US 11,748,450 B2
Method and system for training image classification model
Hye Rim Bae, Busan (KR); and Hye Mee Kim, Busan (KR)
Assigned to PUSAN NATIONAL UNIVERSITY INDUSTRY-UNIVERSITY COOPERATION FOUNDATION, Busan (KR)
Filed by Pusan National University Industry-University Cooperation Foundation, Busan (KR)
Filed on Mar. 4, 2021, as Appl. No. 17/191,715.
Claims priority of application No. 10-2020-0150359 (KR), filed on Nov. 11, 2020.
Prior Publication US 2022/0147771 A1, May 12, 2022
Int. Cl. G06N 3/08 (2023.01); G06F 18/21 (2023.01); G06F 18/23213 (2023.01)
CPC G06F 18/217 (2023.01) [G06F 18/23213 (2023.01); G06N 3/08 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method of training an image classification model, the method comprising:
maintaining a plurality of ground-penetrating radar (GPR) images captured by a GPR in a database;
establishing a feature value extraction model by primarily learning training data comprising a GPR image in the database and a representative feature value determined as one of feature values of the GPR image, wherein the feature value extraction model is a first model that outputs a feature value set of a new GPR image input to an image classification model;
inputting a GPR image to the feature value extraction model and acquiring a feature value set of the GPR image output from the feature value extraction model; and
establishing a feature value classification model by secondarily learning training data comprising the acquired feature value set of the GPR image and a label value to which the GPR image is classified, wherein the feature value classification model is a second model that outputs a label value of the new GPR image as a result value of the image classification model.