首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于Hadoop平台的图像分类
引用本文:朱义明.基于Hadoop平台的图像分类[J].西南科技大学学报,2011,26(2):70-73.
作者姓名:朱义明
作者单位:西南交通大学,四川成都,610031
摘    要:随着图像数据的增加,海量的图像分类过程成为了一个耗时的过程。Hadoop是一个开源的分布式处理系统基础架构,有着优秀的海量数据处理性能。首先对Hadoop系统和编程框架进行了介绍,然后将图像分类中的海量数据处理过程在Hadoop平台上实现。与运行环境DELL powerEdge R170比较显示:基于Hadoop平台的图像分类在小图特征提取处理上Hadoop平台优势不明显,但对于大图特征提取、向量运算和kNN运算,耗时大大缩短,数据处理能力的优势明显。

关 键 词:Hadoop平台  图像分类  kNN运算

Image Classification Based on Hadoop Platform
ZHU Yi-ming.Image Classification Based on Hadoop Platform[J].Journal of Southwest University of Science and Technology,2011,26(2):70-73.
Authors:ZHU Yi-ming
Institution:ZHU Yi-ming (Southwest Jiaotong University,Chengdu 610031,Sichuan,China)
Abstract:As the numbers of images rapidly increasing,image classification itself has become a time consumer process.Hadoop is an open-source distributed-processing platform and an expert at processing immense amounts of data.First,we introduced Hadoop platform and programming process;Second,we implemented immense amounts of data process upon the Hadoop platform.Compared with operational environment DELL power Edge R170,image classification based on Hadoop platform has less advantages in small image feature extractio...
Keywords:Hadoop plateform  Image classification  kNN operation  
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号