US 12,125,243 B2
Inspection device, image forming apparatus, and non-transitory computer readable medium storing inspection program
Daigo Hama, Kanagawa (JP); Kiyotaka Tsuchibuchi, Kanagawa (JP); and Rina Takeuchi, Kanagawa (JP)
Assigned to FUJIFILM Business Innovation Corp., Tokyo (JP)
Filed by FUJIFILM Business Innovation Corp., Tokyo (JP)
Filed on Jun. 10, 2021, as Appl. No. 17/344,935.
Claims priority of application No. 2020-198469 (JP), filed on Nov. 30, 2020.
Prior Publication US 2022/0172400 A1, Jun. 2, 2022
Int. Cl. G06T 7/90 (2017.01); G06T 1/00 (2006.01); G06T 1/20 (2006.01); G06T 7/00 (2017.01)
CPC G06T 7/90 (2017.01) [G06T 1/0007 (2013.01); G06T 7/001 (2013.01); G06T 1/20 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An inspection device comprising:
a processor configured to
acquire image information of each of a correct image and a target image as an inspection target,
extract edge information of each of the correct image and the target image by using the acquired image information,
obtain a difference image between the correct image and the target image, and
in a case in which the correct image has an edge based on the edge information that has been extracted, set a threshold value for detecting a defect by using brightness information or color information of the correct image along with the edge information and detect a defect of the target image by using the difference image and the threshold value, wherein the threshold value differs based on the brightness of the correct image, whether the correct image has an edge, and whether the target image has an edge.
 
20. A non-transitory computer readable medium storing an inspection program causing a computer to execute:
acquiring image information of each of a correct image and a target image as an inspection target;
extracting edge information of each of the correct image and the target image by using the acquired image information;
obtaining a difference image between the correct image and the target image; and
in a case in which the correct image has an edge based on the edge information that has been extracted, setting a threshold value for detecting a defect by using brightness information or color information of the correct image along with the edge information and detecting a defect of the target image by using the difference image and the threshold value, wherein the threshold value differs based on the brightness of the correct image, whether the correct image has an edge, and whether the target image has an edge.