<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE root>
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" article-type="research-article" dtd-version="1.2" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">Journal of Computer and System Sciences International</journal-id><journal-title-group><journal-title xml:lang="en">Journal of Computer and System Sciences International</journal-title><trans-title-group xml:lang="ru"><trans-title>Известия Российской академии наук. Теория и системы управления</trans-title></trans-title-group></journal-title-group><issn publication-format="print">0002-3388</issn><issn publication-format="electronic">3034-6444</issn><publisher><publisher-name xml:lang="en">The Russian Academy of Sciences</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">699207</article-id><article-id pub-id-type="doi">10.7868/S3034543X25060149</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>IMAGE RECOGNITION AND IMAGE PROCESSING</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>РАСПОЗНАВАНИЕ ОБРАЗОВ И ОБРАБОТКА ИЗОБРАЖЕНИЙ</subject></subj-group><subj-group subj-group-type="article-type"><subject>Research Article</subject></subj-group></article-categories><title-group><article-title xml:lang="en">INFORMATION-THEORETIC BOUNDS TO ACCURACY FOR BIOMETRIC IDENTIFICATION IN METRIC SPACES OF DATA REPRESENTATIONS</article-title><trans-title-group xml:lang="ru"><trans-title>ТЕОРЕТИКО-ИНФОРМАЦИОННЫЕ ГРАНИЦЫ ТОЧНОСТИ БИОМЕТРИЧЕСКОЙ ИДЕНТИФИКАЦИИ В МЕТРИЧЕСКИХ ПРОСТРАНСТВАХ ПРЕДСТАВЛЕНИЙ ДАННЫХ</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><name-alternatives><name xml:lang="en"><surname>Lange</surname><given-names>A. M</given-names></name><name xml:lang="ru"><surname>Ланге</surname><given-names>А. М</given-names></name></name-alternatives><email>lange_am@mail.ru</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><name-alternatives><name xml:lang="en"><surname>Lange</surname><given-names>M. M</given-names></name><name xml:lang="ru"><surname>Ланге</surname><given-names>М. М</given-names></name></name-alternatives><email>lange_mm@mail.ru</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><name-alternatives><name xml:lang="en"><surname>Paramonov</surname><given-names>S. V</given-names></name><name xml:lang="ru"><surname>Парамонов</surname><given-names>С. В</given-names></name></name-alternatives><email>psypobox@gmail.com</email><xref ref-type="aff" rid="aff1"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">Federal Research Center “Computer Science and Control” RAS</institution></aff><aff><institution xml:lang="ru">ФИЦ РАН</institution></aff></aff-alternatives><pub-date date-type="pub" iso-8601-date="2025-12-15" publication-format="electronic"><day>15</day><month>12</month><year>2025</year></pub-date><issue>6</issue><issue-title xml:lang="en">NO6 (2025)</issue-title><issue-title xml:lang="ru">№6 (2025)</issue-title><fpage>146</fpage><lpage>154</lpage><history><date date-type="received" iso-8601-date="2025-12-23"><day>23</day><month>12</month><year>2025</year></date></history><permissions><copyright-statement xml:lang="en">Copyright ©; 2025, Russian Academy of Sciences</copyright-statement><copyright-statement xml:lang="ru">Copyright ©; 2025, Российская академия наук</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="en">Russian Academy of Sciences</copyright-holder><copyright-holder xml:lang="ru">Российская академия наук</copyright-holder><ali:free_to_read xmlns:ali="http://www.niso.org/schemas/ali/1.0/" start_date="2026-12-22"/></permissions><self-uri xlink:href="https://rjsvd.com/0002-3388/article/view/699207">https://rjsvd.com/0002-3388/article/view/699207</self-uri><abstract xml:lang="en"><p>For both datasets of biometric objects given by images and an ensemble of the different modality datasets, the lower bounds to error probability of person identification subject to a fixed amount of information have been investigated. The bounds are constructed using a probabilistic object classification model in metric spaces of the object representations. These bounds are independent on decision algorithms and they are formed by the inverses of the rate-distortion functions for the model of discrete source coding with Hamming distortion when the source letters are transmitted over a noisy channel. The difference between a unit and any obtained lower bound to error probability produces an appropriate upper bound to accuracy of person identification depending on a given amount of processed information in a given dataset of the object representations. The obtained bounds are useful for estimating an efficiency of the decision algorithms in terms of deviations of the algorithm error probability or accuracy relative to the boundary values subject to a given average amount of information for making the decisions.</p></abstract><trans-abstract xml:lang="ru"><p>Исследуются нижние границы вероятности ошибки идентификации персон при заданном количестве анализируемой информации на множествах биометрических объектов, заданных изображениями, и на ансамбле множеств различной модальности. Границы вероятности ошибки строятся в рамках вероятностной модели классификации объектов в метрических пространствах их представлений. Полученные границы не зависят от решающих алгоритмов и являются обращениями функций “скорость–погрешность” (rate–distortion functions) для модели кодирования дискретных источников с погрешностью по мере Хемминга по сообщениям на выходе канала с искажениями. Отклонение нижней границы вероятности ошибки от единицы дает верхнюю границу точности идентификации как функцию количества анализируемой информации на заданном множестве объектов. Построенные границы полезны для анализа эффективности алгоритмов принятия решений в терминах отклонения вероятности ошибки или точности алгоритма относительно граничных значений при заданных значениях количества анализируемой информации.</p></trans-abstract><kwd-group xml:lang="en"><kwd>biometric identification</kwd><kwd>classification</kwd><kwd>error probability</kwd><kwd>accuracy</kwd><kwd>mutual information</kwd><kwd>rate–distortion function</kwd><kwd>modality</kwd><kwd>ensemble of sources</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>биометрическая идентификация</kwd><kwd>классификация</kwd><kwd>вероятность ошибки</kwd><kwd>точность</kwd><kwd>взаимная информация</kwd><kwd>функция “скорость–погрешность”</kwd><kwd>модальность</kwd><kwd>ансамбль источников</kwd></kwd-group></article-meta></front><body></body><back><ref-list><ref id="B1"><label>1.</label><mixed-citation>Gallager R.G. Information Theory and Reliable Communication. N.Y.: Wiley and Sons, 1968. 588 p.</mixed-citation></ref><ref id="B2"><label>2.</label><mixed-citation>Dobrushin R.L., Tsybakov B.S. Information Transmission with Additional Noise // IRE Transaction on Information Theory. 1962. V. 8(5). P. 293–304. DOI:10.1109/TIT.1962.1057738.</mixed-citation></ref><ref id="B3"><label>3.</label><mixed-citation>Sethi I.K., Sarvarayudd G.P.R. Hierarchical Classifier Design Using Mutual Information // IEEE Transactions on Pattern Analysis and Machine Intelligence. 1982. V. 4(4). P. 441–445.</mixed-citation></ref><ref id="B4"><label>4.</label><mixed-citation>Rigau J., Fekxas M., Sbert M. An Information Theoretic Framework for Image Segmentation // Intern. Conf. on Image Processing. ICIP '04, Singapura: IEEE, 2005. AN: 8436089. DOI:10.1109/ICIP.2004.1419518.</mixed-citation></ref><ref id="B5"><label>5.</label><mixed-citation>Lange M.M., Lange A.M. Information Theoretic Lower Bounds to Error Probability for the Models of Noisy Discrete Source Coding and Object Classification // Pattern Recognition and Image Analysis. 2022. V. 32(3). P. 570-574. DOI:10.1134/S105466182203021X.</mixed-citation></ref><ref id="B6"><label>6.</label><mixed-citation>Ланге M.M., Ланге A.M. Теоретико-информационные границы точности кодирования сообщений и распознавания образов по ансамблям данных // Компьютерная оптика. 2024. Т. 48(3). С. 460–470. DOI:10.18287/2412-6179-CO-1362</mixed-citation></ref><ref id="B7"><label>7.</label><mixed-citation>Brown G., Pocock A., Zhao M.J., Luj'an M. Conditional Likelihood Maximization: A Unifying Framework for Information Theoretic Feature Selection // J. Machine Learning Research. 2012. V. 13(8). P. 27–66.</mixed-citation></ref><ref id="B8"><label>8.</label><mixed-citation>Fleuret F. Fast Binary Feature Selection with Conditional Mutual Information // J. Machine Learning Research. 2004. V. 5. P. 1531–1555.</mixed-citation></ref><ref id="B9"><label>9.</label><mixed-citation>Ланге A.M., Ланге M.M., Парамонов С.В. О соотношении взаимной информации и вероятности ошибки в задаче классификации данных // ЖВМ и МФ. 2021. Т. 61(7). С. 1129–1205. DOI:10.31857/S0044466921070115.</mixed-citation></ref><ref id="B10"><label>10.</label><mixed-citation>Duin R.P.W., de Ridder D., Tax D.M.J. Experiments with a Featureless Approach to Pattern Recognition // Pattern Recognition Letters. 1997. V. 18. P. 1159–1166.</mixed-citation></ref><ref id="B11"><label>11.</label><mixed-citation>Dovenko S.D. Recovering Missing Values of Paired Comparisons // Pattern Recognition and Image Analysis. 2022. V. 32(3). P. 522–527. DOI:10.1134/S1054661822030099.</mixed-citation></ref><ref id="B12"><label>12.</label><mixed-citation>Sueño H.T., Gerardo B.D., Medina R.P. Multi-class Document Classification Using Support Vector Machine (SVM) Based on Improved Naive Bayes Vectorization Technique // Intern. J. Advanced Trends in Computer Science and Engineering. 2020. V. 9(3). P. 3937–3944. DOI:10.30534/ijatcse/2020/216932020.</mixed-citation></ref><ref id="B13"><label>13.</label><mixed-citation>Xu X., Huang S.L., Zheng L., Wornell G.W. An Information Theoretic Interpretation to Deep Neural Networks // Entropy. 2022. V. 24(1). P. 135. DOI:10.3390/e24010135.</mixed-citation></ref><ref id="B14"><label>14.</label><mixed-citation>Cover T.M., Thomas J.A. Elements of Information Theory. 2<sup>nd</sup> ed. N.Y.: Wiley and Sons, 2006. 748 p.</mixed-citation></ref><ref id="B15"><label>15.</label><mixed-citation>Distance Matrices for Face Dataset. Available: https://github.com/lange-am/tree_distance_matricies/blob/main/treedist_faces_euclidean2.txt</mixed-citation></ref><ref id="B16"><label>16.</label><mixed-citation>Distance Matrices for Signature Dataset. Available: https://github.com/lange-am/tree_distance_matricies/blob/main/treedist_signs_euclidean2.txt</mixed-citation></ref></ref-list></back></article>
