021/019994, filed on Dec. 28, 2021.
Claims priority of application No. 202141000608 (IN), filed on Jan. 6, 2021; and application No. 202141000608 (IN), filed on Sep. 21, 2021.
Prior Publication US 2022/0277547 A1, Sep. 1, 2022
Int. Cl. G06V 10/771 (2022.01); G06V 10/75 (2022.01); G06V 10/77 (2022.01); G06V 40/10 (2022.01)
CPC G06V 10/771 (2022.01) [G06V 10/75 (2022.01); G06V 10/7715 (2022.01); G06V 40/10 (2022.01); G06V 2201/07 (2022.01)] 11 Claims
OG exemplary drawing
 
1. A method for detecting a candid moment in an image frame, the method comprising:
receiving, by an electronic device, a plurality of image frames;
determining, by the electronic device, a candid score of each image frame in the plurality of image frames using at least one Machine Learning (ML) model, wherein the candid score comprises a quantitative value of candidness present in the plurality of image frames;
determining, by the electronic device, whether the candid score of the at least one image frame in the plurality of image frames meets a threshold candid score;
identifying, by the electronic device, that a candid moment is present in the at least one image frame in response to determining that the candid score of the at least one image frame meets the threshold candid score;
displaying, by the electronic device, the at least one image frame comprising the candid moment, and
wherein determining, by the electronic device, the candid score of each image frame in the plurality of image frames using the at least one ML model, comprises:
identifying, by the electronic device, local features in the plurality of image frames;
determining, by the electronic device, a first score of the local features using the at least one ML model, wherein the first score is a quantitative value of the local features present in the plurality of image frames;
identifying, by the electronic device, global features in the plurality of image frames;
determining, by the electronic device, a second score of the global features using the at least one ML model, wherein the second score is a quantitative value of the global features present in the plurality of image frames; and
obtaining, by the electronic device, the candid score of each image frame in the plurality of image frames by providing the first score and the second score to the at least one ML model.