但是现有的检索技术多是基于底层视觉特征的检索，与人们所能理解的高层语义概念相去甚远，这严重地影响检索的实际效果。

But most information retrieval techniques are based on low-level features, which are quite different from the semantic concepts in human thought, affecting the retrieval results inevitably.

youdao

本文通过对现有基于内容图像标引及检索技术的简要介绍，提出应在现有系统中增加图像的高层语义概念描述，以更接近于人的视觉效果。

This paper introduced the technology of content based image indexing and retrieval concisely. It propose to increase high level semantic describe of image to approach visual sense of human being.

youdao

在基于内容的图像检索系统中，图像低层特征和图像所表达高层概念之间的不一致性导致系统出现语义鸿沟问题。

In content-based image retrieval systems, the inconsistency between image low-level features and the concept of high-level expressed by images lead to system semantic gap problem.

youdao