EVOLUTIONARY MATCHING METHOD FOR FACE RECOGNITION USING NEURAL NETWORKS
Section: 1. ARTIFICIAL INTELLIGENCE SYSTEMS
Authors:
1.
Moscow, Russian Federation
2.
Moscow, Russian Federation
Type:
Сonference article
Published:
19.12.2020
Subject area:
VAC 01.01.2000 Математика
UDK 51 Математика
BBK 22 Физико-математические науки
UDK 51 Математика
BBK 22 Физико-математические науки
Language:
Russian
Keywords:
evolutionary matching, face recognition, neural networks
Abstract (English):
The problem of formalizing and automating the process of recognizing human faces was touched upon at the earliest stages of the development of image recognition systems and remains relevant to this day. Moreover, over the past ten years, the number of scientific studies and publications on this topic has increased several times, which indicates an increase in the urgency of this problem. This can be explained by the fact that modern computing technology opens up new possibilities for its application in various fields, and, accordingly, a lot of applied problems have appeared that require their speedy resolution. One of the practical applications of the pattern recognition theory is face recognition, the task of which is to automatically localize a face in an image and identify a person by face. The interest in the procedures underlying the process of localization and face recognition is quite significant due to the variety of their practical applications in areas such as security systems, verification, forensic examination, teleconferences, computer games, etc. For example, the face recognition system developed at Beijing Tsinghua University has been certified by the Chinese Ministry of Public Security for use in public places. Omron Japan, which specializes in recognition, automation and control technologies, has developed a human face recognition system for mobile phones. Riya, founded by a group of specialists in facial recognition algorithms from Stanford University, has begun open testing of a Web service for contextual search of facial images in digital photo albums. The abundance of such examples indicates the practical importance and relevance of face recognition methods.
The problem of formalizing and automating the process of recognizing human faces was touched upon at the earliest stages of the development of image recognition systems and remains relevant to this day. Moreover, over the past ten years, the number of scientific studies and publications on this topic has increased several times, which indicates an increase in the urgency of this problem. This can be explained by the fact that modern computing technology opens up new possibilities for its application in various fields, and, accordingly, a lot of applied problems have appeared that require their speedy resolution. One of the practical applications of the pattern recognition theory is face recognition, the task of which is to automatically localize a face in an image and identify a person by face. The interest in the procedures underlying the process of localization and face recognition is quite significant due to the variety of their practical applications in areas such as security systems, verification, forensic examination, teleconferences, computer games, etc. For example, the face recognition system developed at Beijing Tsinghua University has been certified by the Chinese Ministry of Public Security for use in public places. Omron Japan, which specializes in recognition, automation and control technologies, has developed a human face recognition system for mobile phones. Riya, founded by a group of specialists in facial recognition algorithms from Stanford University, has begun open testing of a Web service for contextual search of facial images in digital photo albums. The abundance of such examples indicates the practical importance and relevance of face recognition methods.
Keywords:
evolutionary matching, face recognition, neural networks
evolutionary matching, face recognition, neural networks
1. Protasov V.I. Konstruirovanie metasistemnyh perehodov. - M.: Izd-vo instituta fiziko-tehnicheskoy informatiki, 2009. - 186 s.
2. Rasch G. Probabilistic Models for Some Intelligence and Attainment Tests /Expanded Edition, with Foreword and Afterword by B.D. Wright. Chicago: University of Chicago Press, 1980.
3. Sondorcet, marquis Marie-Jean-Antoine-Nicolas de Caritat. Essai sur l’application de l’analyse à la probabilité des décisions rendues à la pluralité des voix. Imprimerie Royale, Paris, 1785.
4. V.I. Protasov. Metod evolyucionnogo soglasovaniya resheniy. Komp'yuternaya i matematicheskaya model'. 2011g. 360-379 s.
