US 12,260,606 B2
Method, apparatus, and program for detecting mark by using image matching
Sang Min Park, Seongnam-si (KR); Choong Hyun Seo, Seongnam-si (KR); Jin Seo Lee, Seongnam-si (KR); Seung Ik Kim, Seongnam-si (KR); and Yo Seob Lee, Seongnam-si (KR)
Assigned to NAVER WEBTOON LTD., Seongnam-si (KR)
Filed by NAVER WEBTOON LTD., Seongnam-si (KR)
Filed on Feb. 5, 2021, as Appl. No. 17/168,526.
Application 17/168,526 is a continuation of application No. PCT/KR2019/007958, filed on Jul. 1, 2019.
Claims priority of application No. 10-2018-0091447 (KR), filed on Aug. 6, 2018.
Prior Publication US 2021/0158573 A1, May 27, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 17/00 (2006.01); G06T 3/40 (2006.01); G06T 5/50 (2006.01); G06T 7/00 (2017.01); G06T 7/90 (2017.01); G06V 10/26 (2022.01); G06V 10/44 (2022.01); G06V 10/75 (2022.01)
CPC G06V 10/273 (2022.01) [G06T 3/40 (2013.01); G06T 7/90 (2017.01); G06T 7/97 (2017.01); G06V 10/267 (2022.01); G06V 10/443 (2022.01); G06V 10/754 (2022.01)] 14 Claims
OG exemplary drawing
 
1. An apparatus for detecting marks in damaged content by using image matching, the apparatus comprising:
a processor configured to generate marked content by adding a mark to each cut of original content, the original content including a plurality of cuts that are separated from each other by a space, wherein a location of the mark added to each cut of the original content corresponds to a character of a character string indicating viewer information;
a damaged content obtaining unit configured to obtain the damaged content generated based on the marked content;
a pre-processed content generating unit configured to merge a plurality of images included in the damaged content to generate a combined image in which the plurality of images are connected to each other in a non-overlapping manner;
a matchable content generating unit configured to adjust sizes and/or locations of one or more cuts included in the combined image by comparing the plurality of cuts included in the original content and the one or more cuts included in the combined image to generate matchable content;
a matching unit configured to match the original content with the matchable content, for each cut; and
a mark detecting unit configured to detect a location of a mark present in each cut of the matchable content, but not present in a corresponding cut of the original content by comparing the matchable content with the original content, for each cut, and determine information about a leaker based on the locations of the marks on the matchable content.