인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
개인구독
소속 기관이 없으신 경우, 개인 정기구독을 하시면 저렴하게
논문을 무제한 열람 이용할 수 있어요.
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 저자정보
초록·키워드
In response to the problem of high image similarity in traditional tourism image retrieval, a tourism image retrieval method based on attention mechanism improved deep residual shrinkage network was proposed. The study first utilized deactivation mechanisms and activation functions to improve the deep residual shrinkage network, and applied it to feature extraction in tourism images. Then, based on the improvement of the network, attention mechanism was introduced to construct a retrieval model. The results showed that the average accuracy and consistency of the retrieval model in image dimensionality reduction were 95.18% and 89.55%, respectively. At the same time, the training loss value and image retrieval accuracy in both datasets were 0.21, 0.16, and 94.52% and 90.88%, respectively. And the precision and recall of the image were 92.61% and 96.48%, respectively, which were better than the comparison method. This indicated that the retrieval model could effectively improve the feature representation and retrieval performance of tourism images, while enhancing its robustness to noise and interference. The research aimed to provide a new and effective solution for tourism image retrieval.
본문·목차
인공지능 문자 인식 모델을 통해 추출된 텍스트로, 일부 오타나 오류가 포함될 수 있으나 지속적으로 개선 중입니다.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
최근 본 자료 전체보기
UCI(KEPA) : I410-151-25-02-093686240