?
Directed enumeration method in image recognition
Pattern Recognition. 2012. Vol. 45. No. 8. P. 2952–2961.
The article is devoted to the problem of image recognition in real-time applications with a large database containing hundreds of classes. The directed enumeration method as an alternative to exhaustive search is examined. This method has two advantages. First, it could be applied with measures of similarity which do not satisfy metric properties (chi-square distance, Kullback-Leibler information discrimination, etc). Second, the directed enumeration method increases recognition speed even in the most difficult cases which seem to be very important in practical terms. In these cases many neighbors are located at very similar distances. In this paper we present the results of an experimental study of the directed enumeration method with comparison of color- and gradient-orientation histograms in solving the problem of face recognition with well-known datasets (Essex, FERET). It is shown that the proposed method is characterized by increased computing efficiency of automatic image recognition (3-12 times in comparison with a conventional nearest neighbor classifier).
Language:
English
Keywords: распознавание изображенийметод направленного перебораImage recognitionlarge databaseapproximate nearest neighbor classificationdirected enumeration methodcolor histogramgradient orientation histogramбольшая база данных эталоновприближенные методы ближайшего соседагистограмма цветагистограмма направления градиента
Shchuka I., Miftakhov S., Patrushev V. et al., , in: 2020 International Conference Engineering and Telecommunication (En&T).: IEEE, 2020. P. 1–5.
The paper presents a method for meal recognition, ingredient extraction and recipe suggestion in the Russian language. The proposed algorithm consists of several consecutive stages. On the first stage the model extracts a list of ingredients from a photo of the dish, based on which recipes on the second stage are selected. Two ingredient extraction ...
Added: June 14, 2026
Гущина В. А., / Series chemrxiv-2023-vpzhz-v2 "ChemRxiv". 2023.
All-inorganic perovskite CsPbBr3 and Cs4PbBr6 nanoparticles are being intensively studied due to their unique properties and wide range of applications; however, however, the nature of their optical properties is not yet fully understood due to the difficulty of synthesis of singlephase nanoparticles. In this article we describe the features of the synthesis of single-phase particles ...
Added: May 14, 2026
Pilé I., Deng Y., Shchur L., / Series arXiv "math". 2026. No. 2604.10254.
We investigate the spatial overlap of successive spin configurations in Markov chain Monte Carlo simulations using the local Metropolis algorithm and the Svendsen-Wang and Wolff cluster algorithms. We examine the dynamics of these algorithms for two models in different universality classes: the Ising model and the Potts model with three components. The overlap of two ...
Added: April 20, 2026
Storchevoy M., Mylnikov L., Чернышев В. В. et al., / SSRN. Серия "Working Papers". 2025.
Внимание к охране природы принимает все большую значимость для бизнеса с одной стороны в связи с ужесточением в природоохранном законодательстве, а с другой в связи с использованием ESG рейтингов при принятии решений о коммерческой деятельности компаний. Составление рейтинга LLM систем, способных оказывать консультационные услуги в области природоохраны и ESG, позволяет осуществить выбор такой системы для ...
Added: September 18, 2025
Sokolov B., / Series OSF "SocArXiv". 2025.
This paper reviews various estimands used in modern scientific and applied research to operationalize causal inquiries within the Rubin Causal Model framework. I first introduce the most widely utilized average treatment effects, such as ATE, ATT, and ATC. I then describe their popular extensions, including those targeting local and conditional treatment effects; causal interactions and mediation; effects ...
Added: May 6, 2025
Tsybina Y., Kastalskiy I., Krivonosov M. et al., Neural Computing and Applications 2023 Vol. 34 No. 11 P. 9147 –9160
Modeling the neuronal processes underlying short-term working memory remains the focus of many theoretical studies in neuroscience. In this paper, we propose a mathematical model of a spiking neural network (SNN) which simulates the way a fragment of information is maintained as a robust activity pattern for several seconds and the way it completely disappears ...
Added: April 9, 2025
Ovanesova Y., Moshiashvili M. M., Типсина Н. О., / Series "Working Papers". 2021.
The purpose of this article is to analyze and evaluate the cultural characteristics of the digital ecosystem product teams leaders and operational efficiency. Using binary choice models (the main conclusions were made on the basis of logit regressions), has been found a significant negative relationship between the probability of achieving business goals by a team ...
Added: February 17, 2025
Kagan M., Silkin V. M., Efremov D. V., / Series arXiv "math". 2024. No. 2411.12836.
In this study, we analyze the dielectric function of high-Tc cuprates as a function of doping level, taking into account the full energy band dispersion within the CuO2 monolayer. In addition to the conventional two-dimensional (2D) gapless plasmon mode, our findings reveal the existence of three anomalous branches within the plasmon spectrum. Two of these branches ...
Added: November 27, 2024
Mirkin B., Parinov A., Halynchyk M. et al., / Series WP7 "Математические методы анализа решений в экономике, бизнесе и политике". 2024.
Recently, k-means clustering has been extended to the so-called interval data. In contrast to conventional data case, the interval data feature values are intervals rather than single reals. This paper further explores the least-squares criterion for k-means clustering to tackle the issue of initialization, that is, finding a proper set of initial cluster centers at ...
Added: November 26, 2024
Influence of anisotropy on the study of critical behavior of spin models by machine learning methods
Sukhoverkhova D., Shchur L., / Series arXiv "math". 2024. No. 2410.14523.
In this paper, we applied a deep neural network to study the issue of knowledge transferability between statistical mechanics models. The following computer experiment was conducted. A convolutional neural network was trained to solve the problem of binary classification of snapshots of the Ising model's spin configuration on a two-dimensional lattice. During testing, snapshots of ...
Added: October 21, 2024
Mozolenko V., Fadeeva Marina, Shchur L., / Series arXiv "math". 2024. No. 2405.10865.
The development of new algorithms for simulations in physics is as important as the development of new analytical methods. In this paper we present a comparison of the recently developed microcanonical population annealing (MCPA) algorithm with the rather mature Wang-Landau algorithm. The comparison is performed on two cases of the Potts model exhibiting a first ...
Added: May 20, 2024
Kagan M., Аксёнов С. В., / Series Research Square "Research Suqare". 2024. No. 1.
We study different resonances (first of all of the Fano type) in the interference device formed by the Aharonov-Bohm ring with superconducting (SC) wire in the topologically nontrivial state playing a role of a bridge between top and bottom arms. We analyze Majorana modes on the ends of the SC wire and show that the collapse of the ...
Added: April 10, 2024
Ребров Я. В., Glazkov V., Murtazoev A. F. et al., / Series cond-mat "arxiv.org". 2023.
Nabokoite family compounds ACu7(TeO4)(SO4)5Cl (A=Na, K, Cs, Rb) are one of the candidates for the evasive spin-liquid state predicted for highly-frustrated square kagome lattice (SKL). Their magnetic subsystem includes SKL layers decorated by additional copper ions. All members of this family are characterized by quite high Curie-Weiss temperatures (∼80−200 K), but magnetic ordering was reported ...
Added: January 29, 2024
Shurakov A., Kaurova N., Belikov I. et al., / Series Physics "arxiv.org". 2022.
In this paper, we report on the method of nondestructive quality control that can be used in fabrication of GaAs high-speed electronics. The method relies on the surface potential mapping and enables rigid in vivo analysis of transport properties of an active electronic device incorporated into a complex integrated circuit. The study is inspired by ...
Added: September 15, 2023
Pugach N., Safonchik M. O., Belotelov V. et al., / Series "cond-mat". 2022. No. 2110.00369.
A detailed investigation of a superconducting spin-triplet valve is presented. This spin-valve consists of a superconducting film covering a metal with an intrinsic spiral magnetic order, which could result from competing isotropic exchanges or, if the crystal lattice breaks central symmetry, from asymmetric Dzyaloshinskii-Moriya exchange. Depending on the anisotropy, such a metal may change its ...
Added: November 16, 2022
Novikov S. V., / Series cond-mat "arxiv.org". 2022. No. 2209.14955.
Charge transport in amorphous semiconductors having spatially correlated exponential density of states (DOS) has been considered for the arbitrary behavior of the correlation function of random energies. Average carrier velocity is exactly calculated for the quasi-equilibrium (nondispersive) transport regime. For the symmetric exponential DOS with exponential tails for low and high energies and non-positive correlation ...
Added: November 1, 2022
Головин Р. Д., Zunin V., В кн.: Межвузовская научно-техническая конференция студентов, аспирантов и молодых специалистов имени Е.В. Арменского. Материалы конференции.: М.: МИЭМ НИУ ВШЭ, 2021. С. 120–122.
В работе проводится обзор различных способов реализации нейронной сети для распознавания изображения на примере набора данных MNIST. Дается анализ используемых библиотек и методов их применения в области распознавания объектов. ...
Added: September 25, 2022
Savchenko A., Belova N. S., Expert Systems with Applications 2022 Vol. 207 Article 117885
In this paper, the computational complexity of the probabilistic neural network for the classification of high-dimensional data is improved. At first, the class probability densities are estimated by using only a few principal components of an observed point. The Gaussian–Parzen kernel is replaced by the orthogonal series estimates of class-conditional densities for each principal component using the Fourier series to speed ...
Added: June 29, 2022
Anna Beketova, Makarov I., , in: Advances in Computational Intelligence: 16th International Work-Conference on Artificial Neural Networks, IWANN 2021, Virtual Event, June 16–18, 2021, Proceedings, Part II.: Cham: Springer, 2021. Ch. 3 P. 28–42.
*Реализация соц. сети Instagram запрещена на территории России по основаниям осуществления экстремистской деятельности.
Instagram is one of the most popular photos sharing services. For more convenient content search people use hashtags (#nature, #love, etc.) in posts with photos. The author’s aim is to make hashtag prediction possible and convenient for users.
The paper provides a reader with ...
Added: September 1, 2021
Savchenko A., Information Sciences 2021 Vol. 560 P. 370–385
A novel image recognition algorithm based on sequential three-way decisions is introduced to speed up the inference in a convolutional neural network. In contrast to the majority of existing studies, our approach does not require a special procedure to train a neural network, and thus it can be used with arbitrary architectures including pre-trained convolutional ...
Added: February 25, 2021
Savchenko A., Записки научных семинаров ПОМИ РАН 2021 Т. 499 С. 267–283
In this paper fast image recognition techniques based on statistical sequential analysis are discussed. We examine the possibility to sequentially process the principal components and organize a convolutional neural net- work with early exits. Particular attention is paid to sequentially learn multi-task lightweight neural network model to predict several facial at- tributes (age, gender and ...
Added: January 27, 2021
Savchenko A., , in: Proceedings of International Joint Conference on Neural Networks 2020 (IJCNN 2020).: Piscataway: IEEE, 2020. P. 1–8.
In this paper the problem of high computational complexity of deep convolutional nets in image recognition is considered. An existing framework of adaptive neural networks is extended by appending the separate classifier to intermediate layers. The hierarchical representations of the input image are sequentially analyzed. If the first classifier returns rather high confidence score, the ...
Added: October 15, 2020
Savchenko A., IEEE Transactions on Neural Networks and Learning Systems 2020 Vol. 31 No. 2 P. 651–660
If the training data set in image recognition task is not very large, the feature extraction with a convolutional neural network is usually applied. Here, we focus on the nonparametric classification of extracted feature vectors using the probabilistic neural network (PNN). The latter is characterized by the high runtime and memory space complexity. We propose ...
Added: November 1, 2019
Savchenko A., Information Sciences 2019 Vol. 489 P. 18–36
The paper addresses the issue of insufficient speed of image recognition methods if the number of classes is rather large. We propose the novel algorithm based on sequential three-way decisions and a formal description of granular computing. Each image is associated with principal component scores of the high-dimensional features extracted by deep convolution neural network. ...
Added: March 20, 2019