Computer Optics
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Computer Optics:
Year:
Volume:
Issue:
Page:
Find






Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register


Computer Optics, 2017, Volume 41, Issue 3, Pages 422–430
DOI: https://doi.org/10.18287/2412-6179-2017-41-3-422-430
(Mi co402)
 

This article is cited in 19 scientific papers (total in 19 papers)

IMAGE PROCESSING, PATTERN RECOGNITION

Maximum-likelihood dissimilarities in image recognition with deep neural networks

A. V. Savchenko

National Research University Higher School of Economics, Nizhny Novgorod, Russia
References:
Abstract: In this paper we focus on the image recognition problem in the case of a small sample size based on the nearest neighbor rule and matching high-dimensional feature vectors extracted with a deep convolutional neural network. We propose a novel recognition algorithm based on the maximum likelihood method for the joint density of dissimilarities between the observed image and available instances in a training set. This likelihood is estimated using the known asymptotically normally distribution of the Jensen-Shannon divergence between image features, if the latter can be treated as probability density estimates. This asymptotic behavior is in agreement with the well-known experimental estimates of the distributions of dissimilarity distances between the high-dimensional vectors. The experimental study in unconstrained face recognition for the LFW (Labeled Faces in the Wild) and YTF (YouTube Faces) datasets demonstrated that the proposed approach makes it possible to increase the recognition accuracy by 1-5% when compared with conventional classifiers.
Keywords: statistical pattern recognition, image processing, deep convolutional neural networks, maximum-likelihood directed enumeration method, unconstrained face identification.
Funding agency Grant number
Ministry of Education and Science of the Russian Federation МД-306.2017.9
Russian Science Foundation 14-41-00039
The work is supported by the Russian Federation President's grant No. МД-306.2017.9 and Laboratory of Algorithms and Technologies for Network Analysis, National Research University Higher School of Economics. The research in Section 2 was supported by RSF (Russian Science Foundation) project No. 14-41-00039.
Received: 10.01.2017
Accepted: 11.05.2017
Document Type: Article
Language: Russian
Citation: A. V. Savchenko, “Maximum-likelihood dissimilarities in image recognition with deep neural networks”, Computer Optics, 41:3 (2017), 422–430
Citation in format AMSBIB
\Bibitem{Sav17}
\by A.~V.~Savchenko
\paper Maximum-likelihood dissimilarities in image recognition with deep neural networks
\jour Computer Optics
\yr 2017
\vol 41
\issue 3
\pages 422--430
\mathnet{http://mi.mathnet.ru/co402}
\crossref{https://doi.org/10.18287/2412-6179-2017-41-3-422-430}
Linking options:
  • https://www.mathnet.ru/eng/co402
  • https://www.mathnet.ru/eng/co/v41/i3/p422
  • This publication is cited in the following 19 articles:
    Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Computer Optics
    Statistics & downloads:
    Abstract page:1308
    Full-text PDF :116
    References:47
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024