no code implementations • 18 May 2022 • Anton Trusov, Elena Limonova, Dmitry Nikolaev, Vladimir V. Arlazarov
In this paper, we propose novel fast algorithms of ternary, ternary-binary, and binary matrix multiplication for mobile devices with ARM architecture.
no code implementations • 1 Jul 2021 • Konstantin Bulatov, Ekaterina Emelianova, Daniil Tropin, Natalya Skoryukina, Yulia Chernyshova, Alexander Sheshkus, Sergey Usilin, Zuheng Ming, Jean-Christophe Burie, Muhammad Muzzamil Luqman, Vladimir V. Arlazarov
Identity documents recognition is an important sub-field of document analysis, which deals with tasks of robust document detection, type identification, text fields recognition, as well as identity fraud prevention and document authenticity validation given photos, scans, or video frames of an identity document capture.
1 code implementation • 15 Sep 2020 • Elena Limonova, Daniil Alfonso, Dmitry Nikolaev, Vladimir V. Arlazarov
In the paper, we introduce a bipolar morphological ResNet (BM-ResNet) model obtained from a much more complex ResNet architecture by converting its layers to bipolar morphological ones.
no code implementations • 14 Sep 2020 • Anton Trusov, Elena Limonova, Dmitry Slugin, Dmitry Nikolaev, Vladimir V. Arlazarov
We introduce an efficient implementation of 4-bit matrix multiplication for quantized neural networks and perform time measurements on a mobile ARM processor.
no code implementations • 6 Aug 2020 • Daniil V. Tropin, Sergey A. Ilyuhin, Dmitry P. Nikolaev, Vladimir V. Arlazarov
This paper considers arbitrary document detection performed on a mobile device.
1 code implementation • 6 Aug 2020 • Konstantin Bulatov, Nadezhda Fedotova, Vladimir V. Arlazarov
In this paper, we consider a task of stopping the video stream recognition process of a text field, in which each frame is recognized independently and the individual results are combined together.
no code implementations • 29 Jan 2020 • Elena Andreeva, Vladimir V. Arlazarov, Oleg Slavin, Aleksey Mishev
In this work the methods of comparison of digitized copies of administrative documents were considered.
no code implementations • 2 Dec 2019 • Igor Janiszewski, Dmitry Slugin, Vladimir V. Arlazarov
The paper proposes an approach to training a convolutional neural network using information on the level of distortion of input data.
no code implementations • 5 Nov 2019 • Elena Limonova, Daniil Matveev, Dmitry Nikolaev, Vladimir V. Arlazarov
To demonstrate efficiency of the proposed model we consider classical convolutional neural networks and convert the pre-trained convolutional layers to the bipolar morphological layers.
1 code implementation • 9 Oct 2019 • Konstantin Bulatov, Boris Savelyev, Vladimir V. Arlazarov
This paper is directed on extending the stopping method based on next integrated recognition result modelling, in order for it to be used within a string result recognition model with per-character alternatives.
1 code implementation • 9 Oct 2019 • Konstantin Bulatov, Daniil Matalov, Vladimir V. Arlazarov
The portfolio of methods and algorithms for solving such tasks as face detection, document detection and rectification, text field recognition, and other, is growing, and the scarcity of datasets has become an important issue.
7 code implementations • 16 Jul 2018 • Vladimir V. Arlazarov, Konstantin Bulatov, Timofey Chernov, Vladimir L. Arlazarov
The main goal of this paper is to present a dataset.