基于“点到面”策略的图像检索

顾广华, 霍文华, 任贤龙, 刘江涛, 苏明月

顾广华, 霍文华, 任贤龙, 刘江涛, 苏明月. 基于“点到面”策略的图像检索[J]. 信号处理, 2020, 36(9): 1464-1470. DOI: 10.16798/j.issn.1003-0530.2020.09.011
引用本文: 顾广华, 霍文华, 任贤龙, 刘江涛, 苏明月. 基于“点到面”策略的图像检索[J]. 信号处理, 2020, 36(9): 1464-1470. DOI: 10.16798/j.issn.1003-0530.2020.09.011
Gu Guanghua, Huo Wenhua, Ren Xianlong, Liu Jiangtao, Su Mingyue. "Point-to-Flat" Strategy-Based Image Retrieval[J]. JOURNAL OF SIGNAL PROCESSING, 2020, 36(9): 1464-1470. DOI: 10.16798/j.issn.1003-0530.2020.09.011
Citation: Gu Guanghua, Huo Wenhua, Ren Xianlong, Liu Jiangtao, Su Mingyue. "Point-to-Flat" Strategy-Based Image Retrieval[J]. JOURNAL OF SIGNAL PROCESSING, 2020, 36(9): 1464-1470. DOI: 10.16798/j.issn.1003-0530.2020.09.011

基于“点到面”策略的图像检索

基金项目: 国家自然科学基金(61303128);河北省自然科学基金(F2017203169);河北省高等学校科学研究项目重点项目(ZD2017080)
详细信息
  • 中图分类号: TN919.81

"Point-to-Flat" Strategy-Based Image Retrieval

  • 摘要: 图像检索是计算机视觉领域的一个重要分支。其主要目的是从图像数据库中找出与查询图像相似的语义图像。传统的图像检索方法是在查询图像和数据库图像之间进行“点到点”检索。但是,单个查询图像包含的类别提示较少,即类别信息较弱,使得检索结果并不理想。为了解决这个问题,本文提出了一种基于“点到面”的类别检索策略来扩展一个图像(点)到一个图像类别(面),这意味着从单个查询图像到整个图像类别的语义扩展。该方法挖掘了查询图像的类别信息。在两个常用的数据集上对所提出方法的性能进行了评估。实验表明,该方法可以显著提高图像检索的性能。
    Abstract: Image retrieval is an important branch of computer vision. Its main purpose is to find the similar semantic images to the query image from the image database. The traditional image retrieval method is a “point-to-point” retrieval between the query image and the database. However, a single query image contains fewer category hints, that is, the category information is weaker, and the retrieval results are not satisfactory. In this paper, the "point-to-flat" category-based retrieval strategy is proposed to extend an image (point) to an image category (flat), which means the semantic extension from the individual query image to the whole image category. The proposed method mines the category information of the query image. The performance of the proposed method is evaluated on two commonly used databases. The experimental results demonstrate that the proposed method can significantly improve the performance of image retrieval.
  • [1] Zheng Liang, Yang Yi, Tian Qi. SIFT meets CNN:A decade survey of instance retrieval[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2018, 40(5): 1224-1244.
    [2] Bhattacharyya S, Bhaumik H, De S, et al. Intelligent Analysis of Multimedia Information[M]. Hershey: IGI Global, 2017: 143-180.
    [3] Datta R, Joshi D, Jia L I, et al. Image Retrieval: Ideas, Influences, and Trends of the New Age[J]. ACM Computing Surveys, 2008, 40(2): 35-94.
    [4] Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
    [5] Christian S, Liu Wei, Jia Yangqing, et al. Going deeper with convolutions[J], IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, 1-9
    [6] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2014: 580-587.
    [7] Szegedy C, Toshev A, Erhan D. Deep Neural Networks for Object Detection[C]// Advances in Neural Information Processing Systems. 2013, 2553-2561.
    [8] Li Haoxiang, Lin Zhe, Shen Xiaohui, et al. A convolutional neural network cascade for face detection[C]// IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2015: 5325-5334.
    [9] Sun Y, Wang X, Tang X. Deep Learning Face Representation by Joint Identification-Verification[J]. Advances in neural information processing systems, 2014: 1988-1966.
    [10] Cimpoi M, Maji S, Vedaldi A. Deep convolutional filter banks for texture recognition and segmentation[J]. International Journal of Computer Vision, 2016, 118(1): 65-94.
    [11] Ghodrati A, Diba A, Pedersoli M, et al. DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers[J]. International Journal of Computer Vision, 2017, 124(2): 115-131.
    [12] Bruna J, Szlam A, Lecun Y. Signal Recovery from Pooling Representations[J]. Statistics, 2013: 307-315.
    [13] Li Jinxing, Zhang Bob, Lu Guangming, et al. Dual Asymmetric Deep Hashing Learning[J]. IEEE Access, 2018.
    [14] Ma Lei, Li Hongliang, Wu Qingbo, et al. Hierarchy Neighborhood Discriminative Hashing for An Unified View of Single-Label and Multi-Label Image retrieval[J]. 2019.
    [15] Andoni A, Indyk P. Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions[C]// 47th Annual IEEE symposium on foundations of computer science (FOCS'06). IEEE, 2006: 459-468.
    [16] Carreira-Perpinan M A, Raziperchikolaei R. Hashing with binary autoencoders[C]//IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2015.
    [17] Dai Bo, Guo Ruiqi, Kumar S, et al. Stochastic Generative Hashing[J]. International Conference on Machine Learning. 2017.
    [18] Shi Xiaoshuang, Xing Fuyong, Xu Kaidi, et al. Asymmetric discrete graph hashing[C]// In Proceedings of the AAAI Conference on Artificial Intellignece. AAAI, 2017: 2541-2547.
    [19] Li Zhao, Lu Wei, Xing Weiwei, et al. Image retrieval based on CNN visual features[J]. Journal of Beijing University of Posts and Telecommunications, 2015, 38(B06): 103-106.
    [20] Gregory G, Alex H, Pietro P. Caltech-256 object category dataset[R]. Technical Report 7694, California Institute of Technology, 2007.
    [21] James P,Ondrej C,Michael I, et al. Lost in Quantization: Improving Particular Object Retrieval in Large Scale Image Databases. [C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2008.
    [22] Li Feifei, Fergus R, Perona P. Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories[C]//Conference on Computer Vision and Pattern Recognition Workshop. IEEE, 2005.
    [23] Vedaldi A, Lenc K. MatConvNet: Convolutional Neural Networks for MATLAB[J]. In Proceedings of the 23rd ACM international conference on Multimedia. 2014: 689-692.
  • 期刊类型引用(2)

    1. 丁功鸿,黄山. 结合多特征与线性判别分析的图像检索. 计算机应用与软件. 2024(04): 212-218 . 百度学术
    2. 李薇. 基于云平台和分布式计算的大规模图像检索. 微型电脑应用. 2024(08): 211-215 . 百度学术

    其他类型引用(0)

计量
  • 文章访问数:  95
  • HTML全文浏览量:  11
  • PDF下载量:  211
  • 被引次数: 2
出版历程
  • 收稿日期:  2020-06-14
  • 修回日期:  2020-07-27
  • 发布日期:  2020-09-24

目录

    /

    返回文章
    返回