The authors have considered the effect of a training sample composition on the quality of pattern recognition in noise using the Kora, TEMP, R-method and CORAL algorithms. The algorithms are illustrated by the example of the problem of recognition of noisy black-and-white patterns and are compared with the algorithms of morphological analysis of gray-scale patterns [1, 2] and morphological analysis of Lambert objects [3]. This paper continues the research described in [4].
Department of Computer Methods in Physics, Faculty of Physics, Moscow State University, Leninskie Gory, Moscow, 119992, Russia
Science News of the Faculty of Physics, Lomonosov Moscow State University
This new information publication, which is intended to convey to the staff, students and graduate students, faculty colleagues and partners of the main achievements of scientists and scientific information on the events in the life of university physicists.