计算机与现代化 ›› 2013, Vol. 1 ›› Issue (2): 15-18.doi: 10.3969/j.issn.1006-2475.2013.02.004
• 图像处理 • 上一篇 下一篇
曹 磊,程建来
收稿日期:
修回日期:
出版日期:
发布日期:
CAO Lei, CHENG Jian-la
Received:
Revised:
Online:
Published:
摘要: 随着科技进步,包括网络图片和视频监控在内的图像数据出现了迅速的增长。如何有效管理图像数据成为一个挑战。图像聚类是图像数据管理的重要一环。本文实现Hadoop平台下尺度不变特征转换算法(Scale Invariant Feature Transform, SIFT)和K-means聚类的MapReduce并行化,并且取得不错的效果。
关键词: 并行化, 图像聚类
Abstract: As technology advances, image data is rapidly growing including images and videos on Internet. How to effectively manage the image data is a great challenge. Image clustering is an important image data managing solution. This paper proposes a solution of MapReduce parallelization about the SIFT image feature extraction and K-means clustering method on Hadoop platform. It achieves good results.
Key words: parallelization, image clustering
曹磊;程建来. 图像聚类的并行化[J]. 计算机与现代化, 2013, 1(2): 15-18.
CAO Lei;CHENG Jian-la. Parallelization of Image Clustering[J]. Computer and Modernization, 2013, 1(2): 15-18.
0 / / 推荐
导出引用管理器 EndNote|Ris|BibTeX
链接本文: http://www.c-a-m.org.cn/CN/10.3969/j.issn.1006-2475.2013.02.004
http://www.c-a-m.org.cn/CN/Y2013/V1/I2/15