Google在2001年发布图像搜索功能时，只有2.5亿索引图像，不到10年，这个巨大的搜索功能已经可以检索超过100亿个图像了，每分钟有35小时的内容上传到YouTube。
When Google launched its image search feature in 2001, it had 250 million indexed images. Less than a decade later, the search giant has indexed over 10 billion images.
在基于图像内容的图像检索系统中，搜索引擎检索图像类似于按照相似标准来查询图像。
In content based image retrieval system, search engine retrieves the images similar standard to the Cey words query image according to a similarity measure.
通过对上面典型的图像搜索引擎的分类研究，分析了图像搜索引擎的检索模式。
The image search mode is also analyzed based on research of the typical search engine classification.
图片分类可用作图像搜索引擎的预滤波，以降低图像检索时的图像匹配数量，提高检索速度。
The image classification can be used as a pre-filter of the image search engine to reduce the amount of image matching, and speed up the image index processing.
图像视频中的文字为描述和注释图像内容提供了十分重要的信息，也是图像视频索引与检索的重要依据。
Text in image and video plays an important role in describing and annotating image content, and also provides the important clues for video index and retrieval.
传统的图像索引方法从图像数据库中按照关键字或号码，和按分类描述来检索引图像。
In traditional method of image retrieval searches images according to keys, number and sort describe from image database.
其次，本文研究了图像相似性匹配CBIR关键技术，并实现了本地CBIR检索模块，为图像搜索引擎原型系统构建起了总体框架。
Secondly, based on the key technology of CBIR researching, a local CBIR module is implemented in this thesis, which constructs a general frame for the system of image search engine.
其次，本文研究了图像相似性匹配CBIR关键技术，并实现了本地CBIR检索模块，为图像搜索引擎原型系统构建起了总体框架。
Secondly, based on the key technology of CBIR researching, a local CBIR module is implemented in this thesis, which constructs a general frame for the system of image search engine.
应用推荐