메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(계명대학교) (계명대학교) (계명대학교) (계명대학교) (계명대학교) (계명대학교)
저널정보
대한전자공학회 대한전자공학회 학술대회 2023년도 대한전자공학회 하계학술대회 논문집
오류 신고하기

피인용 0

검색

    초록·키워드

    This paper proposes a new image clustering system for travel application that combines the VAE (Variational Auto Encoder) algorithm for the encoder part and unsupervised learning. The encoder part of the VAE algorithm, which extracts features from images, is shown to outperform the image feature extraction performance of conventional CNNs (Convolutional Neural Networks). Although the VAE algorithm is suitable for feature extraction, it is not well-suited for image classification based on those features. Therefore, in this paper, a new algorithm called VC(VAE Cluster) is proposed by combining the VAE algorithm"s encoder with a clustering algorithm to classify the features extracted by the VAE algorithm. The proposed method leverages the features extracted by the VAE algorithm to perform classification, allowing images with similar features to be grouped together. This advantage enables image clustering without the need for manual labeling of each individual image. Through various tests, the proposed method demonstrates superior clustering performance compared to other existing methods.

    최근 본 자료 전체보기