US 11,915,143 B2
Image determination device, image determination method, and non-transitory computer readable medium storing program
Naoki Tsuchiya, Otsu (JP); Yoshihisa Ijiri, Tokyo (JP); Yu Maruyama, Tokyo (JP); Yohei Okawa, Koshigaya (JP); Kennosuke Hayashi, Tokyo (JP); and Sakon Yamamoto, Tokyo (JP)
Assigned to OMRON Corporation, Kyoto (JP)
Appl. No. 17/270,429
Filed by OMRON Corporation, Kyoto (JP)
PCT Filed Nov. 14, 2019, PCT No. PCT/JP2019/044743
§ 371(c)(1), (2) Date Feb. 22, 2021,
PCT Pub. No. WO2020/137229, PCT Pub. Date Jul. 2, 2020.
Claims priority of application No. 2018-245670 (JP), filed on Dec. 27, 2018.
Prior Publication US 2021/0312235 A1, Oct. 7, 2021
Int. Cl. G06N 3/084 (2023.01); G06F 18/214 (2023.01); G06F 18/21 (2023.01); G06V 10/762 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01)
CPC G06N 3/084 (2013.01) [G06F 18/217 (2023.01); G06F 18/2148 (2023.01); G06V 10/762 (2022.01); G06V 10/776 (2022.01); G06V 10/7747 (2022.01)] 6 Claims
OG exemplary drawing
 
1. An image determination device comprising:
a memory, configured to store a training model which outputs output data indicating a determination result related to an image to be examined on the basis of the image; and
a processor, configured to:
perform a training process which causes the training model to train to output the output data indicating label data associated with a training image in a case where the training image is input to the training model using training data including the training image and the label data;
perform a division process which divides the training data into a plurality of pieces of sub-training data;
perform a measurement process which measures the accuracy of determination in a case where the training model is trained in the training process using each of the plurality of pieces of sub-training data;
perform a selection process which selects at least one of the plurality of pieces of sub-training data on the basis of the accuracy of determinations and
in a case where a predetermined condition based on comparison between accuracy of determination when the training model is trained in the training process using the training data and the accuracy of determination when the training model is trained in the training process using the sub-training data selected in the selection process is satisfied, recursively repeat the division process, the measurement process, and the selection process.