METHOD FOR FILTERING SIMILAR IMAGE BASED ON DEEP LEARNING AND APPARATUS USING SAME

摘要

Disclosed are a method of filtering a similar image based on deep learning and an apparatus using the same. According to the present invention, a method of collecting filtered image data includes the steps of: obtaining, by a computing device, first image data and recording the first image data in an image data pool; obtaining, by the computing device, second image data; using, by the computing device, the first and second image data as input values to perform an operation in a deep learning model and calculating first and second feature vectors corresponding to the first and second image data; and comparing, by the computing device, the degrees of similarity between the first and second feature vectors and, when the degree of similarity is below a predetermined value, recording the second image data in the image data pool.;COPYRIGHT KIPO 2020