In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) will be discontinued after Dec. 31st, 2024.
See More
Technology of Graphic & Image
|
App. Res. of Comp. Printed Article
Vol. 37, 2020 No. 9
2866-2870

Multi-scale feature map matching for image representation

Zhu Jie1
Wu Shufang2
1. Dept. of Information Management, National Police University for Criminal Justice, Baoding Hebei 071000, China
2. College of Management, Hebei University, Baoding Hebei 071000, China
DOI: 10.19734/j.issn.1001-3695.2019.05.0164

Abstract

Spatial pyramid pooling method integrates spatial information into the generation of deep features based on the convolutional neural network, and the corresponding image representation can effectively enhance the retrieval performance. However, spatial pyramid pooling method causes the information described between the different dimensions in the image representations duplicated and the image contents described by the same dimension unmatched. This paper proposed a multi-scale feature map matching(MFMM) based image representation. First, it proposed a feature map selection algorithm which used the variance and covariance matrix of deep features, so as to improve the independence of different dimensions in image representation. Second, according to the characteristic that the high response value positions in the same feature maps of the same channel had higher matching score, it proposed an optimal feature map center selection method based on the deep feature with the maximum response in the activation map. Finally, it extracted deep features with spatial information according to the selected centers and multi-scale windows sampling for representing images. The experimental results demonstrate that the proposed method achieves excellent results in image retrieval tasks.

Foundation Support

国家自然科学基金资助项目(61802269)
河北省自然科学基金青年基金资助项目(F2018511002)
中央司法警官学院校级科研项目(XYZ201602)
河北省高等学校科学技术研究项目(Z2019037)
河北大学中西部提升综合实力专项
河北大学高层次创新人才科研启动经费项目
河北省高等学校科学技术研究青年基金项目(QN2018251)
河北省高等学校科学研究项目青年基金项目(QN2018084)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2019.05.0164
Publish at: Application Research of Computers Printed Article, Vol. 37, 2020 No. 9
Section: Technology of Graphic & Image
Pages: 2866-2870
Serial Number: 1001-3695(2020)09-063-2866-05

Publish History

[2020-09-05] Printed Article

Cite This Article

朱杰, 吴树芳. 基于多尺度特征映射匹配的图像表示方法 [J]. 计算机应用研究, 2020, 37 (9): 2866-2870. (Zhu Jie, Wu Shufang. Multi-scale feature map matching for image representation [J]. Application Research of Computers, 2020, 37 (9): 2866-2870. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)