基于标签语义距离的图像多样化检索

Image Diversity Retrieval Based on Semantic Distance of Tags

随着互联网图像资源的爆炸式增长,用户对图像多样化检索的需求愈发强烈。本文在对比图像视觉特征和图像文本内容算法的基础上,探讨不同标签语义距离算法在多样化检索中的效果,通过实验提供一种较好的基于标签语义距离的图像多样化检索算法。

With the explosive growth of image resources on the internet, the need for image diversity retrieval is becoming stronger. Comparing the visual characteristics and context description using the image diversity retrieval, this paper discusses the effect of different semantic distance algorithms （WordNet、ESA and Google Distance） in image diversity retrieval. At the same time, an image diversity retrieval algorithm has been provided in this paper, which based on the best of the semantic distance algorithms.