Automatic optical recognition of documents is a traditional function of modern document
processing systems. In this context, recognition represents a complex process which …

In this paper we introduce a novel neural network architecture based on Fast Hough
Transform layer. The layer of this type allows our neural network to accumulate features from …

Identity documents recognition is far beyond classical optical character recognition
problems. Automated ID document recognition systems are tasked not only with the …

The majority of document image analysis systems use a document skew detection algorithm
to simplify all its further processing stages. A huge amount of such algorithms based on …

This work focuses on the Fast Hough Transform (FHT) algorithm proposed by ML Brady. We
propose how to modify the standard FHT to calculate sums along lines within any given …

The work briefly describes the activities of the Moscow Scientific School of Digital Image
Processing, formed on the basis of a team led by Professor VL Arlazarov. This school is …

This paper overviews modern computing devices based on the Elbrus VLIW architecture
and presents experimental results for the performance evaluation of the Smart IDReader …

В работе рассматривается задача детектирования пешеходных переходов для
определения собственного положения автономным транспортным средством (ТС) на …

Рассматривается задача двумерной линейной регрессии для зашумленных данных.
Последние представляют собой пары координат, возвращаемых пространственно …

Общепринято применение проективной нормализации (частный случай
ортокоррекции) к фотографиям документов для их дальнейшего оптического …