Efficient indexing for large-scale image search
ICIMCS(2015)
摘要
In content-based image retrieval, inverted indexes allow fast access to database images and summarize all knowledge about the database. Indexing multiple clues of image contents allows retrieval algorithms search for relevant images from different perspectives, which is appealing to deliver satisfactory user experiences. However, when incorporating diverse image features during online retrieval, it is challenging to ensure retrieval efficiency and scalability. Besides that, most of current image indexing systems for retrieval view database as a set of individual images. It limits the flexibility of the retrieval framework to conduct sophisticated cross image analysis, resulting in higher memory consumption and sub-optimal retrieval accuracy. To conquer these two issues and achieve highly efficient indexing system, we propose a semantic-aware co-indexing algorithm to jointly embed multiple cues into the inverted indexes and a cross indexing strategy to group highly relevant image together. In this talk, these two algorithms will be introduced. A real-time large-scale image search system built on these algorithms will also be presented.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络