作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 图形图像处理 • 上一篇    下一篇

基于Spark平台的人脸图像检索系统

陈新荃1,2,陈晓东1,蒋林华3   

  1. (1.中国科学院上海高等研究院,上海 201210; 2.中国科学院大学,北京 100049; 3.上海理工大学,上海 200093)
  • 收稿日期:2016-12-28 出版日期:2018-02-15 发布日期:2018-02-25
  • 作者简介:陈新荃(1991—),男,硕士研究生,主研方向为人脸识别、图像检索;陈晓东,研究员;蒋林华,教授。

Face Image Retrieval System Based on Spark Platform

CHEN Xinquan  1,2,CHEN Xiaodong  1,JIANG Linhua  3   

  1. (1.Shanghai Advanced Research Institute,Chinese Academy of Sciences,Shanghai 201210,China;2.University of Chinese Academy of Sciences,Beijing 100049,China;3.University of Shanghai for Science and Technology,Shanghai 200093,China)
  • Received:2016-12-28 Online:2018-02-15 Published:2018-02-25

摘要: 传统人脸图像检索技术处理大规模图像数据时检索效率较低。为此,基于视觉词袋模型与Spark分布式计算平台构建人脸图像检索系统。根据人脸图像空间分布特点提出局部区块划分方法,减少视觉特征数并提高流程并行度,同时结合SURF局部特征和HOG区块特征设计候选图像相似得分算法,提高检索准确率。实验结果表明,与基于Hadoop的检索系统相比,该系统索引构建和检索的效率较高,并且在海量图像数据场景下具有良好的可扩展性和并发性。

关键词: 人脸图像检索, 分布式计算, 区块匹配, 相似度, 视觉词袋模型

Abstract: Traditional face image retrieval technology has lower retrieval efficiency when processing large-scale image data.Aiming at this problem,a face retrieval system based on Bag-of-Visual-Words(BoVW) model and Spark distributed platform is constructed in this paper.A local block partition method is proposed according to the spatial distribution of a face image,so as to reduce the number of visual features and enhance parallelism.By combining the Speed-up Robust Feature(SURF) local features and Histogram of Oriented Gradient(HOG) block features,a similarity algorithm of candidate images is designed to improve the retrieval accuracy.Experimental results show that the efficiency of the index construction and image retrieval in the proposed system are higher than those of the retrieval system based on Hadoop.The proposed system also has good scalability and concurrency under the massive image data scene.

Key words: face image retrieval, distributed computing, block matching, similarity, Bag-of-Visual-Word(BoVW) model

中图分类号: