This paper analyzes the problems of document image recognition and the existing solutions.
Document recognition algorithms have been studied for quite a long time, but despite this …

In the paper we introduce a novel bipolar morphological neuron and bipolar morphological
layer models. The models use only such operations as addition, subtraction and maximum …

Two methods of convolution-complexity reduction, and therefore acceleration of
convolutional neural network processing, are introduced. Convolutional neural networks …

This paper considers a convolutional neural network transformation that reduces
computation complexity and thus speedups neural network processing. Usage of …

In this paper we propose a dynamic programming solution to the template-based recognition
task in OCR case. We formulate a problem of optimal position search for complex objects …

In this paper we consider speedup potential of morphological image filtering on ARM
processors. Morphological operations are widely used in image analysis and recognition …

In this paper we consider speedup potential of morphological image filtering on ARM
processors. Morphological operations are widely used in image analysis and recognition …

Рассматривается задача сегментации изображений текстовых фрагментов с
известными ограничениями на взаимное расположение элементов. Рассматривается …

This paper considers a convolutional neural network transformation that reduces
computation complexity and thus speedups neural network processing. Usage of …