《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (9): 2845-2852.DOI: 10.11772/j.issn.1001-9081.2021071135

• 多媒体计算与计算机仿真 • 上一篇    

基于深度残差网络的迭代量化哈希图像检索方法

廖列法(), 李志明, 张赛赛   

  1. 江西理工大学 信息工程学院,江西 赣州 341000
  • 收稿日期:2021-07-01 修回日期:2021-09-07 接受日期:2021-09-13 发布日期:2021-09-18 出版日期:2022-09-10
  • 通讯作者: 廖列法
  • 作者简介:李志明(1995—),男,江西南昌人,硕士研究生,主要研究方向:图像检索;
    张赛赛(1997—),女,江西赣州人,硕士研究生,主要研究方向:图像分类。
  • 基金资助:
    国家自然科学基金资助项目(71761018)

Image retrieval method based on deep residual network and iterative quantization hashing

Liefa LIAO(), Zhiming LI, Saisai ZHANG   

  1. School of Information Engineering,Jiangxi University of Science and Technology,Ganzhou Jiangxi 341000,China
  • Received:2021-07-01 Revised:2021-09-07 Accepted:2021-09-13 Online:2021-09-18 Published:2022-09-10
  • Contact: Liefa LIAO
  • About author:LI Zhiming, born in 1995, M. S. candidate. His research interests include image retrieval.
    ZHANG Saisai, born in 1997, M. S. candidate. Her research interests include image classification.
  • Supported by:
    National Natural Science Foundation of China(71761018)

摘要:

针对现有的哈希图像检索方法表达能力较弱、训练速度慢、检索精度低,难以适应大规模图像检索的问题,提出了一种基于深度残差网络的迭代量化哈希图像检索方法(DRITQH)。首先,使用深度残差网络对图像数据进行多次非线性变换,从而提取图像数据的特征,并获得具有语义特征的高维特征向量;然后,使用主成分分析(PCA)对高维图像特征进行降维,同时运用迭代量化对生成的特征向量进行二值化处理,更新旋转矩阵,将数据映射到零中心二进制超立方体,从而最小化量化误差并得到最佳的投影矩阵;最后,进行哈希学习,以得到最优的二进制哈希码在汉明空间中进行图像检索。实验结果表明,DRITQH在NUS-WIDE数据集上,对4种哈希码的检索精度分别为0.789、0.831、0.838和0.846,与改进深度哈希网络(IDHN)相比分别提升了0.5、3.8、3.7和4.2个百分点,平均编码时间小了1 717 μs。DRITQH在大规模图像检索时减少了量化误差带来的影响,提高了训练速度,实现了更高的检索性能。

关键词: 图像检索, 深度残差网络, 迭代量化, 哈希码, 量化误差

Abstract:

Focusing on the issue that the existing hashing image retrieval methods have weak expression ability, slow training speed, low retrieval precision, and difficulty in adapting to large-scale image retrieval, an image retrieval method based on Deep Residual Network and Iterative Quantitative Hashing (DRITQH) was proposed. Firstly, the deep residual network was used to perform multiple non-linear transformations on the image data to extract features of the image data and obtain high-dimensional feature vectors with semantic features. Then, Principal Component Analysis (PCA) was used to reduce the high-dimensional image features' dimensions. At the same time, to minimize the quantization error and obtain the best projection matrix, iterative quantization was used to binarize the generated feature vectors, the rotation matrix was updated and the data was mapped to the zero-center binary hypercube. Finally, the optimal binary hash code which was used to image retrieval in the Hamming space was obtained through performing the hash learning. Experimental results show that the retrieval precisions of DRITQH for four hash codes with different lengths on NUS-WIDE dataset are 0.789, 0.831, 0.838 and 0.846 respectively, which are 0.5, 3.8, 3.7 and 4.2 percentage points higher than those of Improved Deep Hashing Network (IDHN) respectively, and the average encoding time of the proposed method is 1 717 μs less than that of IDHN. DRITQH reduces the impact of quantization errors, improves training speed, and achieves higher retrieval performance in large-scale image retrieval.

Key words: image retrieval, deep residual network, iterative quantization, hashing code, quantization error

中图分类号: