CAJ | 학술논문

图像高层语义和低层视觉特征之间存在的鸿沟，是语义图像检索研究中遇到的一大难题。为了能保证图像语义提取的精度，同时避免降低提取的效率，学者们进行了大量的研究工作，主要集中在图像语义特征的提取、描述和匹配三个问题上进行研究，致力提出有效、完善的图像语义特征提取和描述方法，为语义图像检索提供新的交互式可视化框架。本文对语义图像检索的研究现状和趋势进行了综述和展望。
도상고층어의화저층시각특정지간존재적홍구，시어의도상검색연구중우도적일대난제。위료능보증도상어의제취적정도，동시피면강저제취적효솔，학자문진행료대량적연구공작，주요집중재도상어의특정적제취、묘술화필배삼개문제상진행연구，치력제출유효、완선적도상어의특정제취화묘술방법，위어의도상검색제공신적교호식가시화광가。본문대어의도상검색적연구현상화추세진행료종술화전망。
The gap between high level semantic and low level visual features has become a challenging problem in the research of semantic image retrieval. To ensure the extraction precision and avoid the reduction of efficiency, researchers have finished large amount of work to focus on the research of extraction, description and matching of image semantic features. The researchs aim at proposing new, effective, systematic methods for image semantic extraction and description, providing a new interactive visual framework for semantic image retrieval. In this paper, a review and trend of semantic image retrieval is presented in this paper.