|
This article is cited in 7 scientific papers (total in 7 papers)
IMAGE PROCESSING, PATTERN RECOGNITION
Classification of rare traffic signs
B. V. Faizova, V. I. Shakhuroa, V. V. Sanzharovba, A. S. Konouchineca a Lomonosov Moscow State University, Moscow, Russia
b Gubkin RSU of Oil and Gas
c NRU Higher School of Economics, Moscow, Russia
Abstract:
The paper studies the possibility of using neural networks for the classification of objects that are few or absent at all in the training set. The task is illustrated by the example of classification of rare traffic signs. We consider neural networks trained using a contrastive loss function and its modifications, also we use different methods for generating synthetic samples for classification problems. As a basic method, the indexing of classes using neural network features is used. A comparison is made of classifiers trained with three different types of synthetic samples and their mixtures with real data. We propose a method of classification of rare traffic signs using a neural network discriminator of rare and frequent signs. The experimental evaluation shows that the proposed method allows rare traffic signs to be classified without significant loss of frequent sign classification quality.
Keywords:
traffic sign classification, synthetic training samples, neural networks, image recognition, image transforms, neural network compositions.
Received: 22.07.2019 Accepted: 11.10.2019
Citation:
B. V. Faizov, V. I. Shakhuro, V. V. Sanzharov, A. S. Konouchine, “Classification of rare traffic signs”, Computer Optics, 44:2 (2020), 236–243
Linking options:
https://www.mathnet.ru/eng/co785 https://www.mathnet.ru/eng/co/v44/i2/p236
|
Statistics & downloads: |
Abstract page: | 215 | Full-text PDF : | 119 | References: | 31 |
|