论文笔记(关于图像检索的总结性论文):Content-Based Image Retrieval and Feature Extraction: A Comprehensive Review(上)

放上引用:Latif, Afshan and Rasheed, Aqsa and Sajid, Umer and Jameel, Ahmed and Ali, Nouman and Ratyal, Naeem Iqbal and Zafar, Bushra and Dar, Saadat and Sajid, Muhammad and Khalil, Tehmina:Content-Based I...
摘要由CSDN通过智能技术生成

放上引用:Latif, Afshan and Rasheed, Aqsa and Sajid, Umer and Jameel, Ahmed and Ali, Nouman and Ratyal, Naeem Iqbal and Zafar, Bushra and Dar, Saadat and Sajid, Muhammad and Khalil, Tehmina:Content-Based Image Retrieval and Feature Extraction: A Comprehensive Review,Mathematical Problems in Engineering,Mathematical Problems in Engineering

这是巴基斯坦的一个团队的研究论文,因为无意中看到其实还挺全面且详细的。一切论文都不是完全正确且最新的,这里就当和大家一起基于这篇论文重新整理一下关于Content-Based 图像检索和特征抽取的种种。然后也是为了跟着这篇文章的参考文献思路,各取所需。以下内容仅代表个人观点,有问题欢迎交流。

关于什么叫 content-based,参考以下论文:

Gudivada, Venkat N., and Vijay V. Raghavan. "Content-based image retrieval systems." Computer 28.9 (1995): 18-22.

 

先看abstract我们可以知道作者写这一篇文章的目的是:

We analyzed the main aspects of various image retrieval and image representation models from low-level feature extraction to recent semantic deep-learning approaches. )e important concepts and major research studies based on CBIR and image representation are discussed in detail, and future research directions are concluded to inspire further research in this area.

比起以前使用metadata以及图像描述的检索,近年CBIR的技术得到了发展,然后他们这篇论文呢,就是为了总结从低level的特征抽出图像表现到近年的基于深度学习的图像描述和检索技术,基于图像内容解析的研究,包括对未来这个领域走向的一些预想。

下面进入introduction:

作者说,现在很多检索是基于图像描述以及用户query的关键词匹配,比如以下几篇论文:

[4] S. Yang, L. Li, S. Wang, W. Zhang, Q. Huang, and Q. Tian,“SkeletonNet: a hybrid network with a skeleton-embedding process for multi-view image representation learning,” IEEETransactions on Multimedia, vol. 1, no. 1, 2019.

[5] W. Zhao, L. Yan, and Y. Zhang, “Geometric-constrained multi-view image matching method based on semi-global optimization,” Geo-Spatial Information Science, vol. 21, no. 2,pp. 115–126, 2018.

[6] W. Zhou, H. Li, and Q. Tian, “Recent advance in contentbased image retrieval: a literature survey,” 2017, https://arxiv.

org/abs/1706.06064.

其实我个人角度(关于[4]:地址:https://ieeexplore.ieee.org/document/8695120 ,我觉得这篇作者更多是做了个multi-view subspace learning的无监督学习的方法吧。[5]的话,主要是在加入多视角遥感图像的几何特征的图像匹配方法。[6]的话,主要是一个同这篇论文性质差不多的content-based image retrieval的总结,但是总结了2003-2016年的技术,个人还是比较推荐的,地址:https://arxiv.org/pdf/1706.06064.pdf

然后作者介绍了CBIR的基础概念和所使用的特征,然后作者叙述了特征选择的背景意义:

According to theliterature, the selection of visual features for any system is dependent on the requirements of the end user.

具体的特征选择还要看用户端的需求,为了提高检索效果可能很会消耗很高的计算成本:

[19] N. Ali, Image Retrieval Using Visual Image Features and Automatic Image Annotation, University of Engineering and

Technology, Taxila, Pakistan, 2016.

[20] B. Zafar, R. Ashraf, N. Ali et al., “Intelligent image classification-based on spatial weighted histograms of concentric

circles,” Computer Sci

  • 1
    点赞
  • 13
    收藏
    觉得还不错? 一键收藏
  • 3
    评论
评论 3
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值